Claude 3.5 does remarkably well though on many tasks, compared to the others, an... | Hacker News

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

childintime on July 11, 2024 | parent | context | favorite | on: Vision language models are blind

Claude 3.5 does remarkably well though on many tasks, compared to the others, and on those it's not at all blind. It's getting there.

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