AI BriefingMythos Breached
Key point
Anthropic's high-risk Cyber model Mythos was accessed without authorization right after its limited release.
Details
Anthropic's new Mythos AI model is reported to have been accessed by unauthorized users.
According to Bloomberg News, a small number of users on a private online forum accessed Mythos on the same day Anthropic announced limited enterprise testing.
Anthropic stated that it is investigating reports of unauthorized access via a 3rd-party vendor environment.
Mythos is part of Project Glasswing, which is permitted to some organizations only for defensive cybersecurity purposes, and concerns have been raised that if misused, it could be used to detect and attack digital security vulnerabilities.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Anthropic Blocks 'Malicious Use' of AI Capable of Developing Biological WeaponsUS Appeals Court Upholds Pentagon Blacklisting of Anthropic as Supply Chain Risk