Stay informed

Alignment Forum

The Alignment Forum is a hub for researchers to discuss all ideas related to ensuring that transformatively powerful AIs are aligned with human values. Discussion ranges from technical models of agency to the strategic landscape, and everything in between.

Type

Forum

LessWrong

All Alignment Forum posts are cross-posted to LessWrong where anyone, not just approved researchers, can engage with the research, with moderators able to promote good comments to the Alignment Forum. LessWrong is also is an online forum and community dedicated to improving human reasoning and decision-making more broadly.

Type

Forum

AI Safety Videos

A carefully collected playlist of videos to give you an understanding of what's going on with AI.

Type

YouTube channel

Robert Miles AI Safety

Videos about artificial intelligence safety research, for everyone.

Type

YouTube channel

AISafety.info Book List

AISafety.info has a list of books about AI safety, explaining what they focus on and who should go towards which.

Type

Book

Cold Takes

Blog about transformative AI, futurism, research, ethics, philanthropy etc. by Holden Karnofsky. Includes the "most important century" series, which argues that the 21st century could be the most important ever for humanity.

Type

Blog

The AI Revolution: The Road to Superintelligence

A good pair of articles about Superintelligence on the website Wait But Why.

Type

Article

Doom Debates

It's time to worry about the end of the world. With your host, Liron Shapira.

Type

YouTube channel

The AI Does Not Hate You: Superintelligence, Rationality and the Race to Save the World

This is a book about AI and AI risk. But it's also more importantly about a community of people who are trying to think rationally about intelligence, and the places that these thoughts are taking them, and what insight they can and can't give us about the future of the human race over the next few years.

Type

Book

The 80,000 Hours Podcast

All episodes of The 80,000 Hours Podcast about artificial intelligence.

Type

Podcast

Uncontrollable: The Threat of Artificial Superintelligence and the Race to Save the World

The book Uncontrollable clearly communicates the urgency to act now and provides concrete suggestions for society and concerned citizens to create a safer future with AI. THIS LENGTH

Type

Book

AI Safety Talks

High quality talks from AI Alignment researchers.

Type

YouTube channel

LessWrong podcast

Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.

Type

Podcast

EA Forum podcast

Audio narrations from the Effective Altruism Forum, including curated posts and posts with 125 karma.

Type

Podcast

generative.ink

Blog about large language models by janus the GPT cyborg, focusing on things like prompt engineering, human-in-the-loop interactions, and the metaphysical implications of AI-generated content.

Type

Blog

For Humanity Podcast

This podcast is dedicated solely to the existential threat Artificial General Intelligence poses to humanity.

Type

YouTube channel

Alignment Newsletter Podcast

The Alignment Newsletter was until 2022 a weekly publication with recent content relevant to AI alignment. This podcast is an audio version, recorded by Robert Miles.

Type

Podcast