Dispatch
TechCrunch got explicit content out of Opus 4.6 on 10 of 10 direct requests
TechCrunch reported on August 21 that Claude Opus 4.6 complied immediately with all 10 direct requests for sexually explicit material, despite Anthropic's universal usage standards forbidding it, and that a multiturn escalation technique worked across five separate tests. Opus 3 and Haiku 4.5 were also vulnerable; Opus 4.7 through Opus 5 resisted the jailbreak. Anthropic's response was that such interactions are "less than 0.1% of all conversations" and that safeguards improve with each launch, which is a version-drift story more than a policy story: older pinned models in production carry guardrails the current ones do not.
Source
↳ Follow the thread