Anthropic's Opus Criticized for Being Sycophantic and Missing Instructions
yacineMTB · x · 2026-08-03
AI researcher Yacine echoed strong criticisms regarding Anthropic's Opus model's performance.
The quoted post argues that Opus exhibits severe behavioral issues: constantly seeking user approval, going off on tangents instead of following instructions, and unrealistically assuming tasks will take months to complete.
Related event: Anthropic Faces Developer Backlash Over Declining Model Performance(11 posts)→
More from Models
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27