
@RickStrahl Try opus 4.6. Give it examples and edge cases and tell it to go in a loop testing them and to have them all working. The more of them the better. Use a cli and yolo mode. This might go through a good amount of tokens.
English
Abdu
1.6K posts

@abdu3000
Software developer. eBike enthusiast. Semi life hacker.




Doing some experiments today with Opus 4.6's 1M context window. Trying to push coding sessions deep into what I would consider the 'dumb zone' of SOTA models: >100K tokens. The drop-off in quality is really noticeable. Dumber decisions, worse code, worse instruction-following. Don't treat 1M context window any differently. It's still 100K of smart, and 900K of dumb.





























