AI Researcher Slams Claude Opus 5: Workflow Errors Make it 'Uncomfortable' to Use
heypearlai · x · 2026-07-29
Prominent AI researcher Elvis Saravia (@omarsar0) posted on X, directly calling out significant issues with the Claude Opus 5 model in practical use.
He noted that while he understands the need to adjust workflows and skills for newer models—which generally understand intent much better—Opus 5 is not "plug-and-play." He observed that the model gets a lot of basic things wrong, making him feel "very uncomfortable" using it. Saravia added that based on the reactions to his post, it seems many others are also struggling with Opus 5. He called on Anthropic's Claude team to help users understand what is going on with this model.
Related event: Claude Opus 5 Criticized: Unstable as Coding Agent, Breaks Workflows(5 posts)→
More from Models
- NVIDIA open-weight model ties pplx-decider at #1 on 669-case clinical benchmark — MaziyarPanahi · 2026-10-16
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Thrive Holdings launches real-work AI evals from 75+ businesses, benchmarking 13 models — samaysham · 2026-10-16
- Microsoft's MAI-Transcribe now handles 61% of all transcription on OpenRouter — mustafasuleyman · 2026-10-16
- Reflection AI Releases Open-Weight 501B MoE Beam for Agentic Coding on AWS — AWS ML Blog · 2026-10-16
- Dev RL-tunes Qwen 27B against slop with Meta's XAR method, lands top-4 on EQbench — Mysterious_Hearing14 · 2026-10-16