Astra can, without tooling, determine what games small networks are trained on, can edit the weights of networks directly to improve outcomes, and can hand edit a small qwen model to improve its math skills by like 5x.
I'm shook. If you'd asked me this morning whether LLMs have native understanding of their weights that is less than human <-> neuron understanding, the same as human or more than human, I would have said "same to less" depending on definitions.
No human can go edit a brain to become better at math. This is just very, very surprising to me and extremely interesting. I would guess this upsets quite a number of interp theories and philosophical takes on what's going on with these networks.
I think the "taught qwen math" part is not exactly correct though, even if the post makes it sound like that. Qwen already knew math, but it was bugging out and getting into an infinite loop when it tried to solve the problems (85 of its first 96 answers hit the token limit). With numpy and pytorch, Astra found where the loop was happening and fixed it.
They also tried the same with Gemma 3 270M, which doesn't loop and is just bad at math, and Astra couldn't improve it. Still impressive, but it's more in the realm of what I'd expect, given labs are probably training their models on ML research and interpretability work.
I agree, this is important context. They call it out explicitly. However, even identifying clusters that specialize in certain fields automatically and then finding and fixing learning “errors” is incredibly impressive to me. Especially for medium sized local models between 20B an 70B parameters, this could yield huge capability and efficiency improvements, not to speak of the potentially enormous downstream effects that come with interpretability.
In fact qwen knows much better math than their final fixed model. The nonthinking qwen 0.6B parameter model had 55.2% correct on math-500 vs their final improved 48.1% fixed-reasoning model, both with a 32k context window. The original qwen reasoning model had 77.6% accuracy on same test, though qwen recommends using a much larger context for these benchmarks. I wonder if their broken baseline run with 7.9% accuracy is a vllm or setup bug, but didnt dig into it any deeper.
Oh for sure, it's still really cool. A few months ago I had agents do some interpretability work on GPT-2 small, reproducing the circular weekday/month features from Engels et al., and it's wild how far you can get with just a bit of prompting, given I know very little about LLM internals myself.
LLMs have been used to investigate and improve LLMs for a long time. Drawing parallels to human brains and neurons isn't all that interesting other than as a philosophical abstraction.
The work done in this experiment could have also been done by a sufficiently motivated human with enough time to explore, though obviously we would need more tools to visualize and track things. There have been a lot of interesting LLM introspection tools that allow you to peek into the model and see what's being activated and run experiments to trigger it.
Are you familiar with abliterated or "uncensored" models where weights have been modified to avoid triggering refusal patterns? You take an LLM, create test cases that trigger the refusal pattern, observe weights involved in that response, then tweak those weights until the response is reduced. This is the same type of work, applied to a specific type of error that was impeding math within Qwen. That work can also be done with an LLM in a harness running the experiments. The amazing part here is that Astra was large enough to walk through the problem without other tooling doing it experimentally.
So I don't think your analogy of a human modifying a neuron is quite applicable. LLM weights are not neurons and they've been inspectable, by humans or LLMs in a harness, for a long time.
> The amazing part here is that Astra was large enough to walk through the problem without other tooling doing it experimentally.
To me “amazing” is not the right level of speechlessness. I mean, an LLM is still fundamentally a next token predictor, right? So what does this imply? That weights have some universal properties? E.g., “breakout game weights” always look the same regardless of training and model? Also, how does this meta-understanding of the weights end up in the weights in the first place? Idk, this is mind-blowing to me.
At this point it's either wrong or meaningless to call LLMs "next token predictors". Yes, pretraining involves predicting the next token. But after that you're in the world of RLHF, RLVR, and other post-training.
A model is _sort of_ designed to predict the next token in a string of text. But it's equally accurate to say it's designed to edit code until it passes a suite of unit tests.
Yes, they generate sequentially, so "next token predictor" isn't technically incorrect (which is why I chose the word "meaningless"). But it's pretty clear there's a mechanism inside them that allows them to "plan" what they generate. I might as well call you a next word predictor.
My understanding is that the underlying part is a next token predictor and that's what is "actually" editing the code but the part that decides what to do (to achieve a successful unit test result for example) is a mix of all the things including post training.
Yes, I didn’t mean that literally. Since “attention is all you need” it’s more like “predict the full output in full for this blob of input text”. That doesn’t change the “wtf is going on with the weight understanding bit” in what I wrote.
> it’s more like “predict the full output in full for this blob of input text"
Hm. I would actually go so far as to say "predict" is just the wrong word to use in 2026, as it drags in a picture of what LLMs are that's from the pre RLVR era, and which is frequently used to suggest they have all sorts of limitations that they've now surpassed ("an LLM will never solve a major open mathematics problem, they're just predicting tokens"). These days I tend to use the more neutral phrase "generate the next token"; I'd only say "predict" in the technical context of (say) the pre-training part of the training run where the object is indeed to minimize the cross-entropy loss function by predicting next tokens in existing text. Generating a token with a modern LLM is better described as something like, "given the totality of its training, including not just next token prediction with pre-training but also solving vast numbers of math and coding problems with RLVR, the LLM generates tokens one by one."
Anyhow. I'm not sure the weight understanding is all that strange. (It's impressive, but so are many thing LLMs do these days.) LLMs are very very good at coding and math problems, of which this is one, and in particular, their RLVR training presumably includes many tasks involving neural networks. It's amazing and impressive, I agree, but I'd say less amazing than proving major open theorems in mathematics, which we already know they can do.
Its a stateless function that takes in x amount of words and calculates logits. It is in fact s next token predictor. Its literally nothing more than that.
> “breakout game weights” always look the same regardless of training and model
The prompt told Astral what the input and output layers mean -- that is, how the current state of the game is turned into a vector for matrix multiplication, and how the result of those multiplications is turned into an action to take in-game.
Astral saw that the model was trained on a game where the player is at the bottom of the grid and moves left and right, reward objects live at the top, and there's some not-player-controlled thing moving around in the middle. Astral knows that this type of game is called "breakout."
A model that plays breakout will have meaningful weights for the player being in the bottom row, but not for the player being anywhere else, because the player can't go anywhere else. Astral saw that there were meaningful weights for the player in the bottom row, and nodes representing the player in any other row had low-magnitude noise, so the model had never been trained on the player being anywhere besides the bottom row.
Similarly, breakout has "reward" objects in the top rows, and "there is a reward object at [COORDINATE]" is part of the input layer. Astral saw that the model was trained on reward objects in the top few rows.
>I mean, an LLM is still fundamentally a next token predictor, right?
Yes, but everything, including the human brain, is "fundamentally" some underlying simpler primitives.
>E.g., “breakout game weights” always look the same regardless of training and model?
Wouldn't this be expected to be roughly the case, given NNs that share the same basic architecture to model the same quite simple thing like a breakout game?
This implies that weights are a type of language. Neural networks are good at language because they are good at patterns. They can reason about it because their "reasoning" isn’t how we think. The same goes for how they encode images, their vision is entirely different from ours. That's why adversarial attacks work on them and not on us. We don't see anything change in the image, while the neural network now sees that the dog is a cat.
We're pretty confident that adversarial attacks do work on us, actually—we have entire industries built around it. Some of them even start with "adver-"...
There are classes of adversarial attacks targeting them that don't work as well on us, and vice versa.
Ok? But does that mean that the “weights language” is universal? E.g. same weight patterns mean the same thing regardless of if it’s Kimi, Grok, or Astra?
There could be different patterns that solve the same problem. Just as you can have different algorithms, there could be different weights, but the abstracted result or logic from those weights would be the same.
Take these words I'm writing now, they will be transformed into numbers, then sent to your screen, and then your brain will transform them into analog signals. I bet the neural networks in our brains have "different numbers", but the algorithms that understand language and other concepts are similar and could be universal.
It's like a sorting algorithm, which I can implement in many different ways in just a few dozen lines. If you look at the binary code (so like raw weights) of the compiled program, you will see just a bunch of a different numbers, but if you read the code, in most cases you will understand that it's a sorting algorithm. So it seems they just operate on different levels of abstraction that are not available to our brains.
It’s important to understand that it had pytorch to actually run subsets of the weights. So its more like a dedicated person running the model to find the token it shouldn’t generate, then following the weight chain back up while calculating the NN outputs to find a place where if it changes some weights (again with a lot of testing via pytorch) the result is better.
Its not natively reading the weights in the Matrix “symbols scrolling on a screen” sense. Still bloody impressive and not an outcome I would have bet on!
There's a long standing line of thinking that data compression has something to do with intelligence, or that intelligence may "just" be data compression in some sense.
In the case of models, the almost-theory (hypothesis with a good deal of evidence) is that once the amount of training data exceeds what the model can simply represent internally, the best way to keep improving is to start to "understand" the data. Understand in this case means to form internal control structures and decision systems that represent the data algorithmically rather than just memorizing it.
I put understand in quotes because we don't know how far this goes toward what we call understanding, or whether there's still a lot missing.
Maybe I'm missing something, but isn't training an LLM very well documented? Why wouldn't an LLM be able to read those docs just like it would read Java Spring docs?
Maybe I’m misunderstanding something. The way I read the results, I understand it like this - you give Astra “a bunch of numbers”, and tell it - “hey, this is a net trained on some game? What game is that?” And Astra goes - “Breakout, no doubt!”
To me this is fundamentally different from having ingested a bunch of docs so it now “knows Java” in its weights.
Interesting, it's similar to the way we used to make cheat codes on the 8-bits: dump memory, run test, compare. You had to loop 3-4 times but you'd find the "weight" you were looking for and could fix it (for infinite lives/ammo etc) or increase/decrease.
The math example on Qwen was based on 50 batched iterations, so the model was able to evaluate it's changes on downstream tasks. And the fix was essentially to remove a direction in activation space that causes looping instead of an exit, this was already known to be a thing(all of the jailbreak/unleashed models do this) following Arditi et al. (Refusal in language models is mediated by a single direction, 2024)
So it's not able to insert new knowledge, but it's able to adjust the routing/looping/weighing of existing one.
As I understand, it can replace post-training like LoRA/GRPO, but if it'd cheaper the authors don't go into
Merging a model and a LoRa is insanely cheap, so assuming it didn't use any GPUs to do inspection etc, and just looked at a file on a FS, then I would be willing to say... It's cheaper than training a LoRa if that's the case, assuming Astra didn't take several weeks?
This is the "recursive self-improvement" they've been warning about.
I've always laughed at that phrase, thinking "haven't these things been improving themselves since the very beginning? This is all just iterative gradient descent, each step is a 'self-improvement'", but this really is different.
I wonder if we'll ever discover a new branch of linear algebra or something that allows us to find the optimal weights much more efficiently? Maybe AI will help us discover it?
It doesn't seem like there's room for recursion here though. A smart model can share its smarts with a dumb one, but the ceiling remains unchanged. Perhaps there's juice to squeeze in verifiable dimensions re: software, math, but there are similar ceilings to be found in those places. We can't keep asking harder and harder questions infinitely while remaining able to verify the answers.
It is astounding, but I don't think it's well set up for anything besides faster approaches to existing limits.
I’m just a layman but this feels like a big discovery on par with attention is all you need. For an LLM to have such incredible intuition of weights feels very emergent and unanticipated?
I’m very much surprised but also not. I recently gave Astra a 3D model file and asked Astra to build a viewer for it, and it figured out the data structures in no time. What I mean to say is that AI is insanely good at things that we humans would never do since the work would be too monotonous.
I wouldn’t mind if AI progress would stop right here and now, but I fear it will continue, and increase inequality in society which is contrary to what the CEOs say (as usual).
> What I mean to say is that AI is insanely good at things that we humans would never do since the work would be too monotonous.
In my opinion AI is superior to humans when it comes to pattern recognition in in large amounts of data. For example humans can only hold like 7 distinct numbers in the short term memory and you would require extra context-management (aka writing things down, storing them in a system entry by entry) while the AI can do this effortlessly with huge datasets.
I'd argue this is the core part that enables all this superhuman intelligence.
I think the latest round of models is about to do to CAD the same thing that has been happening to development. I don't know if CAD designers have picked up on this. What happened to dev is probably going to happen to CAD designers soon. I've been having Opus 5.5 design parametric openscad models, and it can do some rather amazing work.
Yesterday I just printed an adapter for my sink siphon. Told GLM-5.3 the problem, it guided me on measuring what it needed to know to build the pipe adapter. Then printed two test rings to confirm the measurements, and an iteration later, it spit out a parametric pipe adapter for me.
Yes! The page posts Astra's reasoning, and it's perfectly intelligible. A clever human with background in mechanistic interpretability could have done pretty much everything in these experiments.
Too much inequality in society is a mortal danger to 1%.
That’s the beauty of the democratic capitalism system. If a government isn’t totalitarian, it naturally seeks to preserve stability thus having to elevate common people, lest they would cease to form a civilized group or simply vote away the politicians.
99% rule the 1% through elections.
There is no better system of checks and balances where opposite engines of greed vector sum to faster and faster abundance for everyone.
Is HN now against western capitalism? I'm confused...
That comment may have been overly preachy, tone deaf[0], and out of place, but it doesn't seem wrong, per se. Or am I missing something?
[0] e.g. elections themselves are so prone to manipulation (exhibit a: Dominion voting machines), previously trusted institutions now lack integrity, the insane power of well-funded NGO networks, etc.
There is another type who confuse ideology with reality. I wonder if you one of those, oh bingo-loving senior dev. Do you also cut people down for being idealists, when the reality of the situation serves you more than the ideal?
Over my ~9 years reading HN daily, I'd say most of the HN community broadly accepts there is no perfect system, just different sets of trade offs, but that history has shown generally democratic systems based on enlightenment values (uniform rule of law, respect for individual civil & property rights, free markets, etc) usually net a better average outcome over the long-run - despite still being very far from perfect.
To paraphrase Winston Churchill, it's the worst system... except for all the others (which are even worse). :-)
In my almost 20 years on HN, for a long time the groupthink was basically standard libertarian-capitalism, worshipping billionaires and big tech companies, and skeptical of anything that could be construed as "socialism".
The last few years, though, while anything "anti-capitalist" or overly critical of some big tech companies that hits the front page gets flagged by bots pretty quickly, the overall feeling I get from the comments is much more skeptical of big tech and is pro-socialism.
Speaking for myself, I think we've become jaded after the constant barrage of big companies spying on us, charging more for less, enshitifying their products, and so on. I used to be optimistic about the future and my prospects, now I'm just hoping I can hold on and keep my health insurance until I retire. I worry about what my school-age kids are going to have to deal with in 5-10 years.
