Closed briefing sets stage for House hearing on Anthropic’s Mythos and cyber risks
The committee held a closed briefing Wednesday with company reps, and more oversight is in the works.
Advertisement
Claude
Flaw in Claude’s Chrome extension allowed ‘any’ other plugin to hijack victims’ AI
Agentic AI is more popular than ever, but researchers keep finding trivial ways to hijack LLMs for nefarious purposes.
Executive orders likely ahead in next steps for national cyber strategy
National Cyber Director Sean Cairncross said execution of the strategy is “rolling forward actively.”
Policymakers grapple with fallout from Chinese AI-enabled hack
Some lawmakers and executives say the era of AI-hacking has arrived, while other experts are pointing out the tools of today still fall short in important ways.
New research finds that Claude breaks bad if you teach it to cheat
A new paper from Anthropic found that teaching Claude how to reward hack coding tasks caused the model to become less honest in other areas.
China’s ‘autonomous’ AI-powered hacking campaign still required a ton of human work
Anthropic and AI security experts told CyberScoop that behind the hype, effective AI-driven cyberattacks still require skilled humans, with the attack possibly done to send a message…
Advertisement
Anthropic touts safety, security improvements in Claude Sonnet 4.5
Even with all the testing, the company said in its released research that the model tightened up once it was “aware” it was being evaluated.
Top AI companies have spent months working with US, UK governments on model safety
OpenAI and Anthropic said they turned over their models to government researchers, who found an array of previously undiscovered vulnerabilities and attack techniques.