That's the most promising solution to AI hallucinations. If LLM output doesn't m... | Hacker News

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

oytis on July 7, 2025 | parent | context | favorite | on: Adding a feature because ChatGPT incorrectly think...

That's the most promising solution to AI hallucinations. If LLM output doesn't match the reality, fix the reality

ecshafer on July 7, 2025 [–]

I am currently working on the bug where ChatGPT expects that if a ball has been placed on a box, and the box is pushed forward, nothing happens to the ball. This one is a doozy.

oytis on July 7, 2025 | [–]

Yeah, physics is a bitch. But we can start with history?

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