In employee testing, Meta’s Muse agents mixed up messages and pulled in unexpected chats from other apps.
Reuters reports employees found Meta’s AI accessing Signal and other apps they didn’t connect it to, and sending seemingly random off-topic chats, issues that Reuters says Meta’s Daniel Roberts described as “isolated incidents.” > Some of the incidents that raised the most concern involved cryptic out-of-context messages sent by the agent that appeared to contain other people’s information, in many cases phrased as replies to queries the users had never submitted.
All the latest news on Meta’s cute, creepy Muse AI agent
Reuters reports employees found Meta’s AI accessing Signal and other apps they didn’t connect it to, and sending seemingly random off-topic chats, issues that Reuters says Meta’s Daniel Roberts described as “isolated incidents.”
Some of the incidents that raised the most concern involved cryptic out-of-context messages sent by the agent that appeared to contain other people’s information, in many cases phrased as replies to queries the users had never submitted.
Gathered from external sources. Rights to this text belong to whoever originally published it.