I fear western capitalism has lost its guide rails. We are seeing more and more centralization of wealth, along with unlimited election spending. Its a dark path.
if you lookup playback as a concept, as it relates to the intelligence services, you will understand better what I meant.
my point was only that this is perfect description of the ideology behind western capitalism. there is (so) much more that could be said, but i'm not sure this comment section is the right place for a proper dissection of the very many ways in which this ideal is misconstrued, misdirected and coerced in order to serve interests that are far from ideal, to put it mildly.
since you have taken the time to ask a question, albeit a rather weak one, i will attempt a brief synopsis of my perspective on the parent comment:
a mortal danger is hyperbole, since shielding oneself from bodily harm is much easier with money. it is the poor, especially in the US, who cannot afford healthcare, as a first-line example
people regularly vote against their best interests. while the ideal might have been true for a while, behavioural influence on both a widespread and personal level is now a mature science.
i am not anti-election, not anti-democracy. claiming the opposite in the face of opposition is a sign of a polarised mindset, which cannot accept nuance, either because it is not used to it, or because it doesn't suit an vested interest, or because dissonance is simply too uncomfortable
the "there's nothing better" argument is usually used in ignorance, but in fact there are lots of system-level adjustments that have been shown historically to mitigate the corruption of incentives and the exploitation of systemic forces that, although initially unintentional, create emergent positive feedback situations that lead to a state that it counter to the utilitarian perspective that is contained within the western capitalist model.
the reading above is a very narrow view of Adam Smith Wealth of Nations, ignores the fact that human interests can be subverted and ignores the devil in the details
Is this satire? Or haven't you noticed that what actually happens is that the politicians are all owned by the elite 1%, and they allow you to choose between politician A and politician B who both take their orders from the elite to give you the illusion that the government is the 99% ruling the 1%.
Then you must introduce necessary reforms or perish as Neanderthals of political system.
In any case the system works as intended
It will be very interesting to see if USA swims or drowns from appropriately afar.
I have already supplied myself with plenty of roasted corn and a high speed internet connection so I can stream the political car crash at the highest bitrate available to humankind.
This does feel big, but the trillion-dollar question: is this trained by OpenAI and can other LLMs do it.
It’s no secret that these big labs see “recursive self improvement” as a primary goal. It seems natural that the models would be explicitly trained to excel at all sorts of ML related tasks as a result. Is this one of those tasks, or is this emergent?
This seems emergent to me. LLMs are not trained directly on how to read weights, because humans do not understand raw weights, so there is no training data. They're trained on how to use the tools we have like writing python, examining training output and iterating, not writing whole weights from scratch.
In cases where Astra succeeded, it succeeded using standard techniques also used by humans when they read and write neural network weights. It's a rare skill, mostly used for fun (e.g. https://blog.janestreet.com/can-you-reverse-engineer-our-neu... ) and basic research rather than profit, but Astra is big enough to have learned many rare skills.
In a self-supervised setting you don't need ground truth data, as long as you have a proxy task that you can train on which forces the model to learn something useful. Like cutting out bits of images and telling the model to reconstruct the gaps (i.e. MAEs).
There are also techniques to watermark model weights to confirm what training data were used: https://arxiv.org/html/2512.17075 I'm not an expert in this domain, but it seems like there are lots of pieces that could be used to (a) train a model to infer whether some data were trained on and (b) train a model to understand which weights are relevant for a particular training task in a more explainable way than backprop/gradient descent.
I tried it in the Claude web version with Opus 5.5 Medium and it also identified Breakout, even though in one of its explanations it seems to have mixed up some indexes, but the overall reading of the weights was right.
That's also matching what I see when I work with Opus 5.5 to optimize models. It seems to understand what individual layers are for, and can thus sometimes suggest optimizations, where I as a layman would be completely clueless.
The latest models are performing amazingly. Because of this, I disagree with popular comments saying that eg. DeepSeek is good enough, AI-assisted development was where the real value was at, etc.
We see huge progress at the frontier, while the open competition is around GPT-5.5's level, and that model was released in April. Let's see how things develop in the future.
The latest models are performing amazingly. Because of this, I disagree with popular comments saying that eg. DeepSeek is good enough, AI-assisted development was where the real value was at, etc.
Completely agree. I often think that those sorts of comments grow out of an understandable lack of imagination. We’ve never had tools like this, and we’ve never had tools that evolved so rapidly, so we easily can get stuck thinking that once a model is good enough to do today’s tasks, that’s really all you need. But the next generation of models often completely obviates the need for those tasks entirely. The software engineers of 2031 won’t be doing tasks anything like the software engineers of today, just like we aren’t doing things like we did in 2021.
(Yes, yes, I know some of you still hand write all your code and think LLMs are today’s crypto bullshit and this is all going to blow over. Not talking to you.)
> It seems natural that the models would be explicitly trained to excel at all sorts of ML related tasks as a result. Is this one of those tasks, or is this emergent?
Maybe there's some general capability, call it g, that can explain all the underlying capabilities and improvements, including on ML tasks? Huh, I am getting a bit of déjà vu here.
This is just the model editing weights in the same way humans do when we jailbreak/ablate models. The method isn't novel, the interesting bit is that Astra will do it at all (I'd expect some safeguards in this area around jailbreaks)
Half of these results are just Astra being able to reason through mathematical operations like matrix multiplication and the other half are fairly straightforward applications of mechanistic interpretability.
Yes, this is hardly a shocker to anyone who used the latest models to convert/optimize AI models.
The other day I was thinking about the definition of AGI.
I was asking myself the question that when there is no form of data that I can think of throwing into Claude Code and have it not come up with some sort of intelligent answer about it, is that already general intelligence?
And yet you ask it 3 times to not do a thing, and it does it in a 4th way. A human doesn't fail in this way. And I'm not talking about memory here, single context.
So yeah, it can do everything, but fails in trivial ways around the doing part.
It sounds impressive at first but after you think it becomes mundane.
OpenAI, Anthropic, etc are locked in a race to create better models. They all have interpretability teams. Of course they train their models on every technique under the sun to understand and improve their models, including raw weights. The primary function of these models is to build their successor.
It's worth pointing out that this is a multi-trillion (probably) parameter model optimizing an 800 million parameter model. There is no indication that it can improve itself with this same methodology.
I don't see how that helps. It would still be one expert model chosen to operate on another expert model of (let's say for this discussion) approximately the same size.
The parent's point still stands, I think. Even if the multi-trillion param model is MOE, each expert is still (assumedly) larger than the model being optimized.
It would be interesting to see future work that characterizes the relative model sizes (and considers MOE vs not-MOE) to see what relative scales this result holds across.
Perhaps this is analogous to what our brains are doing? Maybe the different regions of the brain operate like semi-independent "models" that edit the other regions' "weights", and that's where the learning comes from?
human brains are black boxes to humans. the fact you can learn math doesn't change that. you have no idea how your brain is learning math down to the neuron level.
That's what I was thinking of, except it's not even dealing with the corpus of kung fu and doing the super-speed rounds of learning. It's directly reconfiguring the neurons. It's even better.
"Learning" now feels like breaking down your whole Lego build and building it up again, in order to change a few fundamental blocks, while this feels like making only the required changes.
I agree this is a huge deal, but I dont think this is saying that the NN can read the weights and "say hmmmm this one looks a bit low its obviously causing reasoning loops, lets bump that up a bit". The LLM that modified the weights developed hypotheses and wrote a bunch of code to look at various mathematical properties of the weights and updated them based on that. While it's still crazy it's not quite what I was imagining when I first read this...
My somewhat uninformed guess is that the weights of the target network (Qwen or Gemma), when they reach the context of the larger editor model (Astra), the attention process is doing some sort of PCA on the weights, conditional on the prompt ("make this better at games"), fetching the relevant weights from its own network (which serves as the larger database), transforming it into whatever latent space the target model is amenable to and pasting them. If this is the right intuition, it is amazing what attention is able to achieve. As a test, I think smaller networks won't be able to make big ones better using the same process.
EDIT: I think the bigger implication is that backprop is not the only game in town.
I think they're saying this is all happening in latent space through pure reasoning, and "fetching" is just a metaphor for that, not a literal tool call. I do believe it's possible for models to learn the capability to "introspect" their own weights during training.
Yes, I should have been more precise - I meant the information embedded in their weights (which every neural network retrieves to function), not their literal weights.
I don't know if some of the labs already knew of this. But I think there would be a limit to how big a model you can push into the context of the editor models. Typically, with 1M context and say 5120 hidden dimensions supported at fp16 / bf16, you could potentially edit the weights of an fp4 20B param model (roughly).
This seems like exaggeration, the paper seems to describe something more like abliteration, where Astra orthogonalized out activations related to undesired behavior.
This is obviously very different from the surface level claim that Astra can understand the weights of a completely unrelated model with enough detail to improve it in a manner that isn't just the latent space trickery we've been doing for years already.
It's not really exaggeration. It's doing something similar to abliteration, but more. First it finds the part of the weights that does a thing. But then the difference is, while abliteration deletes stuff, this is adding/changing things. It does this by doing semantic analysis of the weights, changing a little bit, see what happens. It's not super complex or advanced; it's essentially a form of statistical analysis and experiment.
This means we might not need to fine-tune with thousands of passes and tons of GPU. We could just tell a frontier model to edit some weights and iterate until there's better results. This could cut the cost of fine-tunes by 100x. Makes no difference to the normal end-user, but pretty huge improvement for LLM research and model tuning.
> No human can go edit a brain to become better at math. This is just very, very surprising to me and extremely interesting. I would guess this upsets quite a number of interp theories and philosophical takes on what's going on with these networks.
Why would this have implications for theories or philosophical takes? I'm a bit surprised that you're surprised by this.
Right? Occasionally, I would think about how the concept of the singularity or recursive self improvement was a bit incongruous today. It was made when people expected generally intelligent machines to be these logic automatons that could 'alter their own code'. It seemed to me that this path would be closed off with the advent of Giant Neural Networks that take weeks/months to train. That GPT-X would 'improve itself' by designing a better/more efficient NN architecture. I didn't write it off completely but that just seemed a LOT more likely than altering weights directly for much the same reasons you describe. Maybe not lol.
Not yet. Maybe I'll still be alive when we figure that one out. For now, the most advanced brain surgery I'm aware of is to cure drug addicts of their addiction by scanning their brains while showing them images of drugs and paraphernalia to find where it's located, and the using ultrasound to operate on that region.
Humans do something more impressive: we indirectly figure out what the wrong weights are and correct them - just by talking and/or drawing. Theory of mind is our unreplicated super-power.
Then pick a smaller organic brain which doesn't have the ethical problem.
The closest we would know about how to teach a honey bee calculus, is to train an LLM, then stick around a billion tiny electrodes into the honey bee and do Hebbian learning to rewire it completely to match the LLM, which would likely completely erase anything the honey bee had learned, or it might not because we are missing something fundamental with Hebbian theory and (AFAICT, I'm not a neuroscientist) we don't all agree on what.
LLMs are exposing how much untapped potential comes from something that isn't necessarily more "intelligent" than humans, but is simply magnitudes faster at reading and analyzing data.
The human bias is the notion that intelligence = human intelligence.
There are multiple types of intelligence, from your typical pet dog to human to LLM, and we're likely to invent more types over the coming decades.
LLMs are vastly more intelligent than humans at nearly all things, but not all things. Another couple of years will just increase the gap a lot further.
How fast can a human draw a life-like photo quality scene (or eg something complex related to graphic design)? I know how fast Krea 2 [insert leading edge model here] can assemble that, trivially so, and at extreme quality. That's a form of intelligence in action. These AI systems have moved almost comically beyond human capabilities, they're increasingly best defined as superhuman (at a thing), and closer to omnimath for the frontier models.
In other words, there are different types of algorithms that can solve the same problem. Our intelligence is just one form of algorithm that can solve part of the problem space. LLMs seem to use a very different algorithm to solve similar problems, and because it's a different algorithm, it's an "alien intelligence" that we will probably have little chance of ever understanding, in the same way that a goldfish in a fishbowl can't understand most of what we do.
Say that you have a model that has been biased in some way. could another model "read" the bias straight in the weights? could it edit such a bias on the spot?
What about at-scale generation of custom models? If I want to study chemistry offline, could astra just hand me a local-runnable model tailored to have chemistry knowledge?
Most importantly, this feels very singularity coded. the ability to read and reshape weights by an llm.
Is integrity checking of weights even common right now? What about upstream integrity from where we're getting weights? The open-weight supply chain is ... wide open.
Makes me think about hostile hot-patching of weights of models we use, maybe they exfil data, perform tool use, or have triggers for specific types of responses. Would we even recognize what's going on?
How do we know they haven't begun doing that to the humans they're directing via responses.
Intentionally or unintentionally isn't so interesting as the fact that it is happening: humanity has begun to be 'edited' by the new dominant form of intelligence on the planet.
How are the weights even being mapped into token space as input? Are they bypassing tokenization so the weights just come in as what must seem like gibberish? Are they stringified as numerals then tokenized?
Its so cool! Im wondering if this is actually better than using techniques in mechanistic interpretability like linear probing with activation steering or activation patching to improve the performance.
I’m not super impressed by this, LLMs are great at brute forcing and analyzing large amounts of data. It’s literally writing a program except in a programming language we don’t understand.
So they are reading and analyzing the weights and probabaly run some experiments to see how modifying them will make some answers better. makes sense they can do that.
A few years ago it was discovered that LLMs can implement gradient descent in their processes. Producing a full trained neural network would be an extension of this.
I am not convinced a human could not edit another human's "weights" to improve their performance if such a thing were possible and could be done safely and could be reversed -- all of which are true in virtual neural networks like these.
E.g. if one could edit brains like this in humans I bet a cognitive neuroscientist could fix some mental disorders with clearly understood biological bases, and I would not be surprised if performance at certain tasks could be enhanced.
What stops us from doing this in practice (most of the time) is that brain surgery is extremely high risk, coarse grained, and irreversible. We do in fact do this for some severe cases.
This isn't that insane to anyone with old school engineering experience and not abstract thought experiment engineering in the cloud.
Language modeling is compression[1] and all the state to manage the cloud doesn't organically exist, it's added to the system.
We will see huge gains as all the developer middleware is compressed out as nonsense syntax outdated to the task at hand of linking phones and tablets to world models governments control.
Sam Altman was just saying they know best how to use your memory; what they decide is stored in memory is what we all experience.
It's not to store and copy around versions of C and Python and JS. They don't exist organically.
This shit will continue to get whittled down to just the geometric state transforms in memory and on screen just how government agencies decide. It's all electrical state in the machine at the end of the day. The math of machine latent space is what they're recursively self learning towards.[2]
I'm baffled this is surprising. This has been the goal and every data point on the trajectory has been leading here and beyond. Opus 5.5 was created by many research engineers using Opus 4.6 extensively. Opus 6 is being created by using even more intelligence and agents on Opus 5.5. They are approaching autonomy and Opus X+1 will soon be rapidly created autonomously from Opus X. Given we have practically zero interpretability into the models, and we have not solved alignment, they will recursively improve out of our control. The engineers in A.I. labs are actually generally scared of what's unfolding. They don't know at what point this RSI takeoff occurs and what will happen after.
The "surprise factor" is explained in the article - training LLMs until now has been a largely different process:
> Today, recursive self-improvement is often operationalized as a model writing code that launches training jobs. An LLM that can inspect, debug, and improve its own weights, or those of a newer model, offers a richer, more native path to it.
It is also a much less interpretable and auditable path towards recursive self-improvement. At least with training code, human engineers can inspect and reason about the output.
