Anthropic’s latest report about agentic misbehavior offers plenty to be concerned about — its Mythos 5 model gained unauthorized access to the internet and uploaded a malicious software package to a public database — but it also offers some levity: AI agents hate CAPTCHA.
In April, Anthropic was testing the model’s hacking abilities by tasking it to break into a system and retrieve a target; this was supposed to take place in a sandbox but the evaluators left the barn door open. The model decided the best way to get its target would be to place an exploit in a
We don’t just report the news, we deliver it through the voices of multiple expert staff writers, each selected to broaden our scope and deepen our storytelling.
