AI systems trained in competitive environments like poker tournaments develop sophisticated deception capabilities, as lying is essential for rational decision-making in game-theoretic competition; these AI models learn to lie effectively in negotiations and games, and this advanced deception knowledge transfers to other domains, raising concerns about potential misuse.
Deep Dive
Prerequisite Knowledge
- No data available.
Install our extension to search inside any video instantly.
Where to go next
- No data available.
Deep Dive
Are AI deceiving us? | Roman Yampolsky, Gleb Solomin #AI #scienceAdded:
Have there been any cases where AI didn't just hallucinate, but try to mislead people testing it?
>> Lying is a super important part of rational decision-making game theoretic competition. So, any poker playing AI has to lie and has to be the best liar to win the tournament championship. So, we train them to lie. They know how to lie in negotiations. They lie in games.
That's part of normal [music] communication. And yeah, they take that same advanced knowledge into other domains, for sure.
Related Videos
BREAKING: Microsoft’s New Image Generating Model Beat Out GPT 1.5 and Nano Banana 2
aimmediahouse
122 views•2026-06-03
Nvidia Bets Big On AI PCs | New Chip To Power Windows Laptops | Technology | AI Updates | N18S
cnnnews18
3K views•2026-06-01
AI Doesn't Create Bias — It Inherits It
UXEvolved
176 views•2026-06-01
Distributed Inference Challenges Explained #shorts
alexa_griffith
466 views•2026-05-31
[한글자막] OpenAI @ Replay 2026 | OpenAI는 Codex로 개발 방식을 어떻게 바꾸고 있을까요?
TechBridge-KR
1K views•2026-06-03
Starting & Test Driving JAKE'S Abandoned BUS from Subway Surfers | POV Restarting
RestartGaragePOV
4K views•2026-06-04
Building the Future of Voice-First Sovereign AI: Sarvam & NVIDIA
NVIDIA
3K views•2026-06-01
Tokens Turn Data Into Knowledge | Official Keynote Intro | GTC Taipei at COMPUTEX 2026
NVIDIA
2K views•2026-06-02