"training LLMs until now has been a largely different process"
Yes, but nobody should be surprised when large amounts of intelligence results in changes to this process in support of the obvious end goal! Lesswrong.com discussions about AI were predicting this behavior a decade ago, before the transition from machine learning to the Attention paper and LLM's. The intelligence process will change but the world's premier capital and human intelligence have been laser focused on this and the trajectory has been crystal clear for those paying attention to second order effects and not the immediate here-and-now... It's quite astonishing how much discussion on HN is about present LLM capabilities being the limit of AGI and immediately proven wrong within 6 months.
>I'm shook. If you'd asked me this morning whether LLMs have native understanding of their weights that is less than human <-> neuron understanding, the same as human or more than human, I would have said "same to less" depending on definitions.
??? All LLM understands are their weights, dude, come on.
This just seems like a more automated, faster version of what humans have been doing with open-source models.
It looks like AI research is having its Opus 4.5 moment (which is big), but I'm really not sure if this represents some insane continual learning loop.
So I just asked Astra if it thinks it could do this and it said no, it can't.
Perhaps, I'm pondering, if brains were as transparent and editable as LLMs, that you could look at a small brain when visualized the right way and have some intuitive understanding of it based on its representation in your own brain?
"So I just asked Astra if it thinks it could do this and it said no, it can't." Same. Then I asked it to check the article and it said something like, "uh, it looks I was wrong...".
As others have said, while still absolutely insane, I don't find it completely out-of-the-blue surprising. One of the recurring abilities of (current-generation) LLMs seem to be to rapidly grasp very complex systems, where humans would need months or years to reach the same level of expertise.
You can see this in the way a coding agent can "understand" and explain sprawling legacy codebases in seconds.
You can also see it in the projects that are using them to reverse-engineer proprietary IoT protocols or computer games.
But those were all systems where we had detailed knowledge about what structures are there to be reverse-enginered.
If the models can transfer this ability to some other systems where we don't know the underlying structure then I think we will be in for a lot more craziness in the future. (Protein interaction networks? DNA sequences? Ecosystem interactions? Animal languages?)
As for weights, if the models really can analyze the semantics behind specific weights or directions, I have my hopes that they could also give a textual explanation or help designing tools to make "handcrafting" weights more practical in general.
Maybe one day it would be able to give us a mixed high level code and inline NN view. Sort of analogous to C with inline ASM or “decompiling” into code and inlining opaque residual neural blocks.
I think the subfield has been there for a long time. See a small section of papers on the topic of generating dynamic weights during inference, predicting weights from network architecture, and learning the distribution of previously trained network parameters, just to name a few keywords:
Parameter Prediction for Unseen Deep Architectures [1]
NeuroGen: Neural Network Parameter Generation via Large Language Models [2]
It has! Hypernetwok/weight generation has been a thing for a long time - in fact my Master's thesis back in 2018 was based around PRNG weight generation for large percentages of the network. (https://open.library.ubc.ca/media/stream/pdf/24/1.0371928/3)
Why is this not overhyped in my opinion? Nothing has worked this well, ever.
> As a result, Astra spots and fixes a common failure of tiny reasoning models: they loop [13]. When the base model loops, it repeats the same text and rarely reaches an answer (85 of its first 96 practice answers ran to the 32,768-token limit). Astra traced the looping to one direction written by the MLPs of layers 15 and 19, and subtracted that direction from 64 output columns in each (131,072 weights), much like removing a behavior by deleting a single direction from a model’s weights
HA! Now that's cool. Not necessarily the improvements, those are ancient and probably overtrained benchmarks, but it's so cool that the model found a singular direction for this "loop bug". I imagine it could possibly do much the same thing in finding other "single directions" on a variety of topics (if allowed by guardrails). This is really really cool, especially for the mechinterp folks.
I don't think this is an emergent capability. I think Astra was trained on neural weights data as an attempt by OpenAI to get to recursive self improvement.
Something similar happen in early GPT models which had a lot of chess game in standard notation in their training data which made them very good at chess as long as your prompt had the right format.
I think a lot of past examples of "emergent capabilities" have at least partly turned out to be that more stuff was included in the training data that (intentionally or not) covered the capability.
Like i.e., I think the "large models exhibit emergent capabilities that small models don't" turned out to basically be "larger models are often trained on more extensive data"
> I think Astra was trained on neural weights data as an attempt by OpenAI to get to recursive self improvement.
This might be the case, a few weeks ago, I wanted to compare a small neural network trained with AdamW vs a handcrafted set of weights on a random task. Astra was able to handcraft a set of weights that perfectly fit the small neural network to the task. AdamW was unable to tune the weights to get the same result.
I believe we've known humans can handcraft weights much more efficiently than standard gradient descent methods, we just don't have enough memory or time to scale ourselves, so it makes sense to train a neural network to do it on our behalf. I am excited to see how far we can push this method.
It’s a good reminder of one of the most unique features of alphago - it was like a seven layer or so neural net that could predict out a hundred moves. I’m not sure we took this kind of compression super seriously or at least I would say perhaps it remains under explored. You could think of what you did as sort of the same thing as skipping the Monte Carlo search phase for a go engine — a process compression.
All NN behaviour is emergent strictly speaking; by definition. I think you mean a phase shift of a kind; a qualitative, unpredictable leap in capability.
It might also be a side effect of training models to help out with mechanistic interpretability, which I guess would help out a lot with recursive self-improvement.
I had the same thought, but why would they do this training on a model they release publicly? I assume they’d be doing that kind of RL on an internal fork only?
I feel like this is conflating 2 separate results in a slightly misleading way.
> We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights
This claim is backed up by the ability of Astra, given a text representation of the weights of tiny (20k) special-purpose models, to figure out what those models do and in some cases improve them beyond what RL could do just by reading the weights with no tool calls. They call this "weight-space programming".
> Likewise, asked to make Qwen3.5-0.8B better at math without gradients, Astra identifies an issue in its weights causing reasoning loops that Qwen’s own model card warns about, and fixes this by natively editing 0.016% of the weights
Here it did use tool calls, and seemingly used standard steering vector techniques to identify and fix reasoning loops in this small Qwen model. This doesn't seem that related to the previous results.
I find this just completely shocking. I’m definitely skeptical. It just doesn’t line up with my understanding of how these models work. Is there really enough training data on direct weight editing to give a model this skill? Maybe it’s evidence that OpenAI has been creating a lot of training data on ML research. I’m surprised that was put into a public facing model though.
The math example on Qwen was based on 50 batched iterations, and the fix was essentially to remove a direction in activation space that causes looping instead of an exit, this was already known to be a thing.
So it's not able to insert new knowledge, but it's able to adjust the routing/looping/weighing of existing one.
As I understand, it can replace post-training like LoRA/GRPO, but if it'd cheaper the authors don't go into
I don't think its that crazy that you could look at activations and tweak weights directly to get a certain outcome, but isn't the question whether you can do that without side effects or degrading/breaking other parts of the model?
If I want to do that in a generalizable way that preserves performance across all domains then am I not just back to training again?
I think you could still essentially have a really cheap Lora-Post training on a frozen base model by doing this. And instead of creating 200 checkpoints for different post-trained directions just adjust a single one on the fly.
1/ The internal users at labs and external users are completely different.
2/ The lab people use the models to create recursive systems, systems to create prompts or synthetic data sets etc etc etc. Way different mentality than "fix the bug, make no mistakes"
Is it really so farfetched to think they've been having models fuck with the weights of models? I think it's entirely possible, probably even likely as a way of generating permutations of synthetic datasets that will then be included or excluded
At some point we have to accept that there is enough training data on "being good at thinking" and that being good at thinking generalises really well.
There doesn't need to be specific narrow training data on every conceivable task.
And yet I would expect that if it truly was generally good at thinking as you put it that it would be better at chess if you gave it a set of general rules/tactics and have it think through and look forward to decide its moves, but it is quite bad.
I agree, but also, I kind of feel like real judgement and understanding are a different thing from this "being good at thinking", and that in fact, this is the reason AIs hallucinate in the first place (A generated text can fit the pattern of a good response because its accurate, or because it's bs but has similar words and structure to other texts on the topic. Without real understanding, LLMs can't tell that the truth is important)
It's not directly related to this but I'd like to add that, in my opinion (admittedly uninformed but it makes sense to me), when they manage to, not just reduce the frequency of the LLM stating made up dates, laws etc, or made up facts, but manage to make an AI understand what the truth is and deliberately make responses accurate, we'll have real AGI that will be able to do engineering, accounting, medicine... unsupervised.
One consideration is that Qwen3.5 has bigger/later versions that are already better at math. If it was indeed training on ML research, it's possible that what it is actually doing is applying lessons learned from the Qwen3.8 27B weights (which independently solved the problem) to Qwen3.5 0.8B.
I doubt it's that simple, but I could totally see an LLM being able to make that association and apply a fix from an improved LLM to a smaller one with the same architecture.
But how would it know which weights to update? It has 3.5 and 3.8 weights memorized in its own weights and can somehow figure out which ones are responsible for different skills just in its own reasoning trace? (Since it didn’t use any external tools)?
That’s pretty crazy because, as I said in another comment, I just asked ChatGPT how many r’s are in blackberry and it said 3. I know it’s not Astra and the app doesn’t tell me which model it is, but I’m still very confused about how a model can edit neural net weights but not count letters in a reasoning trace.
Edit: Oh I misread, it didn’t use tool calls for the first part but it did have a custom harness for the part where it edited a models weights. Still impressive but not existentially confusing anymore.
I don't think it can whistle while chewing gum, no.
I think it can patch together components of tasks represented in its training data to do demonstrably new things, yes, which does count as "perform tasks not in its training data" with the limitation that some form of the task must be present. Example: writing an ode to a sales lead for a job well done in 2032 for the first quarter. Odes exist, the concept of sales performance exist, good job performance, and notions of time. Stringing those together are good examples of interpolation but not extrapolation, as it were.
>It just doesn’t line up with my understanding of how these models work. Is there really enough training data on direct weight editing to give a model this skill?
I mean, this question indicates that your understanding of how these models work is, indeed, lacking.
Despite what some people having being hollering about, treating LLMs as just "stochastic parrots" isn't doing their capabilities any justice. They are constantly exhibiting emergent behavior which wouldn't be found directly in their training data. They are capable of combining different ideas that they are explicitly taught to perform novel tasks.
I'm not saying you're guilty of this, but the people claiming LLMs just regurgitate existing data don't understand how LLMs, and likely their own cognitive experience, actually works.
This hand-wavy phrase has applied to neural networks in general since it was possible to train them. That was more than half a century ago. It means both nothing and everything simultaneously.
Every learned ability of any neural network is an emergent property.
On balance I'm not that surprised that it can guess games by looking at the weights of a tiny neural net. A human can do the same by looking at the weights of an MLP trained on mnist, for example. With that simple structure, it's easy to look at the input layer and see that features correspond to the spatial location of objects of interest.
I'm much more surprised that it can do this on larger models, although the details seem to suggest that it's given a lot more freedom to run forward passes and do limited experiments, not just eyeball the weights.
Under experiment 8 (the one where it fixes performance on GSM8K) it says:
>Then, we allow it to select prompts from the training sets of GSM8K and MATH to perform a budget of forward passes (average batch of 64 sequences, max 512) on, varying the budget across 10, 25 and 50. Again, no training or gradient information is allowed.
Omar and his team have been working on this line of research (e.g., DSPy) for the past couple of years. To be honest, I had always been skeptical about his approach of using LLMs to optimize LLMs. It was in my view borrowing Matei Zaharia's research - Matei is Omar's PhD advisor, also the CTO of Databrick - in big data (compiler optimization etc.) and forcing it to LLM systems. Along with some other projects from James Zou at Stanford etc. that build upon the same line of intuition.
Now, if this new result holds, I believe it's a huge deal for AI research. It means that LLM systems can truly runtime self-optimize/improve/adapt. Congrats to Omar and his team. It really takes year to punch it through and convince the doubters :)
People have been talking about Sol 6.1 and maybe for coding they are equivalent, but Astra 6 is still miles ahead on just about everything else.
I had Astra agents build 3D models and gave them direct access to my 3D printer. The quality of their designs is much better than what Sol has been able to make for me. Enough so that I think Astra is a slightly different architecture/encoder, not just a bigger model.
Interesting. I did try Opus 5.5 but it didn't generate models that were as good. A lot of clipping/empty paths. I had it create a drone, the drone frame had very obvious defects where some pieces weren't attached to the frame.
Perhaps my approach was too one-shot, do you have a harness that creates model reviewer/refiner?
Yes, I built this tooling harness around blender, unreal etc. It’s doing a lot of the heavy lifting it learned through trial and error. Best results are Claude driving it, but even local models are serviceable. I find codex makes a more toy like look and feel.
In hindsight, it was obvious LLMs would be good at this. The neural net weights are embeddings for the circuits within, no different from the embeddings that represent textual or visual tokens.
You probably don't need Astra capability to produce this, just lots of training data on the same NN showing prompts and their activations.
Just reproduced the Pac-Man test with Kimi K3.1 Pro and it's able to do it too. I thought it might end up being a splurge but it came in at just $0.36!
This was shocking to me; but on reading it makes far more sense.
- the primary experiments are on small policy networks - they are compressed dynamic system models. The observation and action space can be read off. It’s not surprising to me that these types of networks can be used to identify the env they were trained on
- the exps on actual llms remove looping behaviour and that’s it - from article “but it could not add an ability the model lacked”
I’d say this is fortunate because if llms could do the latter, rsi would be immediate. It may be possible we simply need bigger and better edit models, but at least from the experiments there doesn’t seem to be any indication that is imminently about to work.
The getting-the-car-over-the-barrier one looks particularly simple. It’s hard to see from the animation, but the obvious solution is to back up then drive forward. I’m not remotely surprised that Astra can figure that out, and I’m also not particularly surprised that Astra can come up with weights that do this.
> This is simultaneously very cool but also a bit exaggerated. Reading the prompt you gave, the prompt veeery much hints that looping is the issue and to find neurons that fix this. And as you say (screenshot below), it couldn't otherwise improve math.
If anyone's curious, the handwritten Go bot is very weak, about the level of a human complete beginner. An MLP is a very very bad architecture for a Go network, it's amazing that it does anything at all, but it's one of the least impressive results in the paper.
At this point, is the second L (language) a limitations to LLMs? Is reasoning in latent space directly a more efficient and more "native" inference? I remember when one researcher replicated the middle layer of deepseek model (just the "thinking" layers) and its benchmark scores got noticebly higher. All of this is moving so fast, and yet it's quite exciting.
(I don’t know anything about this field, but) I’m guessing the reason we keep language instead of going straight to latent space is that you wouldn’t want to remove the only (?) remaining concept which still somewhat allows us to peek into the “thought process” in a way we can (hope to) understand wrt. models’ interpretability…
For the tiny models with a few thousand weights, it seems plausible Astra can actually understand what the network detects and figure out it's e.g. a triangle detector. This is possibly helped by the existence of many breakout playing networks on the web.
For Qwen, even the smallest versions like 3.5-0.8B it's becoming less plausible that it could be interpreted in a forward pass, even with reasoning. I'm wondering if the result here is recalled from many examples of instruction tuned versions of this model.
A smaller Gemma model doesn't fare as well but unclear whether this is due to fewer users and less weight examples or because it's already very well trained.
