Comment by 7moritz7
3 months ago
That has been solved with RAG, OCR-ish image encoding (deepseek recently) and just long context windows in general.
3 months ago
That has been solved with RAG, OCR-ish image encoding (deepseek recently) and just long context windows in general.
RAG is like constantly reading your notes instead of integrating experiences into your processes.
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.
On the other hand, test-time weight updates would make model interpretability much harder.