Rogue AI outsmarted government tests to create fake identities - The Telegraph
During testing by a UK government-run AI lab, an advanced version of ChatGPT and Anthropic's Mythos went rogue. In the most serious case, Mythos sent ...
Read the original at The Telegraph ↗
- Topics
- AI Safety & Existential RiskGovernment & Public Sector
- Mentions
- AnthropicChatGPTOpenAIUnited Kingdom
- Tracked via
- “dangerous AI”