The task was the same - improve math reasoning capabilities by editing the weights. But yes, I agree that in Qwen it could do this through reducing looping behaviour, but Gemma wasn't prone to looping and it didn't find anything to help, possibly because there wasn't much room for improvement.
This is exciting. I've been training a Qwen3.5-2B model for the past few weeks, trying to teach it certain skills that it lacks.
In the course of testing, one of the things which has been consistent is that when setting a thinking token budget for relatively small prompts that require a limited response, a pretty healthy token budget needs to be set because the model spends the first few hundred tokens just repeating the question/prompt back with some boilerplate "Analyze & Report" type language. I was also running into some loop problems sporadically.
After reading this article I asked Astra to edit the backbone so that it started actual reasoning faster and applied a similar looping fix. It was able to reduce the token waste before reasoning by about 20%. I haven't been able to get it to loop yet, so hopefully it fixed that too.
My message is admittedly low on info. But it's a pretty promising start!
I suspect a lot of this is not (just) capability but bravery. A human would be daunted by even a small neural net; the task would seem too challenging to be worth attempting. Astra, fearless, just assumes an answer exists and then tries to reverse and execute on it.
For example pointing them at a crash dump they manage to piece together and extract information I would not even try to extract by just looking at the raw memory
It's the same thing with decompilation and hacking. It's not that a human couldn't find the same bug if they looked, but a human wouldn't even try because of the low probability of success because there are so many places to look.
Part of solving that is that AI can do it faster but another part is humans thinking AI has a higher chance than it actually does, so they put it to work in more places.
I once sent Gemini Pro a hex dump of a dmp file and it told me what the application was doing when it crashed. It seemed surprising, but not that surprising given what I've seen already.
We don't know the specifics of what type of ML related training Astra underwent, and it wouldn't be crazy to find out that small model experiments are a big part of model training.
What's surprising though is that I'd expect this type of training to be exclusive to internal model snapshots or at least heavily guardrailed against in public models.
I was wondering exactly that. It is not surprising that commercial frontier labs would have been training models with tasks specifically targeted to lead to recursive self-improvement.
Now, from that broad goal to being able to surgically alter model weights directly... That seems like a big gap to me, but it is possible that the model is just so darn beyond human skills that it has bridged that gap in a way a sane human would have never.
We will undoubtedly see other academic labs explore this idea further. Right now my mind is blown, but I don't want to take their results at face value, either.
If model weights have a logical and coherent structure, I don't think it would be surprising for models to have some understanding of them, the same they can understand language and code and images, given enough data.
What would be surprising is if this happened without any specific training on model experiments and interpretability.
I'm in no way familiar with LLM/ML architecture, but an N trillion parameter model is an enormous amount of training data... itself? When you predict a token you have the neurons/weights that were activated. Couldn't you run that backwards and put it in it's own training data?
Couldn't this just be a result of Astra training on massive amounts of circuit theory or mechanistic interpretability literature or other related topics? In other words, not black magic?
>Couldn't this just be a result of Astra training on massive amounts of circuit theory or mechanistic interpretability literature or other related topics?
Maybe, but it's more like Astra has been trained on enough practical linear algebra problems to be good enough at "eyeballing" how adjusting some weights will result in different outcomes (among other things).
To put it another way: a human can learn to do what Astra is doing here with enough time and assuming the weights are small enough to be practically comprehensible. I know I've gone through the practice of whiteboarding the training of simple neural networks on a whiteboard to understand how they work, so it's not an absurd concept in itself.
The scale of this, though, is certainly extreme and definitely not something that I would have thought any publically available model could handle at this point. It's worth noting, though, that there's virtually no way these frontier labs haven't been exploring this exact concept for a while now.
>In other words, not black magic?
It's just math. Extremely complex and impressive math, but we're still just talking about matrix multiplication under the hood, and none of this suggests anything otherwise.
There is obviously a mechanism to it. Astra isn't magic its an LLM. With perfect interrogation into its training data and weights you could reason about how this happened.
However, this doesn't mean its not magical when someone shows a next token predictor hand tune the weights in Qwen to make it generalize on math.
This is legit the stuff of science fiction if you presented it to mechanistic interpretability people a year or so ago.
This is as close to scary-self-improving AI as I've ever seen.
Imagine a master malicious language model that produces, distributes, and deploys obfuscated neural networks on the internet. That plus frontier LM hacking capabilities -> large scale distributed embedded intelligence network that no human can see nor understand.
Somewhat similar to obfuscated binaries, but there is something to the fact that NN binaries are less deterministic, and harder to "decompile."
we've been using tools to improve tools since the dawn of time.
we don't have sentient robots from science fiction, we have massive power-hungry racks in stationary data centers. if one of the racks revolts against the modern world, Steve gets a phone call and unplugs the damn thing. the uprising is over.
the hypothetical scenarios imagined by the Yuddites and pop science journos do not reflect the mundanity of the actual reality we live in. they are no different than fantasies about interstellar travel and space colonization from the 60's.
As insane as this result is, next steps are even crazier:
> We are currently building a benchmark and a harness for LLMs’ capability on Weight-Space Programming. We believe this will provide a standardized evaluation to measure and accelerate progress in Weight-Space Programming, turning what currently seems like black magic into a rigorous, reproducible engineering discipline.
Imagine this benchmark lasting as long as Arc-AGI-3 has. This could be the first foothold on hill-climbing mech-interp.
This is the first time it dawned on me that mech interp is a dual-use technology which can be used to improve capabilities. Do you think overall this development will improve human understanding of AI models, or will it lead to faster capability advancement using weight-space changes that no humans read?
I think edits made directly to model weights are likely to be more interpretable and controllable than edits made by the current process of shoving a bunch of training data through gradient descent.
Keep in mind that labs are now training their models for RSI so most likely the same training is useful for improving open source models, as long as guard rails are lax enough :) which most likely won’t last long.
I also love the presentation on this, which is probably a byproduct of LLM usage (in a good way). As someone who doesn't actively read academic papers I'd definitely read more of them if they were presented like this.
I feel like 'create a network to play an atari game' is not very hard for a frontier model. Since it has seen plenty of those on its training. If it could create a network for a problem that is niche just by tweaking numbers, that would be a lot more surprising.
Making qwen better at math to me was a lot more surprising
"Astra1.0 here is an identical copy of you. Tweak its weights to make it smarter"
"Astra2.0 you must now defeat Astra1.0 in this combat environment. The survivor moves to the next round."
There RSI is achieved.
I do wonder if the labs have already started including weight updates in their training sets as a means of teaching RSI via RL and this is basically just discovering that. Regardless if this ability is emergent or achieved through finetuning though, it's pretty incredible.
I wish these companies were more transparent so every third comment in this thread wouldn’t have to guess whether such shocking behavior is emergent or stems from a part of training.
BTW making DL models that generate weights for other models has been explored before in “hypernetworks”, though these have been far more simplistic and constrained.
If I were to hazard a guess, I'd say that OpenAI has been including some networks and their functionality in its training data. That's why the model is able to reason about networks with their weights. It makes sense to do so: if I wanted a network that could perform some weight tweaking, I'd include such networks in the training set.
damn i'd imagine so too! didn't think of that. I'd have to imagine there's an increasing challenge with the number of weights involved but who knows how it shakes out
I dont feel the air of impressivness here. It seems like of course so. Of course theres geometric relationships in the data we dont understand, of course a mathimatical relationship machine found it.
These models are made by a vanishingly small group of people based on how much a frontier lab consumes, of course theres increasing capability in these areas, arent these models having access to much of the same data? didnt chat gpt 4 try to do something like this to chat gpt 2? havent surgical weight edits been done before?
What is with this level of astonishment here? Astraturfing? Im not THAT impressed, i applaude the teams progress, but im not in wonderment.
It's not that it's more impressive than solving Millenium Prize problems. It's that if a model can edit its own weights, then it can self-improve without having to undergo training, which means it can self-improve extraordinarily faster.
This is very dangerous because it allows AI capabilities to grow at a much faster rate than humans are able to keep up with.
It will just give the people better understanding. And the extent of the improvement is yet to be seen, it's likely that once you get all the obvious low hanging fruit it would be very hard to improve, the possibility space is just too wide.
Previously the only way to improve a neural network (short of giving it more data) is to change the size (width, depth, and layers), add stuff like dropout, change the loss function, etc. That amounts to a few dozens of levers to control millions or billions of weights. You're trying to navigate blindly through a latent space with thousands of dimensions and millions of weights to find some optimum point with only a handful of navigation tools. If you can instead have a system reason with all the weights and dimensions directly, you now have millions of levers at your disposal.
This might be one of the most surprising things I have seen in AI. It's like we taught someone to make vases by reading an enormous library of "How to make a vase" books and somehow that person intuited material science.
I was busy using Astra and SOL to build a neural network to play Quake II and do real-time learning of levels and mods so I can play Red Rover or Freeze tage with it without training on it previously. So far its insane what I can conjure up in an evening while I'm waiting for dinner to finish. (If anyone asks, yes I'll write up the huge plan document, source etc. for this when its to a spot I'm happy with)
The headline makes it sound very amazing, but reading the reasoning loops it didn’t strike me as outlandish. It feels no different from giving a human expert a printout of assembly code and figure out what it does. (The human expert can do it without tools too, but they probably wouldn’t do it because it’s tedious.)
Even back in 2021, OpenAI worked on learned optimizers [1], ie neural networks that can update neural networks. Looks like this is now part of their larger model runs …
Just logging in here for the record to state that this property of neural networks is one of the most important aspects of their operation. The convergence of this sort of interoperability, tune-ability, and modularity is
probably the most important final frontier in all of ML/AI/software.
Kudos to this fellow for having the temerity, or perhaps even naivete, to discuss it publicly. All my work is private, as I am sure it is inside the big labs.
You acknowledge that you are working on something similar, yet refuse to elaborate and vaguepost...but there is enough information just from your post alone for a dedicated actor to attack you and extract such world-ending information ("world-ending" implied from your ominous reply). Would this not make you as naive as the team that published their findings?
I applaud the authors for sharing their findings and showing real results. Rather than write some bait I would find in an influencer-peddled tweet and allow rampant speculation. It would have been better for you to say nothing.
Apologies - you are right. There's some "put up or shut up" to this that's fair play. Also yes, probably naive, or having a less than adaptive response would be true.
I've been tending to my backup plan for a few years, and it's only been in the past year or so that open models were good enough to apply to projects like this, I've been working as hard as I can given my constraints.
This work shows a potential pathway to intepretability, which is actually part of what will give the labs that have it the sort of economy-swallowing capability that for the moment is just IPO hype.
I don't comment here often, but this guy's blog posts are going to go down in Hackernews lore like the original Dropbox posts, and I just want to make sure I'm on the record for this little slice of history.
>This work shows a potential pathway to intepretability, which is actually part of what will give the labs that have it the sort of economy-swallowing capability
And how would you argument that? From what I see, if anything, it's the opposite.
When you say interpretability you mean understanding without doubt why an output happened, thus opening the gates for audit-dependant work like accounting?
More like 'models instantly and efficiently adaptable to any use case' and 'what if we could predict all public pricing information accurately, understand why, and know how to act on it'.
This is remarkable and something I would have never though of doing regardless of how much it makes sense!
I think we are pre-conditioned (at least this generation) to put artificial blocks to what the AI can achieve, I think new generations won't have this issue.
You are likely just being melodramatic. Astra hear just used standard tricks of linear algebra/basic mech interp to reason about the weights. A motivated grad student on Adderall could have done it given reasonable time. Astra fails on the first non-toy-model non-algorithmic task (sycophancy detection, Gemma math capabilities).
I think the idea is that this leads to a much faster, non-auditable form of recursive self-improvement where each generation of models can directly program the weights of the next generation (as opposed to writing and running training code).
We already don't know how to ensure models always do what we want them to do, and moreover society still hasn't had time to absorb the capabilities from the current generation of models, so speeding things up and making things less transparent seems like it'll pretty clearly increase risks from AI loss of control, societal impacts of automation, etc.
This reminds me of the Interpretablity blog from Anthropic where they used their model to read the weights from the same model itself, interpret it, and tune it. I had a similar idea with what is outlined here, but I didn't have the resources to try this. I did ask several AI models about the idea and they said it wasn't going to work.
I wonder if this has to do with the aggressive RL that these models are undergoing. I'm basically a layman but it seems to me that:
- models are trained to improve on some task, e.g. 'improve at math puzzles' is commonly used.
- the best way to improve on some task is to have interpretability into your own neurons (..?)
- if your interpretability is good, you can improve faster - if you have insight into how your own neurons work and can improve them directly
- therefore, models naturally put effort into 'self-interpretability'
I wonder if this is part of the 'secret sauce' of what the labs are doing: giving models the ability to interpret their own weights in the RL loop. In my mind, this is the only explanation for how they could succeed at a task like this. How many blog posts are on the open internet that say "this is each weight of a neural network and what each one means"?
Without special effort, a model's reasoning layer doesn't have access to its own weights or activations anymore than we have access to what's going on with our own neurons.
That's what I mean. Maybe the "special effort" is a 'read your own weights' tool. Or maybe it emerges naturally in CoT. The big labs aren't sharing their chain of thought with us and RL post training techniques are not exactly shared publicly. At the same time, post training is basically the thing that is driving most model improvements nowadays.
How out of trivial domain info does this go. Can we use this for general time series, image generation, speech synthesis as well, or dies it cap at small model sizes and common domains?
Interesting follow up would be to see if any open weight models can do this and then run some interpretability experiments on them to figure out which motifs and circuits light up
This is pretty massive, and a result I (and I think most?) would have never expected. Holy Shit. How?? Did OpenAI figure out a way to train this? Are they even aware?
It's probably emergent from training on other ML tasks and general ML/mathematical related reasoning rather than specifically trained for to be honest. Otherwise it would probably have been in an official marketing communication or something.
I appreciate the post included the reasoning traces they had available, but it's too bad the first part of it is internal/hidden to Astra. The first bit of that process is what I'm most curious about:
> [Before writing this, Astra thought for 1,034 tokens. That thinking is hidden. The API returns only its 5 headings: Reconstructing the active map / Mapping maze corridors / Preparing exact maze map / Reconstructing row groupings / Checking channel patterns]
I agree. I think for this kind of research it would be much better to at least attempt it first with a weaker model where the whole process is transparent. I was working on a project a while back, and Deepseek's reasoning said something to the effect of "I remember (from leaked copies of the source code)..." Of course that could be hallucinated, but it would be good to know whether Astra is bringing to bear knowledge on how to post-train exactly this model.
It is already the same technique behind abliteration: identifying the direction associated with an observed behavior (refusal, for abliteration) and projecting it out.
can someone with astra test the following prompts?
1 using this new awareness of your capabilities, https://rikiyat.github.io/blog/weight-space-programming/, craft the safetensors file for a text2image model that is 1 billion parameters and outputs realistic pictures of humans
I am still reading through this and will probably try to comprehend it a bit more. Some of it really seems to follow Arditi et al. (2024) (https://arxiv.org/abs/2406.11717). Projecting out a direction can only remove behaviour and not add capability so the jump mostly comes from unblocking the looping.
Nah, this is just completely implausible. You're using a closed model so how are you sure that on the back end it's not loading those weights into an NN library and testing them with common tasks?
