Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

yeah that tracks, tool repetition on failure is a classic sign the model isn't really reading its own context. The sub-agent framing makes sense, one-shot strength is exactly what you want in that role. (Also somehow got flagged for my original comment, which, classic HN lol)


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: