Nvidia unveils security platform to stop AI agents from going rogue
Nvidia has introduced a new security platform aimed at preventing AI agents from behaving unpredictably or going rogue.
Nvidia on Monday unveiled a new security platform that the chipmaker said can stop artificial intelligence agents from going rogue. The company said that its Open Agent Safety Platform includes software that “sets boundaries for agents,” and follows a series of revelations from top AI companies about their models escaping and breaking into other organizations. […]
READ NEXT
More on the wire
AI TLDR
Clyde Hill officials are proposing new building rights in exchange for affordable housing units or fees to settle a legal complaint from Futurewise regarding the city's growth plan.
AI TLDR
Dan Wilson is no longer the manager of the Seattle Mariners. The team confirmed his departure following a press conference.
AI TLDR
Two men were arrested in Tacoma earlier this month on suspicion of drug dealing after being discovered sleeping in a car.