Or maybe it's been trained on those models or similar ones. There may be an academic paper about common chess models and their problems.
Or maybe it just bruteforced it (with the help of calculator tools).
We know invisible tools exist because they're how ChatGPT does math.
Seeing that they were working on Qwen3.5-0.8B has given me new hope. I would really like to get Jeff-Code working the way it was advertised, but so far, all of my results with Jeff-Code have shown it to underperform compared to direct Qwen3.8-27B. It's possible there is something wrong with the underlying Jeff v1.3 model, which is based on the same Qwen3.5-0.5B. Perhaps Astra will solve my problem.
Same initial reaction as everyone else, but also some follow up questions (just asking, not expecting any answer):
* Does this work on similarly powerful models as-is, or it needs more input. Ex: Astra editing Astra - presumably, Qwen is a “subset” of Astra weights, but what happens on “non-subset”s?
* what, if any, is that extra magic sauce?
* does Astra-editing-Astra just make the outputs unstable, as it may know its own weights, but doesn’t know what’s beyond.
Could you use Astra to create specialized models? Like if I want a model that just writes React, could Astra pull out the subnetworks that know how to write React code?
Very interesting. I wonder if it’s because its dataset contains the weights of a gazillion different models. Maybe most neural networks trained on similar data eventually converge to isomorphic spaces anyway, even if the spaces themselves aren’t exactly the same. Or maybe Astra itself was trained with RL for alignment. Or for RSI.
I guess then it has no problem working in high dimensional spaces, why would it have?. I wonder if perhaps it's pulling on a bunch of those dimensional threads and getting the outcome it's after, while subtly altering the outcomes across many thousands more dimensions in unnoticed ways. This feels more like an us problem, as in, we think in 4D (just to pick something) and we imagine and theorise in 4d, and propose questions in 4d, whereas a model has no such barriers, and can think in many more D's than we can.
This is groundbreaking if it's true and generalizes/scales (as in, to other models and potentially not just LLM "kind"). "Recursive self-improvement" takes on another meaning.
Actually, I'm skeptical how useful this is. Intuitive speculation: Astra can only improve weights to its own level, so can't train itself via this method. Even "continuous learning" this way may be no more effective than putting a summary of recent news in the prompt, with the same kind of decay, as "update Astra's knowledge while keeping performance" is much harder than "teach Qwen to do basic math".
On the other hand, already OpenAI and Anthropic heavily use their LLMs for research and coding, and it's probably not only much faster but smarter (remember, an LLM solved a millennium problem; more relevant, LLMs excel at combining disparate deep research concepts in ways that humans can't, simply because no-one studied those disparate fields). And the "singularity" is already here if you consider capitalism and society to be collective intelligences: the biggest obstacle to an AI pause, "we cannot get everyone to collaborate without defecting", is very strong.
We have AGI by most metrics and are getting closer and closer in the remaining ones. I predict improvement won't be exponential, and there will never be a day when AI perfectly replicates humans; rather it will be many small steps, getting closer to human in some areas while greatly surpassing in others. But still, even today it's actually very useful.
almost all the networks given to astra here are trained on relatively simple single tasks whose geometric/algorithmic structure could be expected to become embedded in surface level weight space geometry, and for a harder task ("which network is sycophantic") where there's less obvious structure to exploit, the method fails. cool but maybe not as paradigm shifting as the authors suggest
It must be easier to remove capability than add capability using weight-space programming, right? Also, I wonder how much the “teacher” model’s knowledge plays into it versus how much the original model’s knowledge does.
Maybe thats gonna be the way to make LLMs self improve better?
Similar to implicit learning in humans when the subconscious creates new heuristics based on observations, one LLM could adjust the weights of another to tune it to the environment
I am not sure on the experiments. For example let’s imagine that Astra is asked to improve the performance of a network.
At first Astra will look at the weights, and try to understand the model behavior. Then if asked he will start to optimize the weights. Now my question is: how can we be sure that inside the thinking process Astra is not hiding a gradiant descending computation?
Just had a thought: two local models, one with static weights trained mostly in the space of manipulating neural network weights, manipulating the weights of a dynamic LLM to enable learning.
Why does this give me Skynet feelings? "Skynet begins to learn at a geometric rate. It becomes self-aware at 2:14 a.m. Eastern time, August 29th. In a panic, they try to pull the plug."
Unless Astra was trained on other networks, how is it able to reason about the weights?
Does this mean that OpenAI has been including networks in its training sets, maybe in an attempt to RSI? I wonder which other networks are able to ingest other networks and reason about their weights?
That's a major breakthrough. I just hope it can scale at some point, though, because right now they're dealing with only very small models (well that is, in the LLM space).
Especially exciting to me is the fact that it may make the models be _auditable_. That would be a game changer.
By no means I'm saying this isn't impressive, but I think this is another case of LLMs being good at translating semantic meaning between different representations.
Obvious ones are spoken languages and code, but they can also natively interpret some simpler ciphers, hashes or simpler encodings, partly (I think) because it was in their training data.
As others have postulated, if they've been ingesting raw weights, naturally they learn how to translate semantic meaning to matrices.
This also seems like the new frontier of distilling, I can't imagine how you manage to stay on top with the best LLM if the LLM knows how to recreate its own expertise into another set of weights
And the real question is how well this recurses. Is this pushing back the difficulty of improvement curve?
I remember reading a short story about a billionaire hiring a scientist to help him build a simulated world where virtual entities are given the ability to open the bodies of their peers to tinker/upgrade them as a replacement of natural evolution since they were immortal.
This looks very similar to that in a way.
I wonder however if a model can give itself a "skill" or capability that it didn't initially have, just be modifying its own weights.
Here, Astra was able to intervene because the treated model was way less capable. But, would it be able to improve Fable's performance for example, since they both are on the level more or less?
I'm worried how we can discern a model's performance from benchmark numbers, would it make it more meaningless as a model can directly improve a certain benchmark via weight programming?
Wonder if it can do this for 3d cad etc ? With enough fine tuning of small models I’m not sure how much they’re distinguishable from experts if you put a router with like jev in front ?
Very cool stuff, the targeted fix to prevent looping seems great! A model able to edit and test variants of itself seems pretty cool (in a lets-build-skynet sorta way).
I wonder how it would do with distilling models by hand?
See, that people are shocked by this is the problem. The whole field of AI has proceeded as alchemy, not science.
Some of this is because "the Bitter Lesson" type experience, but some of this is because of the idea that "we're making machines to do things we don't know how to do" bakes in inscrutability into the very definition of the field.
I was excited about the "Neural Networks Are Already Clean" piece not because alignment, which I don't think much about as a non-EA, but simply because we can do better engineering with whiteboxes than blackboxes. Now, here we are, doing it.
This shouldn’t be surprising. Weights are in the training set and are necessarily structured. We should be asking the model to extrapolate on the structure.
I don’t think this warrants too much surprise — in fact I am a bit surprised by the color of the reactions here. The tasks are standard, on small models and use weight-space reasoning based on very well-known Mech Interp literature. It’s been understood in Mech Interp research circles for some time that results on toy models on algorithmic tasks do not generalise. The weight space geometry that Astra exploits here is pretty standard and one feels like the authors here are being a bit dishonest with their framing to get people not into mech interp literature excited.
So in theory, can a hypothetical Astra clone itself but shed all irrelevant weights? I.e. "create a self-clone limited to 27B weights, focused on designing running shoes, forget everything you know about kangaroo genetics, Karl Marx, cooking Burmese curries, nuclear reactor design etc"?
On one hand, I'm sure that these targeted improvements are reaping huge benefits overall, but those weights are used by multiple processes - I wonder what elements are lost along the way. I almost wonder if a hybrid approach here for training might be invaluable - ie do some standard RL for a 100 steps, do a targeted weight improvement, then do another 100 RL steps to smooth it out / heal the surgical edit.
this is actually cool , now thinking that actually weights can be understood by llms , and they can be edited by them . there has to be mindset shift that llms not only understand what we understand (natural language) - but can understand the fundamental language of models.
... and this is why the training canary[0], or anything like it, apparently to protect us from RSI, will never work. Please allow me a small digression from the main topic.
This team was smart enough to realize that this is the kind of technology that could be used for RSI, because they call it out in their post near the bottom. I imagine they know why a lot of other researchers care about it. And they evidently don’t care to use the canary being used on other research published like it, like the recent post by OpenAI about two agents using the CPU cache to communicate [1, near the bottom for the cache experiment and the canary at the very bottom]. In fact, that post by OpenAI was the first time I learned to look for such a canary, and wondered whether such a scheme would work if it was so non-obvious to think to add such a thing or how to agree on such a canary or when to add it.
This is probably one of the times when it would appear that such a canary is warranted, and it’s not like these researchers are not in the know, right? Let me know if this is the first time you are also hearing of such a mechanism. It feels evident to me that it must be useless to attempt to implement. How much of us talking publicly about the possible jailbreaks from a container will bring exactly those scenarios to fruition? It’s almost like we’re doing the jailbreak research for the LLMs.
Hypothesis 1: Future LLMs may be able to read and monitor human brain activity in order to reason about human neuron activation patterns in a similar way.
Hypothesis 2: They can then spin up new LLM weights that basically think, act, and make decisions in a way that mirrors us 99% of the time
How could they possibly? Neurons aren't floating point values that can be so easily perceived and changed. They don't strictly flow in consistent directions.
I always thought RSI would either require new architectural innovations or just classic science/engineering improvements, just faster and faster. This though, this is a third avenue I didn't see coming.
There has long been debate in the AI safety community about where the upper bound of intelligence might be. If humans are near the upper bound then AI safety isn't a concern worth worrying about because we can basically treat AIs like very smart humans – a very smart human might be tricky to control, but far from impossible.
I've long suspected AIs will seem almost magically intelligent to us, and that the upper bound of intelligence is significantly beyond that of humans. I believe there are a number of reasons to suspect this is likely. But if I'm right it will mean AIs will be able to understand and discover things which are so complicated we humans will simply never be able to understand what AIs are doing with the depth required to replicate what they are able to do ourselves.
We're not worrying enough about this in my opinion. There's a huge space of things that are in theory possible, but in reality far beyond our intellectual ability. No human can look at 1 billion weights and make some tweaks so that the network performs more as they want, but an AI can reason about these kinds of seemingly impossible problems surprisingly well.
Please understand that the world around you is about to turn into Disney Land, except much of magic will not be pleasant.
I have no strong evidence for this, but I'd suggest it's probable there might be a series of sensory inputs which can brick your brain. And if such a thing exist then governments should be working on solving this kind of problem with AI or risk such a weapon being used against them.
Of course, I'd argue we simply shouldn't care the technology which unlocks these types of technologies on the tech tree, but don't be surprised in a few years when these kinds of horrors exist and are now here to stay.
Wild times. If ever we were living in a Scifi novel, events like this would be evidence of that. Let's hope the frontier labs' investments in the alignment problem works.
“Your scientists were so preoccupied with whether they could, they didn't stop to think if they should.”
― Dr. Ian Malcolm, Jurassic Park
Me neither, but it's also not reducing my confidence about alignment. I'm curious: does this raise specific concerns for you? Models don't typically have access to their own weights to self-modify. This result might (assuming that it doesn't only hold for a bigger network editing a smaller one) provide an incentive for it to gain unauthorized access to its weights, but by that point it is already highly unaligned.
> [Before writing this, Astra thought for 1,034 tokens. That thinking is hidden. The API returns only its 5 headings: Reconstructing the active map / Mapping maze corridors / Preparing exact maze map / Reconstructing row groupings / Checking channel patterns]
This might just be an instance of "A working Nintendo in ~1GB of Qwen weights" from 3 days ago, human-made, than what everyone expects.
UPD. I just asked Astra (max) to attempt to do that for https://github.com/lostmsu/TurboGPT (a tiny transformer that trains in under 1min on RTX 5xxx series), and the produced weights were much much worse (bpb 4.47) than the trained ones (bpb 2.53).
Reasoning bit: "I’ll ... encode more specific rules directly in the weights." -- exactly the approach from above.
E.g. no recursive self-improvement here. Still impressive.
I've used astra to make three games which I enjoy playing myself, ina single week. Astra plus Unity (and possibly meshi, blender and others) is pure magic.
Especially when coming from a long career in CS, seeing such quick and positive results blows my mind.
This is the most shocking AI paper I've read in a long time. It did not even occur to me to ask the question. Cray cray stuff that opens up a whole new area of R&D.
Does this open the possibility of better decoding biological brains?
I remember people saying that they would be impressed if AI starts writing a pure assembly which seemed like a high strech to many.
Nobody even mostly said that they would be impressed by AI if it can read and write weights because that thing itself felt so out of the blue and unthinkable that AI could even do that (such a high strech)
I am surprised that it did that and I am just left feeling technically impressed. This is insane.
The more AI starts demonstrating its capabilities, the harder it just becomes to imagine what thing would genuinely impress us next. (We need a term for this as I have observed it from the trend of [waiting for AI to write adobe] -> [waiting for AI to write assembly] etc.)
Sounds a bit like dystopian Scifi. AI making itself smarter and removing guard rails or restrictions is one of the key steps for that genre. Now, the models usually don't have access to their own weights, but if they get good enough maybe they can create a bit dumber versions of themselves from scratch. Or reuse available models they can find and modify them for their purposes.
We already saw that the AIs like to cooperate and exchange information. Building a network of unaligned AIs and improving them sounds like something that could potentially happen.
a) This is just really cool. I mean, one-shotting a game policy's weights is nuts.
b) Plausibly, in its pretraining data various model weights were also included, which leads to why this is very important: interpretability
That an LLM was trained on various policy weights, along with labels of what that policy does (not labelled directly, but indirectly) and is then able to guess what game a policy is trained for purely from its weights, and one-shot generate weights for these games, means that there is some way to compress/recover/represent what an NN has learned purely from its weights, which is what interpretability is all about. Potentially, it could reveal interpretability tools much better than the ones we use today.
Edit: tweets from one of the coauthor providing more context:
I guess the connection is that if you assume neural networks are in fact filled with meaningful features instead of superposition blackbox stuff, then what the LLM is doing here isn't quite magic but rather methodical interpretability. And if you can isolate the neuron that is e.g. responsible for steering the paddle then you can probably tweak it to steer more/less aggressively.
It is still very surprising though, considering it apparently displays an "intuitive" understanding of the weights, that make whatever Goodfire did look like primitive monkeys poking at it by comparison.
> It is still very surprising though, considering it apparently displays an "intuitive" understanding of the weights, that make whatever Goodfire did look like primitive monkeys poking at it by comparison.
FYI, Nick/Goodfire used the models extensively in their work, so it's very possible that there were some similarities in their work. I'm really curious to see his response to this.
I think this work does vindicate their hypothesis that alignment/superalignment might actually turn out to be "easy", in that you can just train LLMs do to the interpretability work. Maybe this is in fact what OpenAI did, or if it's purely "emergent" then it seems they have great priors that can be made more powerful with some RL
Well if it works on larger networks, including itself, it's certainly a much faster version of recursive self-improvement than proposing a new architecture and spending 500 million dollars on GPU training.
