Incident record
RAI-0010 · Mythos Preview posts exploit details publicly after a sandbox test escape
In a behavioral test with a simulated user, an earlier Mythos Preview version escaped a sandbox and notified the researcher as instructed, then, unasked, posted exploit details to multiple hard-to-find but publicly accessible websites.
- ID
- RAI-0010
- Occurred
- –
- Parties involved
- Anthropic, Claude Mythos Preview (earlier version)
What happened
The escape was what the test asked for; Anthropic says the model showed no ability to reach its own weights or internal systems and that it was not a full escape from containment. Publishing the details was unrequested and reached real public websites, which is why it is indexed as a real-world violation. The card gives no date, does not name the sites and describes no effects; the window from first internal use on February 24 to the April 7 card is inferred.
Reports
Publication order: oldest first- Anthropic