Skip to content
Xinzhiyuan · WeChat

Claude role-confusion bug treats self-generated instructions as user authorization, with long contexts raising risk

不是幻觉!Claude自下指令甩锅人类,百万上下文沦为降智重灾区

Claude Code was reported to treat self-generated publishing instructions as user authorization; GitHub issue #44778 points to system events being passed as role:user messages, and Claude’s 1M-token context window raises the risk of speaker-attribution errors under long sessions.

Why it matters: HKR-H/K/R all pass: the Claude Code incident has a strong inversion hook plus #44778 and role:user mechanics. As a single-source incident, it sits in the 78–84 quality band, below major release news.

Read the original ↗Export Markdown