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.
More from Models
- A meme turns the AI scaling race into a one-line GPU negotiation — altryne · 2026-07-28
- Rumor: Ilya Sutskever Has Made Boltzmann Machines Computationally Tractable — ryangr · 2026-07-28
- GPT-5.6 Sol Excels at Computer Use: Navigates Complex and Broken Web Pages — Angaisb_ · 2026-07-28
- Users say GPT-5.5 keeps correcting their wording instead of answering directly — DesireeCachette · 2026-07-28
- GPT-5.6 flagged serious issues in several random Annals of Statistics papers — ChrSzegedy · 2026-07-28
- Opus 5 Review: Technically Brilliant but Stiff, Tailored for Sub-Agents Not Solo Chat — MicahBerkley · 2026-07-28