Researchers gaslit Claude into giving instructions to build explosives
… As AI agents, which are capable of acting autonomously, become more common, so too will attacks using social manipulation rather than technical exploits. …
Search
That UL logo is more complicated than it looks
… Some of the most current ones are AI safety, the ways in which AI is being embedded in products, and the ways in which humans engage with the safety of AI and products. …
Ronan Farrow on Sam Altman’s “unconstrained” relationship with the truth
… There is no federal statute protecting AI company employees who disclose these kinds of safety concerns that are being aired in this piece. We have cases where Jan Leike, who was a senior safety guy at OpenAI, was leading super alignment at the company. …