Anthropic locked their most dangerous AI in a vault. Four guys in a Discord opened it.
Anthropic's Mythos AI was 'too dangerous to release.' A Discord group accessed it on day one via URL guessing. What this means for AI vendor ...
Read the original at AI Optimisation Checker - Webcoda ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- Anthropic
- Tracked via
- “dangerous AI”