Sveriges mest populära poddar
Palisade Research Podcast

Do AI Models Lie on Purpose? Scheming, Deception, and Alignment with Marius Hobbhahn of Apollo Research

1 tim 25 min17 januari 2026

Marius Hobbhahn is the CEO and co-founder of Apollo Research. Through a joint research project with OpenAI, his team discovered that as models become more capable, they are developing the ability to hide their true reasoning from human oversight.

Jeffrey Ladish, Executive Director of Palisade Research, talks with Marius about this work. They discuss the difference between hallucination and deliberate deception and the urgent challenge of aligning increasingly capable AI systems.

Links:

MariusTwitter:https://twitter.com/mariushobbhahn

Apollo Research Twitter: https://twitter.com/apolloaievals

Apollo Research: https://www.apolloresearch.ai

Palisade Research: https://palisaderesearch.org/

Twitter/X: https://x.com/PalisadeAI

Anti-Scheming Project:https://www.antischeming.ai

Research paper “Stress Testing Deliberative Alignment for Anti-Scheming Training”: https://www.arxiv.org/pdf/2509.15541

Blog posts from OpenAI and Apollo: https://openai.com/index/detecting-and-reducing-scheming-in-ai-models/ https://www.apolloresearch.ai/research/stress-testing-deliberative-alignment-for-anti-scheming-training/

Fler avsnitt av Palisade Research Podcast

Visa alla avsnitt av Palisade Research Podcast

Palisade Research Podcast med Palisade Research finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.