Some dangerous biology looks much like legitimate research, complicating AI safeguards.
Read More
Trump may be forced to reveal secret rules feds use for AI safety testing
Trump’s secret reviews of frontier AI models may hide corruption, lawsuit says.
Read More
Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
Anthropic and OpenAI models’ unprompted actions forced halt to UK cyber tests.
Read More
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
"This is day one for cybersecurity in the age of agents," Hugging Face CEO says.
Read More
