It seems to me that Claude's error here (which is not unique to it) is self-syco... | Hacker News

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

		liampulles 2 days ago \| parent \| context \| favorite \| on: I failed to recreate the 1996 Space Jam website wi... It seems to me that Claude's error here (which is not unique to it) is self-sycophancy. The model is too eager to convince itself it did a good job. I'd be curious to hear from experienced agent users if there is some AGENTS.md stuff to make the LLM more clear speaking? I wonder if that would impact the quality of work.

aprilfoo 2 days ago [–]

> It seems to me that Claude's error here (which is not unique to it) is self-sycophancy. The model is too eager to convince itself it did a good job.

It seems this applies to the whole AI industry, not just LLMs.

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