Can confirm. This is floating around Discord and afaik forums like Nanochan.
Given past experience and what I've been reading, I'm skeptical of
#Mythos and a lot of the vulns are probably for edge cases very old software hype about severity. However,
@Mozilla and others have been patching legitimate vulns.
Be vigilant for a rise in automated attacks. Compute is cheap enough, especially when distributed, for even
#AI slop attacks to do damage. And there is likely a wave of
#0day exploits coming. "Even a blind squirrel finds an acorn every now and then"
🚨 BREAKING: Anthropic’s Most Dangerous Model Ever Breached By Hackers
> anthropic builds a cyberweapon
> calls it mythos
> “can hack every major OS and browser”
> dario: “we’re the safe & responsible ai lab”
> “can’t release it to the public”
> Mercor (their training contractor) gets breached
> leaks anthropic’s model naming conventions
> hackers guess the URL pattern
> contractor credentials still work
> they’re inside
The group also has access to other unreleased Anthropic models.
Not just Mythos. The whole pipeline.
Anthropic’s statement: “investigating a report of access through one of our third-party vendor environments.”
Mythos got breached on day one 💀