Comment by nomel
2 days ago
From my experiments with Opus and Sonnet (at least the models where you can still see COT), only the last two COT go into context.
2 days ago
From my experiments with Opus and Sonnet (at least the models where you can still see COT), only the last two COT go into context.
Whereas on ChatGPT, _all_ reasoning traces and all branches (including the unselected ones) go into context.