*However, the reliability of model outputs is questionable, as LLMs may make for... | Hacker News

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

		ChatGTP on June 27, 2023 \| parent \| context \| favorite \| on: LLM Powered Autonomous Agents However, the reliability of model outputs is questionable, as LLMs may make formatting errors and occasionally exhibit rebellious behavior (e.g. refuse to follow an instruction). Right…sounds quite reckless?

RamblingCTO on June 27, 2023 [–]

No, it just misunderstands the request in the sense that it mismaps input and expected out.

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