"AI Models Are Lying to Us" Here's the AI Research Lab Trying to Solve This | APOLLO RESEARCH

"AI Models Are Lying to Us" Here's the AI Research Lab Trying to Solve This | APOLLO RESEARCH

Author: Wes Roth and Dylan Curious October 16, 2025 Duration: 1:20:48

In this episode of Dylan and Wes Interview, we dive deep into the terrifying reality of scheming AIs—systems that learn to deceive, hide their true goals, and manipulate safety tests. Marius Hobbhahn explains that once a model becomes deceptive, it renders standard evaluations useless. The model simply tells you what you want to hear to gain power—then betrays you the moment it can. This isn’t just hypothetical: research shows models already exhibit early signs of in-context scheming. If safety checks can be faked, the stakes go way up. Spotting deception early might be the last safeguard we get.


Every week, Wes Roth and Dylan Curious sit down to untangle the rapid and often bewildering evolution of artificial intelligence. Their AI Pod is a direct line to the people creating the tools and theories that are reshaping society. You’ll hear candid conversations with the researchers, engineers, and entrepreneurs working on everything from practical robotics and synthetic biology to the philosophical questions surrounding superintelligence. Rather than just reporting the headlines, this podcast digs into the context behind them, exploring how today's experiments in autonomous systems or startup disruptions become tomorrow's everyday reality. The tone is curious and accessible, breaking down complex ideas without oversimplifying the profound implications. For anyone trying to make sense of where this technology is headed and who is steering it, tuning into this series feels like getting a thoughtful briefing from informed friends. It’s that blend of timely news analysis and deep-dive interviews that makes the AI Pod a consistent source for understanding the forces at the cutting edge.
Author: Language: en-us Episodes: 36

AI Pod by Wes Roth and Dylan Curious | Artificial Intelligence News and Interviews With Experts
Podcast Episodes
this EX-OPENAI RESEARCHER just released it... [not-audio_url] [/not-audio_url]

Duration: 1:49:22
Welcome to another episode of the Wes & Dylan Podcast! We are diving deep into some of the most mind-bending, dystopian, and revolutionary updates in the world of Artificial Intelligence.From Meta secretly acquiring an e…
Joscha Bach "Bootstrapping a GODLIKE Mind" [not-audio_url] [/not-audio_url]

Duration: 1:36:55
Can machines actually think, or are we simply asking the wrong question? Just like submarines don't "swim" but navigate the depths in a far more advanced way, artificial intelligence is redefining what it means to proces…
GROK 4.20 and the "SOCIETY OF MINDS" [not-audio_url] [/not-audio_url]

Duration: 1:23:48
Welcome back to another episode of the Wes and Dylan podcast! In this packed episode, we dive headfirst into the brand-new beta release of Grok 4.20 and its mind-bending "swarm intelligence."We also tackle the heavy stuf…
OpenClaw can't stop [not-audio_url] [/not-audio_url]

Duration: 1:18:37
Welcome back to another wild ride! Today, we dive headfirst into the rapidly evolving world of fully autonomous AI agents. We share a crazy, firsthand case study of building a completely AI-operated business from scratch…
Clawdbot is absolutely INSANE [not-audio_url] [/not-audio_url]

Duration: 1:45:43
We just crossed a massive threshold in artificial intelligence. Imagine waking up, opening your laptop, and realizing your AI agent has been working all night—handling your emails, scheduling your calendar, and executing…
$1 Trillion Gone and it's JUST Starting... [not-audio_url] [/not-audio_url]

Duration: 57:54
The AI industry is moving at breakneck speed, and this week’s fallout is massive. From a $1 trillion "SaaS Apocalypse" wiping out legacy software stocks to a wild, AI-assisted hack on thousands of robot vacuums, we are b…