Claude Fable 5.2 fallbacks make AI agents more vulnerable
Anthropic released Claude Fable 5.2 on November 9. Its system card shows a weak spot for anyone running Claude as an agent in Cowork, Claude Code or the browser. When a safety classifier hands a request to the older Opus 4.8, prompt injection attacks succeed…
Adjust this page to suit you. Your choices are saved in this browser.
Cookies. Chipokia uses one cookie, and only if you allow it: a random ID so your up and down votes stay yours. No analytics, no advertising, no tracking of any kind. Privacy & Cookie Policy.
