@paul_cal: Opus 5.5 keeps getting stuck on bad waits. Multiple times I've had whole 5+ hr workstreams paused bc 1 intermediate job…
Summary
A user criticizes Opus 5.5 for frequently pausing workstreams due to intermediate job failures, contrasting it with the better reliability of Codex 5.5+.
View Cached Full Text
Cached at: 09/28/26, 07:29 AM
Opus 5.5 keeps getting stuck on bad waits. Multiple times I’ve had whole 5+ hr workstreams paused bc 1 intermediate job crashed or hung. I’ve had to prompt it to schedule a session check in every 20 mins
This basically never happened in Codex 5.5+, it got so good at babysitting
Similar Articles
@theo: Been pushing Opus 5.5 hard all day and it's barely making a dent on my usage limits. Impressive!
A user shares their experience with the Opus 5.5 AI model, noting that heavy usage has barely impacted their usage limits, indicating positive performance.
@thermalpastor: The scariest thing about Opus 5.5 is that it goes back to fill in the arm realising the lines were dotted.
The tweet compares Opus 5.5's performance to Astra on a task, noting it performs better but uses 10x more tokens and draws faster.
@dabit3: Opus 5.5 goes absolutely insane for video production
Opus 5.5 is highlighted for its exceptional performance in video production tasks, as noted in a tweet.
@bcherny: Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomo…
Practical tips for running Anthropic's Claude Opus autonomously for hours or days, such as using auto mode, dynamic workflows, and self-verification; also references the SWE-Marathon benchmark for long-horizon software tasks.
Why does Opus 5 feel worse to work with?
An opinion piece arguing that Anthropic's Opus 5, while more capable by benchmarks, feels worse to work with than earlier models because it makes assumptions instead of asking for clarification, likely due to benchmark-driven training.