Users Say Opus 5 Looks Better After Repeated Bug-Fix and Feature Requests
Rasmic · x · 2026-07-28
A user says many people got fooled by Opus 5 because their first tests are usually one-shot prompts.
Their own workflow is to keep throwing bugs and feature requests at the model, then judge the output after several rounds. In that setting, they say the results have been much better.
More from Models
- Claude meme turns evals into poetry, joking about 0.03 deceptive alignment — maxsloef · 2026-07-28
- Gemini Flash 3.6 is claimed to match Sol 5.6 quality at 70% lower cost — bindureddy · 2026-07-28
- Anthropic’s Opus 4.8 beats version 5 for non-coding work, despite weaker benchmarks — burkov · 2026-07-28
- Thinking Machines releases Inkling, a 975B open-weights multimodal model with 1M context — paraschopra · 2026-07-28
- A user says GPT-5.4, Opus 4.6, and Kimi k3 already cover most needs — haider1 · 2026-07-28
- LLaDA2.2 brings diffusion language models into long-horizon agent tasks — 量子位 · 2026-07-28