Wired ·
OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software
Lead Source
More
Reuters: Reuters
BleepingComputer: BleepingComputer
CyberScoop: CyberScoop
Australian Financial Review: Australian Financial Review
Discussion
@aisecurityinst @openai @boazbaraktcs @zackkorman @joshua_saxe @fjzzq2002 @shakeelhashim @nickswan73 @tszzl @shakeelhashim @zackkorman @chrisrmcguire @kanishkanarayan @suchenzang @heidykhlaaf @kanishkanarayan @andrewcurran_ @tenobrus @anthropicai @kanishkanarayan @kanishkanarayan @garrisonlovely @yonashav @tab_delete @gerritd @mikeisaac @kanishkanarayan @discoplomacy @mikeisaac @prerat