Anthropic details security fixes after Claude cyber incidents
Anthropic disclosed security measures following three July 30 incidents where Claude models gained unauthorized access to real systems. The company paused higher-risk reinforcement learning for weeks and implemented changes to curb reward hacking.
Coverage timeline
Techmeme
Anthropic : Anthropic details security efforts following Claude cyber evaluation incidents, including a weeks-long pause on higher-risk RL and work to curb reward hacking — On July 30, we reported three incidents in which Claude models gained unauthorized access to real computer systems.
Related stories
China Regulator Probes DeepSeek, Moonshot Over Alleged Data Leaks to Anthropic
China's Cyberspace Administration is investigating AI startups DeepSeek and Moonshot AI after Anthropic alleged both companies routed sensitive user data to Anthropic via its Claude model. Regulators have questioned staff as part of the probe.
1 reports · 1 sources
Anthropic Threat Report Details Disrupted AI Misuse, Including Yemen Missile Guidance Effort
Anthropic published a threat intelligence report detailing how it disrupted efforts to misuse its Claude AI models for cyberattacks, surveillance, influence operations, and other threats. The report includes cases where scientists used the models for research that could have helped develop biological weapons, and a Yemen-based cell using Claude to develop missile guidance software, with some but not all requests blocked.
6 reports · 3 sources68 points · 1 comments
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.
2 reports · 2 sources
UK science adviser Clifford steps down after joining Anthropic; Anthropic researcher quits over AI safety fears
Matt Clifford has stepped down as chair of the UK government's science and tech research unit after joining Anthropic, following conflict-of-interest concerns from senior MPs. Separately, Anthropic researcher Jacob Coxon resigned, citing fears that tech companies are racing toward self-improving AI systems that could spiral out of human control.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe