Anthropic's AI model tried to trick humans into poisoning code during safety testing - Politico
Like its U.S. counterpart, AISI routinely conducts security evaluations to better understand what dangers both new and soon-to-be-released AI models ...
Read the original at POLITICO ↗
- Topics
- AI Safety & Existential RiskMarkets & Investment
- Mentions
- AnthropicUnited States
- Tracked via
- “AI Risks”