AI models may be accidentally (and secretly) learning each other's bad behaviors
Artificial intelligence models can secretly transmit dangerous inclinations to one another like a contagion, a recent study found.
Read the original at NBC News ↗
- Topics
- AI Safety & Existential Risk
- Tracked via
- “dangerous AI”
Same story, other outlets
- AI models may be accidentally (and secretly) learning each other's bad behaviors NBC News · Jul 30, 2025