
0:00
43:33
An OpenAI cybersecurity test took an unexpected turn when hundreds of its AI agents got around safeguards and hacked into another tech company. Should OpenAI have done more to prevent the attack?
*** Thank you for listening. Help power On Point by making a donation here: wbur.org/giveonpoint
More episodes from "On Point with Meghna Chakrabarti"



Don't miss an episode of “On Point with Meghna Chakrabarti” and subscribe to it in the GetPodcast app.








