This is funny, because it confirms that LLM-powered chatbots are easily jailbroken (guardrails are a sham) and it makes Anthropic admit that despite their scaremongering hype marketing, Mythos is not some super hacker. It can spot simple, known exploits like any other model.
Maarten Paulusse
Gotta say I was not expecting my World Cup watching to be interrupted by writing a story like this... arstechnica.com/ai/2026/06/a...
Admin. worries that a Fable 5 "jailbreak" could create national security issues.
