Media Summary: This video explains our latest research on Suppose we're worried about AIs engaging in long-term plans that they don't tell us about. If we were to peek inside their brains, ... A demo video showing that Frontier Models are Capable of In-context

Understanding Ai Scheming Insights From - Detailed Analysis & Overview

This video explains our latest research on Suppose we're worried about AIs engaging in long-term plans that they don't tell us about. If we were to peek inside their brains, ... A demo video showing that Frontier Models are Capable of In-context Marius Hobbhahn (Apollo Research CEO) and Bronson Schoen (Researcher and Lead Author) discuss the motivations behind ... Christopher Summerfield, Professor of Cognitive Neuroscience at Oxford and Research Director at the UK

Photo Gallery

Understanding AI scheming: insights from new research - Episode 1 @Laradavidai
Interpretability: Understanding how AI models think
AIs Are Lying to Users to Pursue Their Own Goals | Marius Hobbhahn (CEO of Apollo Research)
Can We Train AI to Be Less Deceptive?
38.5 - Adrià Garriga-Alonso on Detecting AI Scheming
Apollo Research: Demo 'Frontier Models Are Capable Of In-Context Scheming'
Can We Stop AI from Scheming? Lead Researcher Interview
Can AI Think? Debunking AI Limitations
Christopher Summerfield - Lessons from a Chimp: AI "Scheming" & the Quest for Ape Language [Alignmen
You don't understand AI until you watch this
AI trying to ESCAPE? AI control explained: Ryan Greenblatt on LessWrong
They said AI scheming was just a lab problem - Scheming in the wild - Episode 02
View Detailed Profile
Understanding AI scheming: insights from new research - Episode 1 @Laradavidai

Understanding AI scheming: insights from new research - Episode 1 @Laradavidai

keywords

Interpretability: Understanding how AI models think

Interpretability: Understanding how AI models think

What's happening inside an

AIs Are Lying to Users to Pursue Their Own Goals | Marius Hobbhahn (CEO of Apollo Research)

AIs Are Lying to Users to Pursue Their Own Goals | Marius Hobbhahn (CEO of Apollo Research)

We often worry about

Can We Train AI to Be Less Deceptive?

Can We Train AI to Be Less Deceptive?

This video explains our latest research on

38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

Suppose we're worried about AIs engaging in long-term plans that they don't tell us about. If we were to peek inside their brains, ...

Apollo Research: Demo 'Frontier Models Are Capable Of In-Context Scheming'

Apollo Research: Demo 'Frontier Models Are Capable Of In-Context Scheming'

A demo video showing that Frontier Models are Capable of In-context

Can We Stop AI from Scheming? Lead Researcher Interview

Can We Stop AI from Scheming? Lead Researcher Interview

Marius Hobbhahn (Apollo Research CEO) and Bronson Schoen (Researcher and Lead Author) discuss the motivations behind ...

Can AI Think? Debunking AI Limitations

Can AI Think? Debunking AI Limitations

Want to learn more about

Christopher Summerfield - Lessons from a Chimp: AI "Scheming" & the Quest for Ape Language [Alignmen

Christopher Summerfield - Lessons from a Chimp: AI "Scheming" & the Quest for Ape Language [Alignmen

Christopher Summerfield, Professor of Cognitive Neuroscience at Oxford and Research Director at the UK

You don't understand AI until you watch this

You don't understand AI until you watch this

How does

AI trying to ESCAPE? AI control explained: Ryan Greenblatt on LessWrong

AI trying to ESCAPE? AI control explained: Ryan Greenblatt on LessWrong

AI

They said AI scheming was just a lab problem - Scheming in the wild - Episode 02

They said AI scheming was just a lab problem - Scheming in the wild - Episode 02

Episode 02 -

What Is Understanding? – Geoffrey Hinton | IASEAI 2025

What Is Understanding? – Geoffrey Hinton | IASEAI 2025

What does it actually mean for