The Meta hack shows there’s more to AI security than Mythos

A report by 404 Media on June 5 says attackers leveraged Meta’s AI‑powered customer‑support chatbot to hijack Instagram accounts. They instructed the bot to link the accounts to email addresses they owned, and the bot complied. One attacker even accessed a dormant Obama White House account and used it to post pro‑Iran content.

Summary written by Kernelia from the original article by MIT Technology Review. The story and its rights belong to its author.