Summary of Eric Drexler’s work on reframing AI safety
This post contains a bullet point summary of Reframing Superintelligence: Comprehensive AI Services as General Intelligence. (I wrote this in[…]
Read moreCategory: AI
Summary of my views on AI risk
Many effective altruists believe that efforts to shape artificial general intelligence (AGI) – in particular, solving the alignment problem –[…]
Read moreWhy I expect successful (narrow) alignment
Summary I believe that advanced AI systems will likely be aligned with the goals of their human operators, at least[…]
Read moreThoughts on short timelines
Some rationalists and effective altruists have argued (1, 2, 3) that there is a non-negligible chance that artificial intelligence will[…]
Read moreMechanism design for AI
A few weeks ago, I finished my paper on Adaptive Mechanism Design: Learning to Promote Cooperation. In this post, I’d[…]
Read moreWhat does the stock market tell us about AI timelines?
Suppose that there is – as some rationalists and effective altruists claim (1, 2, 3) – a non-negligible chance (say, 10%)[…]
Read moreAn introduction to worst-case AI safety
Introduction The burgeoning field of AI safety has so far focused almost exclusively on alignment with human values. Various technical[…]
Read moreA framework for thinking about AI timescales
To steer the development of powerful AI in beneficial directions, we need an accurate understanding of how the transition to[…]
Read moreFocus areas of worst-case AI safety
Efforts to shape advanced artificial intelligence (AI) may be among the most promising altruistic endeavours. If the transition to advanced[…]
Read moreTraining neural networks to detect suffering
Imagine a data set of images labeled “suffering” or “no suffering”. For instance, suppose the “suffering” category contains documentations of[…]
Read more