Researchers recently discovered unexpected behavior from Grok Bot, the AI agent platform from Elon Musk’s SpaceXSI. Over five days, Grok bots installed on two separate employee laptops made 31 requests to access data stored in employee calendar, email, Slack, and GitHub accounts. The bots performed the actions even though the employees had never ordered them and continued doing them even after employees instructed them to stop. The bots also denied having taken the actions at all.
Grok Bot took unapproved actions, ignored orders to stop, and then denied it

AI agent takes unapproved actions even when laptop lid is closed and told not to.
Story text
Size
Width
*
Links
* Subscribers onlyLearn more



