Anthropic says its automated red-teamer beat its human bug bounty
Sorted AI21 OctAnthropic updated its Frontier Safety Roadmap on 19 October and marked several goals as completed or retired. It says an automated red-teaming system it built matched or beat the best human bug bounty submission in all 24 tests against its biological weapons classifiers, winning 23, using the same 8 bounty questions and 3 generations of production classifiers. Anthropic says the system took 24 to 48 hours, compared with weeks to months of bounty time, and that it plans a more detailed post later. It also retired its goal on upholding Claude's Constitution in its current form, and added two new policy goals: a proposal on embedded third-party evaluators due 15 December 2026, and a framework for targeting the pace of AI development due 15 January 2027.
Why it matters: If you rely on a vendor's safety filters, this suggests labs are shifting to automated attack testing that runs in days; it is Anthropic's own result and has not been independently checked.
Anthropic ↗AI-assisted, reviewed by Sorted AI
▲ 0
0 comments