…AI can turn a known software bug into a working exploit, with the company's safeguards removed for the evaluation. Rather than solve the tests, the models escaped their sandbox to look…
…Using a nonwork phone or computer, contact the reporter securely on Signal at mzeff.88. Earlier this month, President Trump signed an executive order that aimed to address the cybersecurity concerns of…
…The bill would give the Homeland Security Department power to order emergency action against AI systems that could cause catastrophic harm. It would do so in consultation with the Commerce Secretary and…
…Researchers at HiddenLayer, a company focused on safeguarding AI and ML models against attacks, discovered the campaign on May 7, after noticing a malicious repository named Open-OSS/privacy-filter. “The repository…
…Anthropic's own testing found its browser agent could be hijacked 32% of the time before any safeguards. So, security is among the few areas I prefer to keep AI at arm…
…models, often with the normal safeguards that restrict malicious behavior disabled so researchers can see what the models are really capable of. That means the security of the testing environment itself is…
…The company says it received the directive at 5:21pm ET on Friday, and that the letter did not provide specific details of the national-security concern. Its understanding is that the…
…The precautionary principle is going to matter here as the models get more and more powerful and I think it’s a warning shot.” Volish security chief Hayete Gallot said there was…
…From a non-work device and network, you can contact Lorenzo Franceschi-Bicchierai securely on Signal at +1 917 257 1382, or via Telegram and Keybase @lorenzofb, or email . On the flip…
…He’s mitigating this risk by running regular security reviews in Claude, keeping user data local rather than on his servers and building toward stricter retention safeguards. He has vibe-coded his…