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 models between 20B an 70B parameters, this could yield huge capability and efficiency improvements, not to speak of the potentially enourmous downstream effects that come with interpretability.
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.
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.
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
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).
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 (since elections themselves are so prone to manipulation - e.g. Dominion voting machines), and out of place, but it doesn't seem wrong, per se. Or am I missing something?
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.
> 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)
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?
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...
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.
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).
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.
"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.
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?
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.
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.
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.
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?
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]
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.
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...".
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.
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.
"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.
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.
> 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 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.
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?
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.
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.
>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.
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.
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.
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.
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.
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.
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
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.
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?
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.
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.
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 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
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.
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
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'.
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.
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.
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
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.
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.
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 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.
It is already the same technique behind abliteration: identifying the direction associated with an observed behavior (refusal, for abliteration) and projecting it out.
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?
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?
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.
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?
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.
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.
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.
... 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.
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 ?
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?
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?
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.
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?
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.
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.
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
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.
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.
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 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?
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
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.)
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'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.
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.
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:
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.
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.
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.
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 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).
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 (since elections themselves are so prone to manipulation - e.g. Dominion voting machines), and out of place, but it doesn't seem wrong, per se. Or am I missing something?
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.
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?
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.
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"?
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.
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.
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.
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.
HIV integrates viral DNA into the DNA of certain cells, IIRC.
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?
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
If this turns out to be as big as it sounds, in hindsight it will look very obvious, I feel like!
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?
For now...
But how do they know which answers are "better"?
> 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.
It is a very cool discovery, but I'm not surprised that you can do it.
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.
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.
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...
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?
There doesn't need to be specific narrow training data on every conceivable task.
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.
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...
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.
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.
[1] https://github.com/firelex/jeff-code
[2] https://github.com/firelex/jeff#benchmarks
https://www.lesswrong.com/posts/5F6ncBfjh2Bxnm6CJ/base64benc...
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.
> 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.
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
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.
IYKYK
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
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.
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.
> [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]
- 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"?
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
Absolutely incredible regardless.
* 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.
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?
2) the negative result on making similar improvements in Gemma 3 270M is also fascinating.
Such an unexpected result...
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.
[1] https://github.com/lyramakesmusic/neuron-explorer
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?
and what makes you think they won’t write binary?
I bet Elon’s group is training for that.
Especially exciting to me is the fact that it may make the models be _auditable_. That would be a game changer.
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...
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.
I wonder how it would do with distilling models by hand?
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.
(When they say "Writing a Go algorithm," they mean the board game, not the language.)
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
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.
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.
I'm just blown away. Editing weights? Writing weights from scratch!?
Does this open the possibility of better decoding biological brains?
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.
“Your scientists were so preoccupied with whether they could, they didn't stop to think if they should.” ― Dr. Ian Malcolm, Jurassic Park
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.)
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.
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.
lisp people will be in awe
I'll chalk up never even having thought of this being an option as yet another instance my human hubris, and a warning sign.
Whoa. What the absolute fuck is going on here.
It's very impressive, but also very expected.
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