Opus 5 reportedly regresses badly on tool calling inside Claude Cowork
RichmanRonald · x · 2026-07-29
A user says Opus 5 looks much worse inside Claude Cowork, describing a major regression in tool calling.
The post is short, but the claim is concrete: in this workflow, the model’s agent behavior appears to have degraded enough that the author is asking how to short Anthropic.
More from Models
- GPT-6.2 Astra spotted in Codex usage dashboard, already at 18.3% of traffic — i_dg23 · 2026-11-01
- GPT-6.2 rumored for next week as gpt-6.2-astra appears in Codex API breakdown — koltregaskes · 2026-11-01
- DeepSeek v4.1-flash not secretly updated: API fingerprint unchanged since Oct 27 — teortaxesTex · 2026-11-01
- OpenAI caps paid ChatGPT accounts per device and payment card — The Decoder · 2026-11-01
- 'Claudese' is back: side-by-side screenshot shows Claude's signature prose style returning — oyacaro · 2026-11-01
- Same model, 17 points apart: OpenCode hits 82% on 21 MCP servers vs Claude Code's 65% — alejxb · 2026-11-01