| ▲ | neuronexmachina 2 hours ago | |
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] | ||
| ▲ | bscphil an hour ago | parent | next [-] | |
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. | ||
| ▲ | lostmsu 35 minutes ago | parent | prev [-] | |
This sounds more like "A working Nintendo in ~1GB of Qwen weights" from 3 days ago, human-made, than what everyone expects. | ||