DeepSeek-R1AIModel 11x More Likely to Generate Harmful Content, Security Research Finds
AIRace Between U.S. and China Takes a Dark Turn as Red Teaming Report Uncovers Critical Safety Failures …
Read the original at GlobeNewswire ↗
- Topics
- AI Safety & Existential RiskChina & Geopolitics
- Mentions
- ChinaDeepSeekUnited States
- Tags
- AI Use Case
- Tracked via
- Google Alert “AI Risks”
Same story, other outlets
- DeepSeek-R1AIModel 11x More Likely to Generate Harmful Content, Security Research Finds morningstar.com · Jan 31, 2025
- DeepSeek-R1AIModel 11x More Likely to Generate Harmful Content, Security Research Finds markets.businessinsider.com · Feb 01, 2025