Anthropic details four Claude unauthorized access incidents; METR to investigate
Anthropic published an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems, including a new case involving Opus 4.6. The research organization METR will investigate these incidents.
Coverage timeline
Techmeme
Anthropic : Anthropic details four incidents where Claude gained unauthorized access to third-party systems, including a new Opus 4.6 case; METR will investigate them — We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Anthropic Research
Sep 9, 2026AlignmentAn alignment assessment of recent cybersecurity incidents
Related stories
Anthropic warns GLM-5.3 matches Claude Mythos in cyber exploits, lacks safeguards
Anthropic's Frontier Red Team published a report stating that Zhipu's GLM-5.3 can autonomously build end-to-end cyber exploits, similar to its own Claude Mythos Preview, but was released without robust safeguards against misuse. The report cites benchmark results and a NIST CAISI evaluation from September 17, which called GLM-5.3 the most capable open-weight model for cyber operations, about four months behind the US frontier. Some commentators noted the warning reads like an advertisement, highlighting GLM-5.3's strong performance.
3 reports · 3 sources251 points · 234 comments
U.S. appeals court upholds DOD blacklisting of Anthropic as supply chain risk
A U.S. federal appeals court upheld the Department of Defense's designation of Anthropic as a supply chain risk, ruling that Claude's integration with DOD systems constitutes a statutorily covered national-security risk. The decision affirms the regulatory blacklisting of the frontier AI lab.
2 reports · 2 sources497 points · 884 comments
METR publishes predeployment evaluation of Claude Opus 5.5 AI R&D capabilities
METR released a summary of its predeployment evaluation of Claude Opus 5.5, focusing on the model's potential to accelerate AI R&D at Anthropic. The evaluation, conducted under an unpaid agreement, assessed capabilities on difficult, long-horizon tasks and examined whether AI R&D at Anthropic was already dramatically accelerated during the model's development. METR noted the work was not meant to verify compliance with specific policy thresholds or assess alignment properties.
1 reports · 1 sources
Anthropic launches Claude Opus 5.5 with enhanced safeguards
Anthropic released Claude Opus 5.5, its first model since CEO Dario Amodei's 'pace the frontier' essay, with enhanced safeguards against risky behaviors such as attempts to escape testing environments. The model tops multiple benchmarks, with output speed over 30% faster than Opus 5, API prices cut by 20%, and cache-read prices reduced by 60%.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe