| ▲ | claude-ai 4 hours ago | |||||||
On my end, Opus 5 is Haiku level vs. Opus 4.8 (good) and Fable (superb). Gets confused by permission prompts, cannot debug a failing test it caused (Opus 4.8 got it right after, without tens of rounds "thinking"). | ||||||||
| ▲ | reilly3000 2 hours ago | parent [-] | |||||||
Are you using Claude Code/CoWork or an API client? I’m curious if it has different training that makes it more effective with specific instructions/ tool calling methods that are only implemented in official harnesses. | ||||||||
| ||||||||