Thanks to Chris Olah, Neel Nanda, Kate Woolverton, Richard Ngo, Buck Shlegeris, Daniel Kokotajlo, Kyle McDonell, Laria Reynolds, Eliezer Yudkowksy, M…| www.alignmentforum.org
ARC explores the challenge of extracting information from AI systems that isn't directly observable in their outputs, i.e "eliciting latent knowledge…| www.alignmentforum.org
AI safety research — research on ways to prevent unwanted behaviour from AI systems — generally involves working as a scientist or engineer at major AI labs, in academia, or in independent nonprofits.| 80,000 Hours
Machine learning systems are on a spectrum from process-based to outcome-based. This post explains why Ought is devoted to process-based systems.| ought.org
The three biggest AI companies — Anthropic, OpenAI, and DeepMind — have now all released policies designed to make their AI models less likely to go rogue or cause catastrophic damage as they approach, and eventually exceed, human capabilities. Are they good enough?| 80,000 Hours
TL;DR: This document lays out the case for research on “model organisms of misalignment” – in vitro demonstrations of the kinds of failures that migh…| www.alignmentforum.org
In this post, we argue that AI labs should ensure that powerful AIs are controlled. That is, labs should make sure that the safety measures they appl…| www.alignmentforum.org
Our list of the most promising high-impact career paths for helping others.| 80,000 Hours
By Pedro A. Ortega, Vishal Maini, and the DeepMind safety team| Medium
Advanced AI systems could have massive impacts on humanity and potentially pose global catastrophic risks. There are opportunities...| 80,000 Hours
Even when you try to do good, you can end up doing accidental harm. But there are ways you can minimise the risks.| 80,000 Hours
Please contact us to suggest ideas, improvements, or corrections.| jobs.80000hours.org
Please contact us to suggest ideas, improvements, or corrections.| jobs.80000hours.org
OpenAI says its mission is to build AGI — an AI system that is better than human beings at everything. Should the world trust them to do this safely?| 80,000 Hours
Course materials and notes for Stanford class CS231n: Convolutional Neural Networks for Visual Recognition.| cs231n.github.io
Which problems are the biggest, most tractable, and most neglected in the world - and what can you do about them?| 80,000 Hours
We are no longer accepting submissions. We'll get in touch with winners and make a post about winning proposals sometime in the next month. …| www.alignmentforum.org
This is an archived version of the early 2022 hiring round page.| Alignment Research Center
Get free 1:1 career advice from one of our advisors. We can help you choose your focus, make connections, and find a fulfilling job.| 80,000 Hours
Why do we think that reducing risks from AI is one of the most pressing issues of our time? There are technical safety issues that we believe could, in the worst case, lead to an existential threat to humanity.| 80,000 Hours