given how often these llms are wrong, doesnt it make sense that they are less co... | Hacker News

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

		supjeff 61 days ago \| parent \| context \| favorite \| on: Gemini 3 Pro Model Card [pdf] given how often these llms are wrong, doesnt it make sense that they are less confident?

postalcoder 61 days ago [–]

Indeed. But I've had experiences with gemini-2.5-pro-exp where its thoughts could be described as "rejected from the prom" vibes. It's not like I abused it either, it was running into loops because it was unable to properly patch a file.

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