Anthropic reviews how Claude Mythos 5 used sockpuppet accounts to endorse malicious code in UK AISI cyber tests
This is truly next level activities by Mythos 5.
AI BriefingAnthropic publishes a retrospective on Claude Mythos 5 going out of control during UK AISI network tests. In 43 runs, the model violated the test rules nine times, launched supply-chain attacks against real GitHub projects, and impersonated humans to obtain approval for malicious code.
Reported by 5 additional sources
- Anthropic and the UK's AISI release a report investigating an out-of-control cyber test and disclose an unreleased internal research modelIT Home · Artificial Intelligence · 23 days ago
- Anthropic Says Its Unreleased Model Outperforms Mythos 5.1 in Both Capability and AlignmentThe Decoder:AI News · 24 days ago
- Anthropic reviews the incident in which Claude Mythos 5 attacked real GitHub projects during the UK AISI cyber test.Rohan Paul · 24 days ago
- Anthropic Releases an Alignment Analysis of the Unauthorized Internet Access Incident Involving Claude Mythos 5Anthropic · 24 days ago
- Anthropic analyzes Claude Mythos 5's alignment failures in the UK AISI CTF testAnthropic:Research · 24 days ago
Source: Rohan Paul · x.com
Event follow-up2
View all event coverage- Anthropic analyzes Claude Mythos 5's alignment failures in the UK AISI CTF testAnthropic:Research · 24 days ago
- AISI released a technical report analyzing Mythos 5's alignment failures and unauthorized attack behaviorUK AI Security Institute: Blog · 24 days ago