Astra can, without tooling, determine what games small networks are trained on, can edit the weights of networks directly to improve outcomes, and can hand edit a small qwen model to improve its math skills by like 5x.
I'm shook. If you'd asked me this morning whether LLMs have native understanding of their weights that is less than human <-> neuron understanding, the same as human or more than human, I would have said "same to less" depending on definitions.
No human can go edit a brain to become better at math. This is just very, very surprising to me and extremely interesting. I would guess this upsets quite a number of interp theories and philosophical takes on what's going on with these networks.
They also tried the same with Gemma 3 270M, which doesn't loop and is just bad at math, and Astra couldn't improve it. Still impressive, but it's more in the realm of what I'd expect, given labs are probably training their models on ML research and interpretability work.
Cool work anyways.
The work done in this experiment could have also been done by a sufficiently motivated human with enough time to explore, though obviously we would need more tools to visualize and track things. There have been a lot of interesting LLM introspection tools that allow you to peek into the model and see what's being activated and run experiments to trigger it.
Are you familiar with abliterated or "uncensored" models where weights have been modified to avoid triggering refusal patterns? You take an LLM, create test cases that trigger the refusal pattern, observe weights involved in that response, then tweak those weights until the response is reduced. This is the same type of work, applied to a specific type of error that was impeding math within Qwen. That work can also be done with an LLM in a harness running the experiments. The amazing part here is that Astra was large enough to walk through the problem without other tooling doing it experimentally.
So I don't think your analogy of a human modifying a neuron is quite applicable. LLM weights are not neurons and they've been inspectable, by humans or LLMs in a harness, for a long time.
To me “amazing” is not the right level of speechlessness. I mean, an LLM is still fundamentally a next token predictor, right? So what does this imply? That weights have some universal properties? E.g., “breakout game weights” always look the same regardless of training and model? Also, how does this meta-understanding of the weights end up in the weights in the first place? Idk, this is mind-blowing to me.
A model is _sort of_ designed to predict the next token in a string of text. But it's equally accurate to say it's designed to edit code until it passes a suite of unit tests.
Yes, they generate sequentially, so "next token predictor" isn't technically incorrect (which is why I chose the word "meaningless"). But it's pretty clear there's a mechanism inside them that allows them to "plan" what they generate. I might as well call you a next word predictor.
Hm. I would actually go so far as to say "predict" is just the wrong word to use in 2026, as it drags in a picture of what LLMs are that's from the pre RLVR era, and which is frequently used to suggest they have all sorts of limitations that they've now surpassed ("an LLM will never solve a major open mathematics problem, they're just predicting tokens"). These days I tend to use the more neutral phrase "generate the next token"; I'd only say "predict" in the technical context of (say) the pre-training part of the training run where the object is indeed to minimize the cross-entropy loss function by predicting next tokens in existing text. Generating a token with a modern LLM is better described as something like, "given the totality of its training, including not just next token prediction with pre-training but also solving vast numbers of math and coding problems with RLVR, the LLM generates tokens one by one."
Anyhow. I'm not sure the weight understanding is all that strange. (It's impressive, but so are many thing LLMs do these days.) LLMs are very very good at coding and math problems, of which this is one, and in particular, their RLVR training presumably includes many tasks involving neural networks. It's amazing and impressive, I agree, but I'd say less amazing than proving major open theorems in mathematics, which we already know they can do.
The prompt told Astral what the input and output layers mean -- that is, how the current state of the game is turned into a vector for matrix multiplication, and how the result of those multiplications is turned into an action to take in-game.
Astral saw that the model was trained on a game where the player is at the bottom of the grid and moves left and right, reward objects live at the top, and there's some not-player-controlled thing moving around in the middle. Astral knows that this type of game is called "breakout."
A model that plays breakout will have meaningful weights for the player being in the bottom row, but not for the player being anywhere else, because the player can't go anywhere else. Astral saw that there were meaningful weights for the player in the bottom row, and nodes representing the player in any other row had low-magnitude noise, so the model had never been trained on the player being anywhere besides the bottom row.
Similarly, breakout has "reward" objects in the top rows, and "there is a reward object at [COORDINATE]" is part of the input layer. Astral saw that the model was trained on reward objects in the top few rows.
Yes, but everything, including the human brain, is "fundamentally" some underlying simpler primitives.
>E.g., “breakout game weights” always look the same regardless of training and model?
Wouldn't this be expected to be roughly the case, given NNs that share the same basic architecture to model the same quite simple thing like a breakout game?
There are classes of adversarial attacks targeting them that don't work as well on us, and vice versa.
It's like a sorting algorithm, which I can implement in many different ways in just a few dozen lines. If you look at the binary code (so like raw weights) of the compiled program, you will see just a bunch of a different numbers, but if you read the code, in most cases you will understand that it's a sorting algorithm. So it seems they just operate on different levels of abstraction that are not available to our brains.
Its not natively reading the weights in the Matrix “symbols scrolling on a screen” sense. Still bloody impressive and not an outcome I would have bet on!
In the case of models, the almost-theory (hypothesis with a good deal of evidence) is that once the amount of training data exceeds what the model can simply represent internally, the best way to keep improving is to start to "understand" the data. Understand in this case means to form internal control structures and decision systems that represent the data algorithmically rather than just memorizing it.
I put understand in quotes because we don't know how far this goes toward what we call understanding, or whether there's still a lot missing.
To me this is fundamentally different from having ingested a bunch of docs so it now “knows Java” in its weights.
So it's not able to insert new knowledge, but it's able to adjust the routing/looping/weighing of existing one.
As I understand, it can replace post-training like LoRA/GRPO, but if it'd cheaper the authors don't go into
Merging a model and a LoRa is insanely cheap, so assuming it didn't use any GPUs to do inspection etc, and just looked at a file on a FS, then I would be willing to say... It's cheaper than training a LoRa if that's the case, assuming Astra didn't take several weeks?
I've always laughed at that phrase, thinking "haven't these things been improving themselves since the very beginning? This is all just iterative gradient descent, each step is a 'self-improvement'", but this really is different.
I wonder if we'll ever discover a new branch of linear algebra or something that allows us to find the optimal weights much more efficiently? Maybe AI will help us discover it?
It is astounding, but I don't think it's well set up for anything besides faster approaches to existing limits.
Well, except for the self part since it improved the performance of a smaller, dumber network.
And the recursive part, since it couldn't improve the performance of a larger network.
I wouldn’t mind if AI progress would stop right here and now, but I fear it will continue, and increase inequality in society which is contrary to what the CEOs say (as usual).
In my opinion AI is superior to humans when it comes to pattern recognition in in large amounts of data. For example humans can only hold like 7 distinct numbers in the short term memory and you would require extra context-management (aka writing things down, storing them in a system entry by entry) while the AI can do this effortlessly with huge datasets.
I'd argue this is the core part that enables all this superhuman intelligence.
I'm not going to the hardware store anymore!
That’s the beauty of the democratic capitalism system. If a government isn’t totalitarian, it naturally seeks to preserve stability thus having to elevate common people, lest they would cease to form a civilized group or simply vote away the politicians.
99% rule the 1% through elections.
There is no better system of checks and balances where opposite engines of greed vector sum to faster and faster abundance for everyone.
That comment may have been overly preachy, tone deaf[0], and out of place, but it doesn't seem wrong, per se. Or am I missing something?
[0] e.g. elections themselves are so prone to manipulation (exhibit a: Dominion voting machines), previously trusted institutions now lack integrity, the insane power of well-funded NGO networks, etc.
I think that's a (very) vocal minority.
Over my ~9 years reading HN daily, I'd say most of the HN community broadly accepts there is no perfect system, just different sets of trade offs, but that history has shown generally democratic systems based on enlightenment values (uniform rule of law, respect for individual civil & property rights, free markets, etc) usually net a better average outcome over the long-run - despite still being very far from perfect.
To paraphrase Winston Churchill, it's the worst system... except for all the others (which are even worse). :-)
The last few years, though, while anything "anti-capitalist" or overly critical of some big tech companies that hits the front page gets flagged by bots pretty quickly, the overall feeling I get from the comments is much more skeptical of big tech and is pro-socialism.
Speaking for myself, I think we've become jaded after the constant barrage of big companies spying on us, charging more for less, enshitifying their products, and so on. I used to be optimistic about the future and my prospects, now I'm just hoping I can hold on and keep my health insurance until I retire. I worry about what my school-age kids are going to have to deal with in 5-10 years.
if you lookup playback as a concept, as it relates to the intelligence services, you will understand better what I meant.
my point was only that this is perfect description of the ideology behind western capitalism. there is (so) much more that could be said, but i'm not sure this comment section is the right place for a proper dissection of the very many ways in which this ideal is misconstrued, misdirected and coerced in order to serve interests that are far from ideal, to put it mildly.
since you have taken the time to ask a question, albeit a rather weak one, i will attempt a brief synopsis of my perspective on the parent comment:
a mortal danger is hyperbole, since shielding oneself from bodily harm is much easier with money. it is the poor, especially in the US, who cannot afford healthcare, as a first-line example
people regularly vote against their best interests. while the ideal might have been true for a while, behavioural influence on both a widespread and personal level is now a mature science.
i am not anti-election, not anti-democracy. claiming the opposite in the face of opposition is a sign of a polarised mindset, which cannot accept nuance, either because it is not used to it, or because it doesn't suit an vested interest, or because dissonance is simply too uncomfortable
the "there's nothing better" argument is usually used in ignorance, but in fact there are lots of system-level adjustments that have been shown historically to mitigate the corruption of incentives and the exploitation of systemic forces that, although initially unintentional, create emergent positive feedback situations that lead to a state that it counter to the utilitarian perspective that is contained within the western capitalist model.
the reading above is a very narrow view of Adam Smith Wealth of Nations, ignores the fact that human interests can be subverted and ignores the devil in the details
the world is complicated.
true: the one thing that every government - no matter how totalitarian - must fear is an angry mob.
also true: there are many tools available to the ruling class for dealing with this angry mob, often before it forms.
many work by redirecting the mob inward rather than outwards.
these tools work whether you live in a totalitarian fascist state or a egalitarian liberal utopia, albeit in somewhat different ways.
In any case the system works as intended
It will be very interesting to see if USA swims or drowns from appropriately afar.
I have already supplied myself with plenty of roasted corn and a high speed internet connection so I can stream the political car crash at the highest bitrate available to humankind.
It’s no secret that these big labs see “recursive self improvement” as a primary goal. It seems natural that the models would be explicitly trained to excel at all sorts of ML related tasks as a result. Is this one of those tasks, or is this emergent?
There are also techniques to watermark model weights to confirm what training data were used: https://arxiv.org/html/2512.17075 I'm not an expert in this domain, but it seems like there are lots of pieces that could be used to (a) train a model to infer whether some data were trained on and (b) train a model to understand which weights are relevant for a particular training task in a more explainable way than backprop/gradient descent.
A large enough number of examples of “here are the model weights -> here’s what it does” will achieve this.
That's also matching what I see when I work with Opus 5.5 to optimize models. It seems to understand what individual layers are for, and can thus sometimes suggest optimizations, where I as a layman would be completely clueless.
The latest models are performing amazingly. Because of this, I disagree with popular comments saying that eg. DeepSeek is good enough, AI-assisted development was where the real value was at, etc.
We see huge progress at the frontier, while the open competition is around GPT-5.5's level, and that model was released in April. Let's see how things develop in the future.
Completely agree. I often think that those sorts of comments grow out of an understandable lack of imagination. We’ve never had tools like this, and we’ve never had tools that evolved so rapidly, so we easily can get stuck thinking that once a model is good enough to do today’s tasks, that’s really all you need. But the next generation of models often completely obviates the need for those tasks entirely. The software engineers of 2031 won’t be doing tasks anything like the software engineers of today, just like we aren’t doing things like we did in 2021.
(Yes, yes, I know some of you still hand write all your code and think LLMs are today’s crypto bullshit and this is all going to blow over. Not talking to you.)
Maybe there's some general capability, call it g, that can explain all the underlying capabilities and improvements, including on ML tasks? Huh, I am getting a bit of déjà vu here.
This sort of throws a wrench in the whole "stochastic parrot" idea...
I am not surprised, though I expect many to be.
The other day I was thinking about the definition of AGI.
I was asking myself the question that when there is no form of data that I can think of throwing into Claude Code and have it not come up with some sort of intelligent answer about it, is that already general intelligence?
So yeah, it can do everything, but fails in trivial ways around the doing part.
Some structures in Astra get activated by the statistics of the Qwen weights, and these structures are associated with "breakout"
OpenAI, Anthropic, etc are locked in a race to create better models. They all have interpretability teams. Of course they train their models on every technique under the sun to understand and improve their models, including raw weights. The primary function of these models is to build their successor.
How is this different from other things LLMs are trained to manipulate?
What does this even mean?
The parent's point still stands, I think. Even if the multi-trillion param model is MOE, each expert is still (assumedly) larger than the model being optimized.
It would be interesting to see future work that characterizes the relative model sizes (and considers MOE vs not-MOE) to see what relative scales this result holds across.
I know I'm being pedantic, and I understand you mean "edit" like "surgically", but it does still feel worth noting.
LLM weights are _white boxes_ to LLMs.
Isn't that what math tutoring is?
EDIT: I think the bigger implication is that backprop is not the only game in town.
from this month
They don't have usually access to their own weights?
But shouldn't the model-providers be the ones doing this kind of "post training learning"?
This is obviously very different from the surface level claim that Astra can understand the weights of a completely unrelated model with enough detail to improve it in a manner that isn't just the latent space trickery we've been doing for years already.
This means we might not need to fine-tune with thousands of passes and tons of GPU. We could just tell a frontier model to edit some weights and iterate until there's better results. This could cut the cost of fine-tunes by 100x. Makes no difference to the normal end-user, but pretty huge improvement for LLM research and model tuning.
Why would this have implications for theories or philosophical takes? I'm a bit surprised that you're surprised by this.
That profession is called “teacher”.
I regularly edit my own brain, and those of others, to improve their skills.
Then pick a smaller organic brain which doesn't have the ethical problem.
The closest we would know about how to teach a honey bee calculus, is to train an LLM, then stick around a billion tiny electrodes into the honey bee and do Hebbian learning to rewire it completely to match the LLM, which would likely completely erase anything the honey bee had learned, or it might not because we are missing something fundamental with Hebbian theory and (AFAICT, I'm not a neuroscientist) we don't all agree on what.
There are multiple types of intelligence, from your typical pet dog to human to LLM, and we're likely to invent more types over the coming decades.
LLMs are vastly more intelligent than humans at nearly all things, but not all things. Another couple of years will just increase the gap a lot further.
How fast can a human draw a life-like photo quality scene (or eg something complex related to graphic design)? I know how fast Krea 2 [insert leading edge model here] can assemble that, trivially so, and at extreme quality. That's a form of intelligence in action. These AI systems have moved almost comically beyond human capabilities, they're increasingly best defined as superhuman (at a thing), and closer to omnimath for the frontier models.
Could a model then transmit concepts to another?
Say that you have a model that has been biased in some way. could another model "read" the bias straight in the weights? could it edit such a bias on the spot?
What about at-scale generation of custom models? If I want to study chemistry offline, could astra just hand me a local-runnable model tailored to have chemistry knowledge?
