Media Summary: How do we measure harm to improve the performance of How do you implement an on/off switch on a General A movie where you're deciding the edits, consciously and subconsciously. Richard Ramchurn and his brain

The Hard Problem Of Controlling Powerful Ai Systems Computerphile - Detailed Analysis & Overview

How do we measure harm to improve the performance of How do you implement an on/off switch on a General A movie where you're deciding the edits, consciously and subconsciously. Richard Ramchurn and his brain Discussing ideas of what happens after Generative It's an older paper, but it checks out. Rob Miles discusses the Language Models' Achilles heel: Rob Miles talks about "glitch" tokens, those mysterious words which, which result in gibberish ...

Bug Byte puzzle here - - and apply to Jane Street programs here - (episode sponsor).

Photo Gallery

The Hard Problem of Controlling Powerful AI Systems - Computerphile
Defining Harm for Ai Systems - Computerphile
General AI Won't Want You To Fix its Code - Computerphile
AI "Stop Button" Problem - Computerphile
Brain Controlled Movie - Computerphile
Concrete Problems in AI Safety (Paper) - Computerphile
Stop Button Solution? - Computerphile
No Regrets - What Happens to AI Beyond Generative? - Computerphile
The Problem with A.I. Slop! - Computerphile
Sleeper Agents in Large Language Models - Computerphile
AI Sandbagging - Computerphile
Glitch Tokens - Computerphile
Sponsored
Sponsored
View Detailed Profile
The Hard Problem of Controlling Powerful AI Systems - Computerphile

The Hard Problem of Controlling Powerful AI Systems - Computerphile

As

Defining Harm for Ai Systems - Computerphile

Defining Harm for Ai Systems - Computerphile

How do we measure harm to improve the performance of

Sponsored
General AI Won't Want You To Fix its Code - Computerphile

General AI Won't Want You To Fix its Code - Computerphile

Part 1 of a Series on

AI "Stop Button" Problem - Computerphile

AI "Stop Button" Problem - Computerphile

How do you implement an on/off switch on a General

Brain Controlled Movie - Computerphile

Brain Controlled Movie - Computerphile

A movie where you're deciding the edits, consciously and subconsciously. Richard Ramchurn and his brain

Sponsored
Concrete Problems in AI Safety (Paper) - Computerphile

Concrete Problems in AI Safety (Paper) - Computerphile

AI

Stop Button Solution? - Computerphile

Stop Button Solution? - Computerphile

After seemingly insurmountable

No Regrets - What Happens to AI Beyond Generative? - Computerphile

No Regrets - What Happens to AI Beyond Generative? - Computerphile

Discussing ideas of what happens after Generative

The Problem with A.I. Slop! - Computerphile

The Problem with A.I. Slop! - Computerphile

Researchers suggested there's more

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

AI Sandbagging - Computerphile

AI Sandbagging - Computerphile

Following the theme of

Glitch Tokens - Computerphile

Glitch Tokens - Computerphile

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

Has Generative AI Already Peaked? - Computerphile

Has Generative AI Already Peaked? - Computerphile

Bug Byte puzzle here - https://bit.ly/4bnlcb9 - and apply to Jane Street programs here - https://bit.ly/3JdtFBZ (episode sponsor).