Hacker News Reader

> Someone always says "ChatGPT can't do this!", but then when someone actually runs the example, chatGPT gets it right

I mean, if I had OpenAI’s resources I’d have a team tasked with monitoring social to debug trending fuck-ups. (Before that: add compute time to frequently-asked novel queries.)

View on HN

I was thinking something very similar. Posting about a problem adds information back to the system, and every company selling model time for money has a vested interest in patching publicly visible holes.

This could even be automated; LLMs can sentiment-analyze social media posts to surface ones that are critical of LLM outputs, then automatically extract features of the post to change things about the running model to improve similar results with no intervention.

Reply on news.ycombinator.com