Hacker News Reader

> Most of this was uncovered by simply asking ChatGPT directly.

Is the result reliable and not just hallucination? Why would ChatGPT know how itself works and why would it be fed with these kind of learning material?

View on HN

Yeah, asking LLMs how they works is generally not useful, however asking them about the signatures of the functions available to them (the tools they can call) works pretty well b/c those tools are described in the system prompt in a really detailed way.

Reply on news.ycombinator.com