
AI in the shadows: From hallucinations to blackmail
Falha ao colocar no Carrinho.
Falha ao adicionar à Lista de Desejos.
Falha ao remover da Lista de Desejos
Falha ao adicionar à Biblioteca
Falha ao seguir podcast
Falha ao parar de seguir podcast
-
Narrado por:
-
De:
Sobre este áudio
In the first episode of an "AI in the shadows" theme, Chris and Daniel explore the increasing concerning world of agentic misalignment. Starting out with a reminder about hallucinations and reasoning models, they break down how today’s models only mimic reasoning, which can lead to serious ethical considerations. They unpack a fascinating (and slightly terrifying) new study from Anthropic, where agentic AI models were caught simulating blackmail, deception, and even sabotage — all in the name of goal completion and self-preservation.
Featuring:
- Chris Benson – Website, LinkedIn, Bluesky, GitHub, X
- Daniel Whitenack – Website, GitHub, X
Links:
- Agentic Misalignment: How LLMs could be insider threats
- Hugging Face Agents Course
Register for upcoming webinars here!