robertskmiles

Video: Why AI Systems Lie, and What We Can Do About It

Second Channel Video: Why Don't I Give Specifics?

Second Channel/Short Video: Would You Help an AI to Escape?

Video: Second Research Talk by John Wentworth

Video: Research Talk by John Wentworth

Early Access Short: Win $50k for Solving a Single AI Problem?

Early Access 2nd Channel Video: There's No Rule That Says We'll Make It

Video: Experimental TikTok about GitHub Copilot

New(ish) Video: Intro to AI Safety, Remastered

Early Access Video: The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment

Early Access Video: Quantilizers: AI That Doesn't Try Too Hard

BTS Video: New Camera! Unboxing, Testing, and Modification

Early Access Video: Sharing the Benefits of AI: The Windfall Clause

Early Access Video: 10 Reasons to Ignore AI Safety

Answering your AI Safety Questions (Part 2)

Early Access Video: 9 Examples of Specification Gaming

Patron Exclusive (obviously): Quarantine Haircut

Answering your AI Safety Questions (1)

Early Access Video: Training AI Without Writing A Reward Function, with Reward Modelling

Patreon-exclusive Video: Yann Lecun and Stuart Russell Discuss Instrumental Convergence

Early Access Video: AI That Doesn't Try Too Hard - Maximizers and Satisficers

Computerphile Video: Why Didn't OpenAI Release GPT-2?

Computerphile Video: More about GPT-2

2nd Channel Video: Generating Fake YouTube Comments with GPT-2

Is AI Safety a Pascal's Mugging?

Early Access Video: A Response to Steven Pinker

How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification

Behind the Scenes: Lightboard tests

Deleted Scenes from "Why Not Just: Think of AGI Like a Corporation?"

Why Not Just: Think of AGI Like a Corporation?

Computerphile Video: Logical Induction

BTS/WIP: Explaining Markov Decision Processes

Early Access Video: Safe Exploration: Concrete Problems in AI Safety Part 6

Patreon Update: Stay Tuned!

Patron-only Video: There's No Rule...

Early Access Video: Friend or Foe? AI Safety Gridworlds extra bit

BTS/WIP: Starting to explain Supervision Partially Observable Markov Decision Processes

Early Access New Video! AI Safety Gridworlds

Behind The Scenes Video: RAISE Corrigibility Intro

2nd Channel Early Access: Talk at 'AI and Politics' meetup

Experts' Predictions about the Future of AI

Early Access: Why Would AI Want to do Bad Things? Instrumental Convergence

Draft Video Lecture

Early Access: Superintelligence Mod for Civilization V

Behind The Scenes: Filming a Let's Play

The Orthogonality Thesis, Intelligence, and Stupidity

Early Access Video: What can AGI do? I/O and Speed