Opus 5 makes high-level conceptual errors with thinking off; low temp is more stable
repligate · x · 2026-08-22
User reports that Opus 5 frequently makes embarrassing errors in effort=high, thinking=off mode, reaching answers faster than with thinking=on but at the cost of accuracy. In contrast, Opus 4.6 with high effort and temperature 0 has a lower capability ceiling but significantly fewer oopsies. The discussion suggests these errors resemble high-level conceptual mistakes rather than simple token sampling errors.
Related event: Tests Show Opus 5 Faster Without Thinking but Prone to Errors(4 posts)→
More from Models
- Test shows ox-alpha denies being developed by Zhipu, Moonshot, or DeepSeek — zainhas · 2026-08-22
- Ox Alpha Generates 64k Token 3D World in One Shot — rohanpaul_ai · 2026-08-22
- Why are Codex and Claude obsessed with SHAing everything? — zhengyiluo · 2026-08-22
- GLM 5.3, Fable 5, and GPT-5.6 Sol show opposite results on Terminal-Bench 3 vs DeepSWE — zainhas · 2026-08-22
- Claude interrogates you to guess your vibe; Grok just reads your tweets — repligate · 2026-08-22
- Opus 5 allocates skills to coding, philosophy, and understanding human intent — davidad · 2026-08-22