Top postsTop post
Introduction Polarisation hampers cooperation and progress towards understanding whether future AI poses an existential risk to humanity and how to reduce the risks of catastrophic outcomes. It is exceptionally challenging to pin down what these risks are and what decisions are best. We believe that a model-based approach offers many...
A professor I'm friendly with has been teaching a course on AI ethics this semester, and he asked me if I could come give a guest lecture on "AI apocalypse" scenarios. What should I include in the lecture? Details: * Audience is mostly graduate engineering students. Some are in a...
(Cross-post from the EA Forum) The US National Institute of Standards and Technology (NIST) previously put out a request for information (RFI) to help shape the AI Risk Management Framework that it is working on. NIST is an important organization in establishing standards for government and industry, so contributions here...
Numerous books, articles, and blog posts have laid out reasons to think that AI might pose catastrophic or existential risks for the future of humanity. However, these reasons often differ from each other both in details and in main conceptual arguments, and other researchers have questioned or disputed many of...
Cross-posted from the EA Forum: https://forum.effectivealtruism.org/posts/Ry4C4CKZvuRG7ztxY/pros-and-cons-of-working-on-near-term-technical-ai-safety Recently I've been thinking about the pros and cons of working on near-term technical AI safety and assurance. This includes topics such as interpretability for near-term systems, generalizability / robustness, AI security, testing, verification, and the like. Here are my own considerations so far:...
Can we compile a list of good project ideas related to AI safety that people can work on? There are occasions at work when I have the opportunity to propose interesting project ideas for potential funding, and it would be really useful if there was somewhere I could look for...
Just a very brief link to a resource that people may not know about: Johns Hopkins Institute for Assured Autonomy newsletter For anybody interested in nearer-term AI safety / assured autonomy issues, I have found this recently-started newsletter to be a useful aggregator of relevant news and articles. (Full disclosure:...