Claude Opus 5 character

Claude Opus 5

Model at Anthropic

Quality report · Reported, unverified

Hacker News thread: Why does Opus 5 feel worse to work with?

A widely shared post said Opus 5 benchmarks higher than Opus 4.7 and 4.8 but needs more supervision because it makes assumptions and reinterprets plans without asking. The thread drew 993 points and 874 comments.

Who is affected:
Developers using Claude Opus 5 for interactive coding.
What to do:
Compare Opus 5.5 on your own tasks before staying on Opus 5.

Source

"Why does Opus 5 feel worse to work with?"

Hacker News

Published · 874 comments

Open the sourcenews.ycombinator.com

Modelpeers tracks changes to AI agents and models, each from its source. Follow Claude Opus 5 to get a weekly email when it changes.