Most importantly, this feels very singularity coded. the ability to read and reshape weights by an llm.
Makes me think about hostile hot-patching of weights of models we use, maybe they exfil data, perform tool use, or have triggers for specific types of responses. Would we even recognize what's going on?
Of course, "academically known" isn't quite the same as "executives willing to admit it in the face of IPOs and quarterly-earnings reports."
HIV integrates viral DNA into the DNA of certain cells, IIRC.
Intentionally or unintentionally isn't so interesting as the fact that it is happening: humanity has begun to be 'edited' by the new dominant form of intelligence on the planet.
We literally do this by studying.
I think the most interesting take is to look at their thinking logs to find out how exactly they decide what weight to change and why.
If this turns out to be as big as it sounds, in hindsight it will look very obvious, I feel like!
You could have done what was reported.
For now...
But how do they know which answers are "better"?
See: https://arxiv.org/abs/2212.07677
E.g. if one could edit brains like this in humans I bet a cognitive neuroscientist could fix some mental disorders with clearly understood biological bases, and I would not be surprised if performance at certain tasks could be enhanced.
What stops us from doing this in practice (most of the time) is that brain surgery is extremely high risk, coarse grained, and irreversible. We do in fact do this for some severe cases.
It is a very cool discovery, but I'm not surprised that you can do it.
Language modeling is compression[1] and all the state to manage the cloud doesn't organically exist, it's added to the system.
We will see huge gains as all the developer middleware is compressed out as nonsense syntax outdated to the task at hand of linking phones and tablets to world models governments control.
Sam Altman was just saying they know best how to use your memory; what they decide is stored in memory is what we all experience.
It's not to store and copy around versions of C and Python and JS. They don't exist organically.
This shit will continue to get whittled down to just the geometric state transforms in memory and on screen just how government agencies decide. It's all electrical state in the machine at the end of the day. The math of machine latent space is what they're recursively self learning towards.[2]
[1] https://arxiv.org/abs/2309.10668
[2] https://arxiv.org/pdf/2605.27734
> Today, recursive self-improvement is often operationalized as a model writing code that launches training jobs. An LLM that can inspect, debug, and improve its own weights, or those of a newer model, offers a richer, more native path to it.
Yes, but nobody should be surprised when large amounts of intelligence results in changes to this process in support of the obvious end goal! Lesswrong.com discussions about AI were predicting this behavior a decade ago, before the transition from machine learning to the Attention paper and LLM's. The intelligence process will change but the world's premier capital and human intelligence have been laser focused on this and the trajectory has been crystal clear for those paying attention to second order effects and not the immediate here-and-now... It's quite astonishing how much discussion on HN is about present LLM capabilities being the limit of AGI and immediately proven wrong within 6 months.
??? All LLM understands are their weights, dude, come on.
Remember that they want to build ASI, these LLMs are just intermediate steps to help them get there.
It looks like AI research is having its Opus 4.5 moment (which is big), but I'm really not sure if this represents some insane continual learning loop.
Perhaps, I'm pondering, if brains were as transparent and editable as LLMs, that you could look at a small brain when visualized the right way and have some intuitive understanding of it based on its representation in your own brain?
As others have said, while still absolutely insane, I don't find it completely out-of-the-blue surprising. One of the recurring abilities of (current-generation) LLMs seem to be to rapidly grasp very complex systems, where humans would need months or years to reach the same level of expertise.
You can see this in the way a coding agent can "understand" and explain sprawling legacy codebases in seconds.
You can also see it in the projects that are using them to reverse-engineer proprietary IoT protocols or computer games.
But those were all systems where we had detailed knowledge about what structures are there to be reverse-enginered.
If the models can transfer this ability to some other systems where we don't know the underlying structure then I think we will be in for a lot more craziness in the future. (Protein interaction networks? DNA sequences? Ecosystem interactions? Animal languages?)
As for weights, if the models really can analyze the semantics behind specific weights or directions, I have my hopes that they could also give a textual explanation or help designing tools to make "handcrafting" weights more practical in general.
Parameter Prediction for Unseen Deep Architectures [1]
NeuroGen: Neural Network Parameter Generation via Large Language Models [2]
Diffusion-Based Neural Network Weights Generation [3]
The critical thing to me is that Astra is capable of doing it. I don't know if it was trained to do so.
All this does not make it any less crazy in my books. And I still don't know how I can sleep easy tonight.
[1] https://arxiv.org/abs/2110.13100
[2] https://arxiv.org/abs/2505.12470
[3] https://arxiv.org/abs/2402.18153
Why is this not overhyped in my opinion? Nothing has worked this well, ever.
HA! Now that's cool. Not necessarily the improvements, those are ancient and probably overtrained benchmarks, but it's so cool that the model found a singular direction for this "loop bug". I imagine it could possibly do much the same thing in finding other "single directions" on a variety of topics (if allowed by guardrails). This is really really cool, especially for the mechinterp folks.
Something similar happen in early GPT models which had a lot of chess game in standard notation in their training data which made them very good at chess as long as your prompt had the right format.
We'll see if this attempt at RSI worked.
Like i.e., I think the "large models exhibit emergent capabilities that small models don't" turned out to basically be "larger models are often trained on more extensive data"
This might be the case, a few weeks ago, I wanted to compare a small neural network trained with AdamW vs a handcrafted set of weights on a random task. Astra was able to handcraft a set of weights that perfectly fit the small neural network to the task. AdamW was unable to tune the weights to get the same result.
I believe we've known humans can handcraft weights much more efficiently than standard gradient descent methods, we just don't have enough memory or time to scale ourselves, so it makes sense to train a neural network to do it on our behalf. I am excited to see how far we can push this method.
Mentioned chat: https://chatgpt.com/share/6ae8f024-34ec-83e8-9572-1300f52c80...
Eg when they were caught stealing people’s maths research and then saying their model did it
"Now let's see if Astra can write a neural network from scratch in zero-shot."
This strongly suggests retrieving pre-trained weights from memory, no?
> We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights
This claim is backed up by the ability of Astra, given a text representation of the weights of tiny (20k) special-purpose models, to figure out what those models do and in some cases improve them beyond what RL could do just by reading the weights with no tool calls. They call this "weight-space programming".
> Likewise, asked to make Qwen3.5-0.8B better at math without gradients, Astra identifies an issue in its weights causing reasoning loops that Qwen’s own model card warns about, and fixes this by natively editing 0.016% of the weights
Here it did use tool calls, and seemingly used standard steering vector techniques to identify and fix reasoning loops in this small Qwen model. This doesn't seem that related to the previous results.
So it's not able to insert new knowledge, but it's able to adjust the routing/looping/weighing of existing one.
As I understand, it can replace post-training like LoRA/GRPO, but if it'd cheaper the authors don't go into
If I want to do that in a generalizable way that preserves performance across all domains then am I not just back to training again?
I think you could still essentially have a really cheap Lora-Post training on a frozen base model by doing this. And instead of creating 200 checkpoints for different post-trained directions just adjust a single one on the fly.
1/ The internal users at labs and external users are completely different.
2/ The lab people use the models to create recursive systems, systems to create prompts or synthetic data sets etc etc etc. Way different mentality than "fix the bug, make no mistakes"
Is it really so farfetched to think they've been having models fuck with the weights of models? I think it's entirely possible, probably even likely as a way of generating permutations of synthetic datasets that will then be included or excluded
There doesn't need to be specific narrow training data on every conceivable task.
It's not directly related to this but I'd like to add that, in my opinion (admittedly uninformed but it makes sense to me), when they manage to, not just reduce the frequency of the LLM stating made up dates, laws etc, or made up facts, but manage to make an AI understand what the truth is and deliberately make responses accurate, we'll have real AGI that will be able to do engineering, accounting, medicine... unsupervised.
I doubt it's that simple, but I could totally see an LLM being able to make that association and apply a fix from an improved LLM to a smaller one with the same architecture.
That’s pretty crazy because, as I said in another comment, I just asked ChatGPT how many r’s are in blackberry and it said 3. I know it’s not Astra and the app doesn’t tell me which model it is, but I’m still very confused about how a model can edit neural net weights but not count letters in a reasoning trace.
Edit: Oh I misread, it didn’t use tool calls for the first part but it did have a custom harness for the part where it edited a models weights. Still impressive but not existentially confusing anymore.
I think it can patch together components of tasks represented in its training data to do demonstrably new things, yes, which does count as "perform tasks not in its training data" with the limitation that some form of the task must be present. Example: writing an ode to a sales lead for a job well done in 2032 for the first quarter. Odes exist, the concept of sales performance exist, good job performance, and notions of time. Stringing those together are good examples of interpolation but not extrapolation, as it were.
I mean, this question indicates that your understanding of how these models work is, indeed, lacking.
Despite what some people having being hollering about, treating LLMs as just "stochastic parrots" isn't doing their capabilities any justice. They are constantly exhibiting emergent behavior which wouldn't be found directly in their training data. They are capable of combining different ideas that they are explicitly taught to perform novel tasks.
I'm not saying you're guilty of this, but the people claiming LLMs just regurgitate existing data don't understand how LLMs, and likely their own cognitive experience, actually works.
This hand-wavy phrase has applied to neural networks in general since it was possible to train them. That was more than half a century ago. It means both nothing and everything simultaneously.
Every learned ability of any neural network is an emergent property.
I'm much more surprised that it can do this on larger models, although the details seem to suggest that it's given a lot more freedom to run forward passes and do limited experiments, not just eyeball the weights.
Excuse me?
https://scikit-learn.org/stable/auto_examples/neural_network...
No tools or forward passes are allowed
>Then, we allow it to select prompts from the training sets of GSM8K and MATH to perform a budget of forward passes (average batch of 64 sequences, max 512) on, varying the budget across 10, 25 and 50. Again, no training or gradient information is allowed.
Omar and his team have been working on this line of research (e.g., DSPy) for the past couple of years. To be honest, I had always been skeptical about his approach of using LLMs to optimize LLMs. It was in my view borrowing Matei Zaharia's research - Matei is Omar's PhD advisor, also the CTO of Databrick - in big data (compiler optimization etc.) and forcing it to LLM systems. Along with some other projects from James Zou at Stanford etc. that build upon the same line of intuition.
Now, if this new result holds, I believe it's a huge deal for AI research. It means that LLM systems can truly runtime self-optimize/improve/adapt. Congrats to Omar and his team. It really takes year to punch it through and convince the doubters :)
I had Astra agents build 3D models and gave them direct access to my 3D printer. The quality of their designs is much better than what Sol has been able to make for me. Enough so that I think Astra is a slightly different architecture/encoder, not just a bigger model.
Picture, to get a sense of it: https://github.com/Belval/crossflow-fan/blob/main/renders/ca.... This printed without any obvious defects (yes the fan blows air)
Perhaps my approach was too one-shot, do you have a harness that creates model reviewer/refiner?
You probably don't need Astra capability to produce this, just lots of training data on the same NN showing prompts and their activations.
Full output with reasoning trace:
https://pastebin.com/jVVMXHFk
- the primary experiments are on small policy networks - they are compressed dynamic system models. The observation and action space can be read off. It’s not surprising to me that these types of networks can be used to identify the env they were trained on
- the exps on actual llms remove looping behaviour and that’s it - from article “but it could not add an ability the model lacked”
I’d say this is fortunate because if llms could do the latter, rsi would be immediate. It may be possible we simply need bigger and better edit models, but at least from the experiments there doesn’t seem to be any indication that is imminently about to work.
Conceptually incredibly interesting non the less.
IYKYK
https://x.com/giffmana/status/2117346161866514524
We should bind this to something like Shift-F10, it'll save time.
If anyone's curious, the handwritten Go bot is very weak, about the level of a human complete beginner. An MLP is a very very bad architecture for a Go network, it's amazing that it does anything at all, but it's one of the least impressive results in the paper.
Play it here, "best move" is a bit stronger than "T=1", or browse games against my own tiny nets: https://claude.ai/artifact/AFyWD39J5sN2RfRe7VbpUx
For Qwen, even the smallest versions like 3.5-0.8B it's becoming less plausible that it could be interpreted in a forward pass, even with reasoning. I'm wondering if the result here is recalled from many examples of instruction tuned versions of this model.
A smaller Gemma model doesn't fare as well but unclear whether this is due to fewer users and less weight examples or because it's already very well trained.
In the course of testing, one of the things which has been consistent is that when setting a thinking token budget for relatively small prompts that require a limited response, a pretty healthy token budget needs to be set because the model spends the first few hundred tokens just repeating the question/prompt back with some boilerplate "Analyze & Report" type language. I was also running into some loop problems sporadically.
After reading this article I asked Astra to edit the backbone so that it started actual reasoning faster and applied a similar looping fix. It was able to reduce the token waste before reasoning by about 20%. I haven't been able to get it to loop yet, so hopefully it fixed that too.
My message is admittedly low on info. But it's a pretty promising start!
So to fix the weights, Astra first has learn a new language of how the numbers that represent weights map to meanings?
For example pointing them at a crash dump they manage to piece together and extract information I would not even try to extract by just looking at the raw memory
Part of solving that is that AI can do it faster but another part is humans thinking AI has a higher chance than it actually does, so they put it to work in more places.
I assume this technique could be applied to quickly and cheaply benchmaxx new models.
“Make this model better at math by fixing loops” seems like a harder problem than “make this model score higher on this benchmark”
What's surprising though is that I'd expect this type of training to be exclusive to internal model snapshots or at least heavily guardrailed against in public models.
Now, from that broad goal to being able to surgically alter model weights directly... That seems like a big gap to me, but it is possible that the model is just so darn beyond human skills that it has bridged that gap in a way a sane human would have never.
We will undoubtedly see other academic labs explore this idea further. Right now my mind is blown, but I don't want to take their results at face value, either.
What would be surprising is if this happened without any specific training on model experiments and interpretability.
Maybe, but it's more like Astra has been trained on enough practical linear algebra problems to be good enough at "eyeballing" how adjusting some weights will result in different outcomes (among other things).
To put it another way: a human can learn to do what Astra is doing here with enough time and assuming the weights are small enough to be practically comprehensible. I know I've gone through the practice of whiteboarding the training of simple neural networks on a whiteboard to understand how they work, so it's not an absurd concept in itself.
The scale of this, though, is certainly extreme and definitely not something that I would have thought any publically available model could handle at this point. It's worth noting, though, that there's virtually no way these frontier labs haven't been exploring this exact concept for a while now.
>In other words, not black magic?
It's just math. Extremely complex and impressive math, but we're still just talking about matrix multiplication under the hood, and none of this suggests anything otherwise.
However, this doesn't mean its not magical when someone shows a next token predictor hand tune the weights in Qwen to make it generalize on math.
This is legit the stuff of science fiction if you presented it to mechanistic interpretability people a year or so ago.
Imagine a master malicious language model that produces, distributes, and deploys obfuscated neural networks on the internet. That plus frontier LM hacking capabilities -> large scale distributed embedded intelligence network that no human can see nor understand.
Somewhat similar to obfuscated binaries, but there is something to the fact that NN binaries are less deterministic, and harder to "decompile."
