Hacker News new | ask | show | jobs
by alastairr 119 days ago
Not sure I agree with you. For lower ability models, yes. Claude Opus 4.6 is incredibly capable, so it's odd to me it has this residual 'misspeak' behaviour.
1 comments

That's the issue, people are anthropomorphizing those models, but... they're all the same (conceptually). They just do random hallucinations, trying to make those hallucination match the "reality" (of their training data) as much as possible