Once the LLM has made one mistake, it's often best to start a new context. Since... | Hacker News

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

		Dilettante_ 1 day ago \| parent \| context \| favorite \| on: The new calculus of AI-based coding Once the LLM has made one mistake, it's often best to start a new context. Since its mechanism is to predict the next token of the conversation, it's reasonable to "predict" itself making more mistakes once it has made one.

manmal 1 day ago [–]

I‘m not sure this is still the case with codex. In this instance, restarting had no strong effect.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact