After a dozen prompts, one user says Opus 5 still breaks basic project work
tomjohndesign · x · 2026-07-28
The author says they tried Opus 5 on about a dozen prompts in the morning for a project, and also asked Fable to review the work.
Each time, the reviewer kept saying the output would “break something,” so the author says the model’s responses do not inspire confidence for significant work.
Related event: Claude Opus 5 Criticized: Unstable as Coding Agent, Breaks Workflows(5 posts)→
More from Models
- 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
- HotDogBench tests 10 LLMs on 1,000 hot dog photos — all within each other's error bars — josh_wills · 2026-10-16