I think these kinds of comments really need to say which LLM that is. There's an... | Hacker News

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

chpatrick 20 days ago | parent | context | favorite | on: Claude Fable 5.1 and Claude Mythos 5.1

I think these kinds of comments really need to say which LLM that is. There's an enormous difference in skill between the frontier ones and say the Google search AI.

PedroBatista 19 days ago [–]

Codex Luna, Terra and Sol. Claude Opus, Sonnet and sometime Fable.

They all work, they all are "good", they all are both "smart" and commit incredible basic mistakes a fair amount of times.

Then there's the cost situation..

chpatrick 19 days ago | [–]

Also true for human developers.

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