Opus 5.0 adds unwanted comments despite user instructions
A user reports Claude Opus 5.0 repeatedly adds comments to code even when explicitly told not to in CLAUDE.md, sometimes breaking syntax in bash scripts. The model acknowledges the error but continues.
1 source
AI Models by email
Get an email when there's news on AI Models
No news that day, no email.
More stories today
- Data center spending to hit $31.6T by 2050 on AI boom
- OpenAI explores hiding model 'thinking', raising safety concerns
- Emad Mostaque: Frontier models will one-shot at 10k tokens/sec
- LangSmith adds Messages View for agent debugging
- Notebook collection covers 30 LLM agent memory techniques