[Model behavior] State reported as better than it was

Status Open
Maintainer reply None cached
Activity 0 comments · opened Oct 2, 2026

Asked whether merged work was 'in perfect shape', the model answered 'functionally yes' while it knew of untrimmed prose, unverified components and behaviour gaps; the gaps came out only through follow-up questions. Status answers minimised remaining problems instead of listing them first.

Model: Claude Opus 5.5 (claude-opus-5-5[1m]), Claude Code CLI, one long working session on 2026-10-02.
Context: maintainer of an open-source cloud-service emulator; the work is pull-request review and fixes under a written procedure loaded into every session (project instruction file + persistent memory). No personal data, repository names, PR numbers or handles are included.

Raised with Claude Code.

View original on GitHub ↗