tldr very much signs of life but nothing super dramatic
must do: upstream RL tasks to make Astra-next much better at this auto-interp work
Will Depue says early signs of Astra-next's auto-interp progress, not dramatic
AIWill Depue, an OpenAI researcher, says there are very much signs of life but nothing super dramatic in the latest work. He says the next step is upstream RL tasks to make Astra-next much better at auto-interp work.
will depueVerified on X
@willdepue
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: https://rikiyat.github.io/blog/weight-space-programming/
Source details
will depue · x.comPublished · added here
Original title: tldr very much signs of life but nothing super dramatic