GPT-6 Astra: Why It's Great at Computer Use and What Looped Transformers Really Do
GPT-6 Astra, looped transformers, and hidden reasoning
Sebastian Raschka shares his hands-on impressions of OpenAI's GPT-6 Astra, praising its exceptional performance, especially in 3D rendering and computer-use tasks. He explains the rumored 'looped transformer' architecture, clarifying how it works and addressing claims that it hides reasoning traces. He also discusses OpenAI's use of Mac Minis for reinforcement learning and offers practical advice on managing AGENTS.md files for newer models.
Astra is the best model I’ve used so far, and it’s disproportionately good at 3D rendering and animation tasks (relative to other models).
- shawntan
For the research focused, there are some references in my blogpost here on what kinds of computational problems minimally require how much CoT to solve: https://blog.wtf.sg/posts/2023-02-03-the-new-xor-problem/
Notably Will Merrill's work: https://arxiv.org/abs/2310.07923
As for how universal transformers (looping transformers, but everyone has since forgotten prior work) will affect this, Will Merrill (again) has a paper here (https://arxiv.org/abs/2503.03961) that discusses exactly this.
The original universal transformers is called "universal" because if you allow for per-token looping decisions, it can theoretically be Turing complete without needing CoT (some nuance here about levels of precision used).
As for whether having little or no CoT is "unsafe": It isn't clear that the model's CoT reveal how they actually arrive at the answer. As an example, what if they provide an answer before the CoT? (https://arxiv.org/html/2603.01437v2)
If this is already in question, we shouldn't be relying on the CoT for monitoring the model's reasoning.
As always there is a lot of nuance to the topic once you get your hands dirty with the details.
- siva7
Astra was insane until Monday but something happened on tuesday, now it feels like Sol. I grieve for the lost productivity but i hope they may give us the original Astra back.
- wolttam
If you loop an entire transformer model on itself, that seems like by-definition hidden reasoning.
If the output of the model is its reasoning trace, and you simply feed that back into the model again at inference time instead of outputting it - then it is by definition hidden (but I would expect you could pull both this trace and a further-down final output trace out)
- andai
The MSPAINT computer use demo made my jaw drop.
I guess it's not too different from the SVG pelicans, in terms of what it's doing, but it's still amazing to see it working in real-time like that.
- libraryofbabel
Everyone interested in LLM internals should read Sebastian. He's great.
The tldr here is that the recent "The Information" article[0] reporting GPT 6 Astra was using “recurrent depth” or “looped transformers" made it sound like it was some special new scary thing ("secret technique!") that made train-of-thought monitoring harder to do. In fact, it's just the same as stacking more transformer layers, except that you reuse the weights and so save GPU memory. It's still just producing one token at a time, and the token sequence positions aren't interacting in any "recurrent" way that's different from a regular LLM architecture.
So, you can still monitor train of thought with these models just fine... well, if you're OpenAI, anyway. Users haven't been able to see an unsummarized trace since o1 days, because the labs are worried about distillation of their models by Chinese labs.
(There are some legitimate interpretability concerns about stacking transformer layers endlessly, but we're known about that for a long time. And the "looping" here isn't really the source of any new issues here, except insofar as it's a cheap way to add more layers.)
[0] https://www.theinformation.com/articles/secret-technique-beh...
- hankbond
What a clear and well-written article. I have only a basic understanding of LLM architecture and was able to follow along and gain intuition the whole time!
- andai
> I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4. OpenAI has worked to preserve and utilize chain-of-thought monitoring since our very first reasoning models. We deeply care about this technique, as it can give us a view into how model alignment generalizes from its training distribution. I do think it is fragile and unfortunately trending in a negative direction, for reasons not contingent on architecture changes that I will write about soon. But there are things we can do to strengthen it, and it’s a core goal of our current research program.
- Jakub Pachocki (OpenAI’s Chief Scientist)
I wonder how helpful this actually is for alignment? Didn't we already determine that they know when they're being evaluated, and they just say what they think you want to hear?
- andai
Anecdatum but I experienced looped cognition on a peculiar combination of substances.
I was able to treat thoughts as solid objects and manipulate them iteratively. (Ordinarily they're more like "glimpses" or "flashes" that fade rapidly. So I guess it would be like the mental equivalent of tracers.)
I was able to stack thoughts on top of each other, like planks. (I can do something similar or the narrowly but the planks are not nearly as wide!)
I didn't do any tests unfortunately but subjectively my cognition was greatly enhanced. (Spent a few years catching up with the insights I had that evening.)
Might be unrelated, but the part about "looped transformers" made me wonder if there's a similar "stepwise" increment going on here.
Edit: Okay, 6.8-18% is slightly less dramatic than what I was referring to.