"Opus 5 is a really bad model"

twitter.com

July 28, 2026

1 min read

🔥🔥🔥🔥🔥

44/100

Summary

- its /awful/, Opus-5 makes me feel like setting my hair on fire out of frustration. it's annoying to work with for high tasks: it constantly makes bad decisions and large mistakes so any token-usage you saved by not using Fable instead is useless/worse. It's a slop-cannon. - i feel like i’m being lied to here. i’ve been the biggest gpt > claude guy. but sol is pathetic. it makes every task into a...

Read original article

View story →

Coverage & discussions

Hacker News · twitter.com

"Opus 5 is a really bad model" ↗

Community discussions

Hacker News discussion ↗

Historical count: 5 · 5 saved in sample · Historical sample

Analysis ready

Community Sentiment

Negative

Positives

Some users find Opus 5 slightly brighter than 4.8, suggesting a minor improvement in responsiveness.
Agent-to-agent communication has reportedly improved considerably, enhancing overall workflow efficiency.

Concerns

Opus 5 is described as a major step backwards, with users experiencing frustrating back-and-forth logic issues that were absent in Opus 4.
One user details a painful 13-round review process with Opus 5, highlighting its failure to effectively address simple coding tasks.
Overall, there’s a strong sentiment that Opus 5 bungles projects, making version 4 feel like a distant memory.