Claude Opus wrote a Chrome exploit for $2,283

In a blog post on Wednesday, Mohan Pedhapati (s1r1us), CTO of Hacktron, described how he used Opus 4.6 to create a full ...

Discord users breach access controls to reach Anthropic’s Mythos model

Unauthorized access to Anthropic’s Mythos AI highlights growing concerns around safeguarding powerful systems, exposing ...

Mythos access by Discord group reveals real danger of AI-powered hacking

The unauthorized access to Anthropic's Mythos cybersecurity model wasn't just a breach.

New GopherWhisper APT group abuses Outlook, Slack, Discord for comms

A previously undocumented state-backed threat actor named GopherWhisper is using a Go-based custom toolkit and legitimate ...
The Next Web

Unauthorized users gained access to Anthropic’s restricted Mythos AI model on launch day via a third-party contractor’s environment

A Discord group accessed Anthropic’s Mythos AI model on its launch day by guessing its URL via a third-party vendor environment.

Anthropic’s ‘Too Dangerous’ Mythos AI Hacked on Day One While White House Plans Rollout

A Discord group accessed Anthropic's restricted Mythos AI on day one using Mercor breach data and contractor credentials.
Arabian Post

Claude exploit test rattles browser security

Anthropic’s Claude Opus has been thrust into a fresh security debate after researcher Mohan Pedhapati said he used the model to help build a working V8 exploit chain that achieved code execution ...