robertskmiles

Early Access: 6 New AI Safety Talks

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

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

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

Early Access Video: We Were Right! Real Inner Misalignment

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

Early Access Video: Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think...

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

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

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

Early Access Video: 10 Reasons to Ignore AI Safety

Early Access Video: 9 Examples of Specification Gaming

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

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

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

Why Not Just: Think of AGI Like a Corporation?

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

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

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

Early Access Video: AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes #1

Early Access Video: What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4

Early Access Video: The REAL "Killer Robot Arms Race" Elon Musk should worry about

Early Access Video: Reward Hacking: Concrete Problems in AI Safety Part 3