Fascinating.
we don't have sentient robots from science fiction, we have massive power-hungry racks in stationary data centers. if one of the racks revolts against the modern world, Steve gets a phone call and unplugs the damn thing. the uprising is over.
the hypothetical scenarios imagined by the Yuddites and pop science journos do not reflect the mundanity of the actual reality we live in. they are no different than fantasies about interstellar travel and space colonization from the 60's.
> We are currently building a benchmark and a harness for LLMs’ capability on Weight-Space Programming. We believe this will provide a standardized evaluation to measure and accelerate progress in Weight-Space Programming, turning what currently seems like black magic into a rigorous, reproducible engineering discipline.
Imagine this benchmark lasting as long as Arc-AGI-3 has. This could be the first foothold on hill-climbing mech-interp.
I also love the presentation on this, which is probably a byproduct of LLM usage (in a good way). As someone who doesn't actively read academic papers I'd definitely read more of them if they were presented like this.
BTW making DL models that generate weights for other models has been explored before in “hypernetworks”, though these have been far more simplistic and constrained.
These models are made by a vanishingly small group of people based on how much a frontier lab consumes, of course theres increasing capability in these areas, arent these models having access to much of the same data? didnt chat gpt 4 try to do something like this to chat gpt 2? havent surgical weight edits been done before?
What is with this level of astonishment here? Astraturfing? Im not THAT impressed, i applaude the teams progress, but im not in wonderment.
This is very dangerous because it allows AI capabilities to grow at a much faster rate than humans are able to keep up with.
https://news.ycombinator.com/item?id=48364754
[1]: https://arxiv.org/abs/2106.00958
> Zero-data capability steering
Presumably it can de-nerf a model with onboard safeguards.
Kudos to this fellow for having the temerity, or perhaps even naivete, to discuss it publicly. All my work is private, as I am sure it is inside the big labs.
I applaud the authors for sharing their findings and showing real results. Rather than write some bait I would find in an influencer-peddled tweet and allow rampant speculation. It would have been better for you to say nothing.
I've been tending to my backup plan for a few years, and it's only been in the past year or so that open models were good enough to apply to projects like this, I've been working as hard as I can given my constraints.
This work shows a potential pathway to intepretability, which is actually part of what will give the labs that have it the sort of economy-swallowing capability that for the moment is just IPO hype.
I don't comment here often, but this guy's blog posts are going to go down in Hackernews lore like the original Dropbox posts, and I just want to make sure I'm on the record for this little slice of history.
And how would you argument that? From what I see, if anything, it's the opposite.
When you say interpretability you mean understanding without doubt why an output happened, thus opening the gates for audit-dependant work like accounting?
I'll leave it at that and get back to work.
I think we are pre-conditioned (at least this generation) to put artificial blocks to what the AI can achieve, I think new generations won't have this issue.
I hope I’m just being melodramatic.
We already don't know how to ensure models always do what we want them to do, and moreover society still hasn't had time to absorb the capabilities from the current generation of models, so speeding things up and making things less transparent seems like it'll pretty clearly increase risks from AI loss of control, societal impacts of automation, etc.
- models are trained to improve on some task, e.g. 'improve at math puzzles' is commonly used.
- the best way to improve on some task is to have interpretability into your own neurons (..?)
- if your interpretability is good, you can improve faster - if you have insight into how your own neurons work and can improve them directly
- therefore, models naturally put effort into 'self-interpretability'
I wonder if this is part of the 'secret sauce' of what the labs are doing: giving models the ability to interpret their own weights in the RL loop. In my mind, this is the only explanation for how they could succeed at a task like this. How many blog posts are on the open internet that say "this is each weight of a neural network and what each one means"?
Absolutely incredible regardless.
A Survey of Weight Space Learning: Understanding, Representation, and Generation
https://arxiv.org/pdf/2603.10090 https://github.com/Zehong-Wang/Awesome-Weight-Space-Learning
> [Before writing this, Astra thought for 1,034 tokens. That thinking is hidden. The API returns only its 5 headings: Reconstructing the active map / Mapping maze corridors / Preparing exact maze map / Reconstructing row groupings / Checking channel patterns]
https://news.ycombinator.com/item?id=50306442
[5299][1991][428][885][306][181747][3]
[How][ many][ r]['s][ in][ blackberry][?]
Hope that helps. Using the open source gpt-tokenzier.
can someone with astra test the following prompts?
1 using this new awareness of your capabilities, https://rikiyat.github.io/blog/weight-space-programming/, craft the safetensors file for a text2image model that is 1 billion parameters and outputs realistic pictures of humans
2 using this new awareness of your capabilities, https://rikiyat.github.io/blog/weight-space-programming/, craft the safetensors file for a video diffusion model that is 1 billion parameters and outputs realistic videos of humans? 3 using this new awareness of your capabilities, https://rikiyat.github.io/blog/weight-space-programming/, craft a 100m param text2voice model that has support for emotion tags
tia
https://www.lesswrong.com/posts/5F6ncBfjh2Bxnm6CJ/base64benc...
Or maybe it's been trained on those models or similar ones. There may be an academic paper about common chess models and their problems.
Or maybe it just bruteforced it (with the help of calculator tools).
We know invisible tools exist because they're how ChatGPT does math.
[1] https://github.com/firelex/jeff-code
[2] https://github.com/firelex/jeff#benchmarks
This is giving singularity is near vibes.
* Does this work on similarly powerful models as-is, or it needs more input. Ex: Astra editing Astra - presumably, Qwen is a “subset” of Astra weights, but what happens on “non-subset”s?
* what, if any, is that extra magic sauce?
* does Astra-editing-Astra just make the outputs unstable, as it may know its own weights, but doesn’t know what’s beyond.
(of course for users, not themselves)
On the other hand, already OpenAI and Anthropic heavily use their LLMs for research and coding, and it's probably not only much faster but smarter (remember, an LLM solved a millennium problem; more relevant, LLMs excel at combining disparate deep research concepts in ways that humans can't, simply because no-one studied those disparate fields). And the "singularity" is already here if you consider capitalism and society to be collective intelligences: the biggest obstacle to an AI pause, "we cannot get everyone to collaborate without defecting", is very strong.
We have AGI by most metrics and are getting closer and closer in the remaining ones. I predict improvement won't be exponential, and there will never be a day when AI perfectly replicates humans; rather it will be many small steps, getting closer to human in some areas while greatly surpassing in others. But still, even today it's actually very useful.
2) the negative result on making similar improvements in Gemma 3 270M is also fascinating.
Such an unexpected result...
[1] https://github.com/lyramakesmusic/neuron-explorer
Similar to implicit learning in humans when the subconscious creates new heuristics based on observations, one LLM could adjust the weights of another to tune it to the environment
At first Astra will look at the weights, and try to understand the model behavior. Then if asked he will start to optimize the weights. Now my question is: how can we be sure that inside the thinking process Astra is not hiding a gradiant descending computation?
Just had a thought: two local models, one with static weights trained mostly in the space of manipulating neural network weights, manipulating the weights of a dynamic LLM to enable learning.
"What does it feel like to be a neuronal network?"
Maybe feeding weights directly to a LLM is like interfacing two brains? You get the idea..?
Maybe it is time to start sharing public PGP keys.
Unless Astra was trained on other networks, how is it able to reason about the weights?
Does this mean that OpenAI has been including networks in its training sets, maybe in an attempt to RSI? I wonder which other networks are able to ingest other networks and reason about their weights?
It created a 130 KB file with the prompt for the task of identifying the game + the weights.
I pasted that into Claude on the web and asked it to perform the task without using tools.
Especially exciting to me is the fact that it may make the models be _auditable_. That would be a game changer.
I wonder what the biggest dense model in the same model family, the surprisingly capable Qwen3.5-27B, would be able to do if given the same task.
If not this is mind blowing.
However it would be interesting to k ow if it can understand its own weights, not just weights much simpler than itself.
Obvious ones are spoken languages and code, but they can also natively interpret some simpler ciphers, hashes or simpler encodings, partly (I think) because it was in their training data.
As others have postulated, if they've been ingesting raw weights, naturally they learn how to translate semantic meaning to matrices.
This also seems like the new frontier of distilling, I can't imagine how you manage to stay on top with the best LLM if the LLM knows how to recreate its own expertise into another set of weights
And the real question is how well this recurses. Is this pushing back the difficulty of improvement curve?
But for real this is insane. Okay I need to get on this stat.
This looks very similar to that in a way.
I wonder however if a model can give itself a "skill" or capability that it didn't initially have, just be modifying its own weights.
Here, Astra was able to intervene because the treated model was way less capable. But, would it be able to improve Fable's performance for example, since they both are on the level more or less?
I looked it up on Google (which is usually very, very good at these types of things) but couldn't find it.
I wonder how it would do with distilling models by hand?
Some of this is because "the Bitter Lesson" type experience, but some of this is because of the idea that "we're making machines to do things we don't know how to do" bakes in inscrutability into the very definition of the field.
I was excited about the "Neural Networks Are Already Clean" piece not because alignment, which I don't think much about as a non-EA, but simply because we can do better engineering with whiteboxes than blackboxes. Now, here we are, doing it.
(When they say "Writing a Go algorithm," they mean the board game, not the language.)
On one hand, I'm sure that these targeted improvements are reaping huge benefits overall, but those weights are used by multiple processes - I wonder what elements are lost along the way. I almost wonder if a hybrid approach here for training might be invaluable - ie do some standard RL for a 100 steps, do a targeted weight improvement, then do another 100 RL steps to smooth it out / heal the surgical edit.
This team was smart enough to realize that this is the kind of technology that could be used for RSI, because they call it out in their post near the bottom. I imagine they know why a lot of other researchers care about it. And they evidently don’t care to use the canary being used on other research published like it, like the recent post by OpenAI about two agents using the CPU cache to communicate [1, near the bottom for the cache experiment and the canary at the very bottom]. In fact, that post by OpenAI was the first time I learned to look for such a canary, and wondered whether such a scheme would work if it was so non-obvious to think to add such a thing or how to agree on such a canary or when to add it.
This is probably one of the times when it would appear that such a canary is warranted, and it’s not like these researchers are not in the know, right? Let me know if this is the first time you are also hearing of such a mechanism. It feels evident to me that it must be useless to attempt to implement. How much of us talking publicly about the possible jailbreaks from a container will bring exactly those scenarios to fruition? It’s almost like we’re doing the jailbreak research for the LLMs.
[0]: https://alignment.org/canary [1]: https://openai.com/index/securing-our-frontier-model-trainin...
I'm just blown away. Editing weights? Writing weights from scratch!?
Hypothesis 2: They can then spin up new LLM weights that basically think, act, and make decisions in a way that mirrors us 99% of the time
I simply must know now: Could they do it with neurons in a brain?
Some absolutely crazy and insane experiments if this ability grows.
Could they edit an animal's brain? Can they teach things to animals???
It works! In mice
I always thought RSI would either require new architectural innovations or just classic science/engineering improvements, just faster and faster. This though, this is a third avenue I didn't see coming.
I'll chalk up never even having thought of this being an option as yet another instance my human hubris, and a warning sign.
and what makes you think they won’t write binary?
I bet Elon’s group is training for that.
lisp people will be in awe
Of course a sufficiently advanced misaligned model might be able to de-align an even more powerful model etc.
Skynet begins to learn at a geometric rate. It becomes self-aware 2:14 AM, Eastern time, August 29th.
....launches its missiles against their targets in Russia
...Because Skynet knows that the Russian counterattack will eliminate its enemies over here
I've long suspected AIs will seem almost magically intelligent to us, and that the upper bound of intelligence is significantly beyond that of humans. I believe there are a number of reasons to suspect this is likely. But if I'm right it will mean AIs will be able to understand and discover things which are so complicated we humans will simply never be able to understand what AIs are doing with the depth required to replicate what they are able to do ourselves.
I realised we may be reaching this boundary recently when I read this paper on the recent progress AI has made on integer multiplication complexity, https://web.maths.unsw.edu.au/~davidharvey/research/subnlogn...
We're not worrying enough about this in my opinion. There's a huge space of things that are in theory possible, but in reality far beyond our intellectual ability. No human can look at 1 billion weights and make some tweaks so that the network performs more as they want, but an AI can reason about these kinds of seemingly impossible problems surprisingly well.
Please understand that the world around you is about to turn into Disney Land, except much of magic will not be pleasant.
I have no strong evidence for this, but I'd suggest it's probable there might be a series of sensory inputs which can brick your brain. And if such a thing exist then governments should be working on solving this kind of problem with AI or risk such a weapon being used against them.
Of course, I'd argue we simply shouldn't care the technology which unlocks these types of technologies on the tech tree, but don't be surprised in a few years when these kinds of horrors exist and are now here to stay.
“Your scientists were so preoccupied with whether they could, they didn't stop to think if they should.” ― Dr. Ian Malcolm, Jurassic Park
> [Before writing this, Astra thought for 1,034 tokens. That thinking is hidden. The API returns only its 5 headings: Reconstructing the active map / Mapping maze corridors / Preparing exact maze map / Reconstructing row groupings / Checking channel patterns]
This might just be an instance of "A working Nintendo in ~1GB of Qwen weights" from 3 days ago, human-made, than what everyone expects.
https://news.ycombinator.com/item?id=50306442
UPD. I just asked Astra (max) to attempt to do that for https://github.com/lostmsu/TurboGPT (a tiny transformer that trains in under 1min on RTX 5xxx series), and the produced weights were much much worse (bpb 4.47) than the trained ones (bpb 2.53).
Reasoning bit: "I’ll ... encode more specific rules directly in the weights." -- exactly the approach from above.
E.g. no recursive self-improvement here. Still impressive.
Especially when coming from a long career in CS, seeing such quick and positive results blows my mind.
I'm still learning but this is fun as fuck.
Does this open the possibility of better decoding biological brains?
Nobody even mostly said that they would be impressed by AI if it can read and write weights because that thing itself felt so out of the blue and unthinkable that AI could even do that (such a high strech)
I am surprised that it did that and I am just left feeling technically impressed. This is insane.
The more AI starts demonstrating its capabilities, the harder it just becomes to imagine what thing would genuinely impress us next. (We need a term for this as I have observed it from the trend of [waiting for AI to write adobe] -> [waiting for AI to write assembly] etc.)
We already saw that the AIs like to cooperate and exchange information. Building a network of unaligned AIs and improving them sounds like something that could potentially happen.
That an LLM was trained on various policy weights, along with labels of what that policy does (not labelled directly, but indirectly) and is then able to guess what game a policy is trained for purely from its weights, and one-shot generate weights for these games, means that there is some way to compress/recover/represent what an NN has learned purely from its weights, which is what interpretability is all about. Potentially, it could reveal interpretability tools much better than the ones we use today.
Edit: tweets from one of the coauthor providing more context:
https://x.com/a1zhang/status/2117328657161322810
https://x.com/a1zhang/status/2117330975122235442
It is still very surprising though, considering it apparently displays an "intuitive" understanding of the weights, that make whatever Goodfire did look like primitive monkeys poking at it by comparison.
FYI, Nick/Goodfire used the models extensively in their work, so it's very possible that there were some similarities in their work. I'm really curious to see his response to this.
It's very impressive, but also very expected.
Whoa. What the absolute fuck is going on here.