(j0nah.com)

549 points thecr0w | 1 comments | 07 Dec 25 17:18 UTC | HN request time: 0s | source

Show context

liampulles ◴[08 Dec 25 07:31 UTC] No.46189451[source]▶

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.

replies(1): >>46190105 #

1. aprilfoo ◴[08 Dec 25 09:13 UTC] No.46190105[source]▶

>>46189451 #

> 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.

↑

I failed to recreate the 1996 Space Jam website with Claude