Anthropic’s Opus 5 now self-checks by default, making old “double-check” prompts redundant
AlexKim · x · 2026-07-28
Anthropic’s Opus 5 reportedly verifies its own work without being prompted, which changes a long-standing prompting pattern:
- Telling the model to “double-check your answer before responding” may now make it do the job twice.
- The migration guide’s advice is to delete that instruction, not rewrite it.
The key point is that a prompt that used to improve reliability can now add redundant work because the model already performs self-checking.
More from Models
- Unverified: GPT-6.1 Terra reportedly released, leaked chart shows top score per dollar on Agents' Last Exam — ZeroStateReflex · 2026-10-27
- GPT-6.1 Terra cuts factual error rate from 22.3% to 4.3%, an ~81% drop — haider1 · 2026-10-27
- GPT-6.1 Terra lands: early users praise speed, value and subagent performance — BenBajarin · 2026-10-27
- Leaked GPT-6.1 Terra benchmarks: cheap but 'boring', still far behind Astra and Claude — Angaisb_ · 2026-10-27
- Artificial Analysis Ships Intelligence Index v4.3.2 With GPT-6.1 Terra Comparison — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra cuts hallucination rate by 50 points while lifting accuracy 2 points — ArtificialAnlys · 2026-10-27