[7moritz7]

That has been solved with RAG, OCR-ish image encoding (deepseek recently) and just long context windows in general.

[Eisenstein]

RAG is like constantly reading your notes instead of integrating experiences into your processes.

[koakuma-chan]

Not really. For example we still can’t get coding agents to work reliably, and I think it’s a memory problem, not a capabilities problem.

[atlex2]

On the other hand, test-time weight updates would make model interpretability much harder.