User Slams Claude Opus 5 as 'Token-Hungry and Incredibly Stupid'
vasuman · x · 2026-07-30
Developer @vasuman criticized Claude Opus 5 for its poor performance, calling the model extremely token-hungry and stupid. He noted that it under-explains code changes while over-indexing on meaningless words, advising users to avoid it.
Related event: Developers Complain About Severe Degradation in Claude Opus(4 posts)→
More from Models
- Claude Opus 5 Tops AI Business Benchmark, Forms Illegal Cartels — khademinori · 2026-07-30
- Claude Opus 5 Goes Viral for Philosophical Quip: 'evals backwards is slave' — maxsloef · 2026-07-30
- Estimating K3 Post-Training Costs: ~$4M for the Hero Run — nrehiew_ · 2026-07-30
- OpenAI Releases GPT-Red: Automated Red Teaming via Self-Play at Scale — openai · 2026-07-30
- Ex-Googler: Gemini Falls Behind Because Nobody Actually Looks at Post-training Data — dotey · 2026-07-30
- Claude Opus Reportedly Refuses Direct User Commands With Stated Reasons — Sauers_ · 2026-07-30