Media Summary: It's an older paper, but it checks out. Rob Miles discusses the problem of 'Sleeper Agents' - where LLMs could have hidden traits ... Open source tools for creating videos? Lewis decides to help Mike take a break by creating 'MikeBot3000' - an How do we measure harm to improve the performance of

Ai Just Sandbox It Computerphile - Detailed Analysis & Overview

It's an older paper, but it checks out. Rob Miles discusses the problem of 'Sleeper Agents' - where LLMs could have hidden traits ... Open source tools for creating videos? Lewis decides to help Mike take a break by creating 'MikeBot3000' - an How do we measure harm to improve the performance of Language Models' Achilles heel: Rob Miles talks about "glitch" tokens, those mysterious words which, which result in gibberish ... Sponsored by Wix Code: Check them out here: Amazing photo-realistic video generation is one thing, but being able to insert yourself in there, how does that work? Lewis Stuart ...

off your 1st purchase at use the code “ How much of a problem is DeepFake, the ability to swap people's faces around? Dr Mike Pound decided to try it with colleague Dr ... How to we check to see if a black box system is giving us the right result for the right reason? Even a broken clock is correct twice ... The real-world doesn't graph well. Sydney Von Arx discusses GenAI & RL -- See Jane Street's training programs in New York, ... Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains ...

Photo Gallery

AI? Just Sandbox it... - Computerphile
Sleeper Agents in Large Language Models - Computerphile
MikeBot3000: Can We Build an AI Mike from Open Source Tools? - Computerphile
DeepSeek is a Game Changer for AI - Computerphile
Defining Harm for Ai Systems - Computerphile
The Singularity & Friendly AI? - Computerphile
Glitch Tokens - Computerphile
The Problem with A.I. Slop! - Computerphile
The Hard Problem of Controlling Powerful AI Systems - Computerphile
AI Gridworlds - Computerphile
Cloning Yourself in AI using LoRA  - Computerphile
AI Sandbagging - Computerphile
Sponsored
Sponsored
View Detailed Profile
AI? Just Sandbox it... - Computerphile

AI? Just Sandbox it... - Computerphile

Why can't we

Sleeper Agents in Large Language Models - Computerphile

Sleeper Agents in Large Language Models - Computerphile

It's an older paper, but it checks out. Rob Miles discusses the problem of 'Sleeper Agents' - where LLMs could have hidden traits ...

Sponsored
MikeBot3000: Can We Build an AI Mike from Open Source Tools? - Computerphile

MikeBot3000: Can We Build an AI Mike from Open Source Tools? - Computerphile

Open source tools for creating videos? Lewis decides to help Mike take a break by creating 'MikeBot3000' - an

DeepSeek is a Game Changer for AI - Computerphile

DeepSeek is a Game Changer for AI - Computerphile

An

Defining Harm for Ai Systems - Computerphile

Defining Harm for Ai Systems - Computerphile

How do we measure harm to improve the performance of

Sponsored
The Singularity & Friendly AI? - Computerphile

The Singularity & Friendly AI? - Computerphile

Audible free book: http://www.audible.com/

Glitch Tokens - Computerphile

Glitch Tokens - Computerphile

Language Models' Achilles heel: Rob Miles talks about "glitch" tokens, those mysterious words which, which result in gibberish ...

The Problem with A.I. Slop! - Computerphile

The Problem with A.I. Slop! - Computerphile

Researchers suggested there's more

The Hard Problem of Controlling Powerful AI Systems - Computerphile

The Hard Problem of Controlling Powerful AI Systems - Computerphile

As

AI Gridworlds - Computerphile

AI Gridworlds - Computerphile

Sponsored by Wix Code: Check them out here: http://wix.com/go/

Cloning Yourself in AI using LoRA  - Computerphile

Cloning Yourself in AI using LoRA - Computerphile

Amazing photo-realistic video generation is one thing, but being able to insert yourself in there, how does that work? Lewis Stuart ...

AI Sandbagging - Computerphile

AI Sandbagging - Computerphile

Following the theme of

Holy Grail of AI (Artificial Intelligence) - Computerphile

Holy Grail of AI (Artificial Intelligence) - Computerphile

Audible free book: http://www.audible.com/

AI Self Improvement - Computerphile

AI Self Improvement - Computerphile

off your 1st purchase at http://www.littlebits.com use the code “

Is DeepFake Really All That? - Computerphile

Is DeepFake Really All That? - Computerphile

How much of a problem is DeepFake, the ability to swap people's faces around? Dr Mike Pound decided to try it with colleague Dr ...

Verifying AI 'Black Boxes' - Computerphile

Verifying AI 'Black Boxes' - Computerphile

How to we check to see if a black box system is giving us the right result for the right reason? Even a broken clock is correct twice ...

Gen AI & Reinforcement Learning- Computerphile

Gen AI & Reinforcement Learning- Computerphile

The real-world doesn't graph well. Sydney Von Arx discusses GenAI & RL -- See Jane Street's training programs in New York, ...

Generative AI's Greatest Flaw - Computerphile

Generative AI's Greatest Flaw - Computerphile

Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains ...

Related Video Content

OpenAI | Research & Deployment information

We believe our research will eventually lead to artificial general intelligence, a system that can solve human-level...

‎Google Gemini information

Meet Gemini, Google’s AI assistant. Get help with writing, planning, brainstorming, and more. Experience the power of...

ChatGPT information

Chat with the most advanced AI to explore ideas, solve problems, and learn faster.

Google AI - How we're making AI helpful for everyone information

Discover how Google AI is committed to enriching knowledge, solving complex challenges and helping people grow by...

Microsoft Copilot: Your AI companion information

Microsoft Copilot is your companion to inform, entertain and inspire. Get advice, feedback and straightforward...