Opus 5 Found Useful for CUDA Kernel Writing with Strict Verification
gandamu_ml · x · 2026-08-24
gandamuml added that while Opus 5 causes more harm than good for most tasks, they still risk using it for optimization tasks where exact outputs are verified at each step. The model has successfully written CUDA kernels for them in the past.
Related event: Users Report Anthropic's Opus 5 and Sonnet 5 as a Regression(6 posts)→
More from coding & agent
- AI as a software factory to replace legacy mess and business processes — arieljalali · 2026-08-24
- LLM Agents Invent Tool Arguments: A Sanitization Checklist Before Execution — blaizedsouza · 2026-08-24
- An AI coding agent is an input to an engineering system, not the system itself — ruslansv · 2026-08-24
- Production Guide: Limit Tool Output Size for Agents — blaizedsouza · 2026-08-24
- Six months of evals: never let the model rewrite the source; BM25 weighting lifts recall@10 to 0.86 — Cryvixx · 2026-08-24
- Run AI Tool Parameters in Strict Schema Mode to Catch Prompt Drift — blaizedsouza · 2026-08-24