Current work in AI alignment | Paul Christiano | EA Global: San Francisco 2019
Paul Christiano, a researcher at OpenAI, discusses the current state of research on aligning AI with human values: what’s happening now, what needs to happen, and how people can help. This talk covers a broad set of subgoals within alignment research, from inferring human preferences to verifying the properties of advanced systems. To learn more about effective altruism, visit effectivealtruism.org This talk was filmed at EA Global: San Francisco 2019. You can learn more about these conferences at eaglobal.org You can read a transcript, or discuss this talk, on the Effective Altruism Forum: https://forum.effectivealtruism.org/p...

▶︎
Reframing superintelligence | Eric Drexler | EA Global: London 2018

▶︎
The Windfall Clause: Sharing the benefits of advanced AI | Cullen O’Keefe

▶︎
Paul Christiano - How Misalignment Could Lead to Takeover

▶︎
Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

▶︎
Eliezer Yudkowsky - Difficulties of Artificial General Intelligence Alignment

▶︎
Full interview: "Godfather of artificial intelligence" talks impact and potential of AI

▶︎
"A.I. and Our Economic Future," Professor Chad Jones

▶︎
Visualizing transformers and attention | Talk for TNG Big Tech Day '24

▶︎
The Future of Science With AI | Nobel Prize Dialogue London 2026

▶︎
1:AGI Safety: Evan Hubinger 2023

▶︎
Eliezer Yudkowsky "Friendly AI"

▶︎
Andrew Ng: Building Faster with AI

▶︎
Yudkowsky vs Hanson — Singularity Debate

▶︎
No Priors Ep. 39 | With OpenAI Co-Founder & Chief Scientist Ilya Sutskever

▶︎
A Nobel Laureate's Honest Review of AI In Biology

▶︎
Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start

▶︎
Think Fast, Talk Smart: Communication Techniques

▶︎
What happens when our computers get smarter than we are? | Nick Bostrom

▶︎
Positive Outcomes for AI | Nate Soares | Talks at Google

▶︎
