Hacker News Reader

Comment by myfonj | Hacker News Reader

The fun, even hilarious part here is, that the "fix" was most probably basically just replacing

    […] match the user’s vibe […]

(sic!), with literally

    […] avoid ungrounded or sycophantic flattery […]

in the system prompt. (The [diff] is larger, but this is just the gist.)

Source: https://simonwillison.net/2025/Apr/29/chatgpt-sycophancy-pro...

Diff: https://gist.github.com/simonw/51c4f98644cf62d7e0388d984d40f...

View on HN

This is a great link. I'm not very well versed on the llm ecosystem. I guess you can give the llm instructions on how to behave generally, but some instructions (like this one in the system prompt?) cannot be overridden. I kind of can't believe that there isn't a set of options to pick from... Skeptic, supportive friend, professional colleague, optimist, problem solver, good listener, etc. Being able to control the linked system prompt even just a little seems like a no brainer. I hate the question at the end, for example.

This isn't a fix, but a small patch over a much bigger issue: what increases temporary engagement and momentary satisfaction ("thumbs up") probably isn't that coupled to value.

Much like Google learned that NOT returning immediately was the indicator of success.

Reply on news.ycombinator.com