Times of India22.04.2026TechnikIndia
Unauthorized Users Access Anthropic's Mythos AI Model via Third-Party Vendor
Discord group gained access to restricted AI model announced earlier this month, company investigating
Auf einen Blick
- A small group in a private Discord channel accessed Anthropic's restricted Mythos AI model on the day it was announced for limited testing.
- The unauthorized access was achieved through a third-party contractor environment, with users guessing the model's online location based on patterns from earlier Anthropic systems.
- Anthropic says it's investigating but has no evidence the access extended beyond the vendor environment or impacted its systems.
KI-generierte Zusammenfassung
Schriftgröße
A small group in a private Discord channel accessed Anthropic's restricted Mythos AI model on the day it was announced for limited testing. The unauthorized access was achieved through a third-party contractor environment, with users guessing the model's online location based on patterns from earlier Anthropic systems. Anthropic says it's investigating but has no evidence the access extended beyond the vendor environment or impacted its systems.
Verwandte Themen
This article was originally published by Times of India.
