Top postsTop post
Abstract: In an effort to inform the discussion surrounding existential risks from AI, we formulate Extinction-level Goodhart’s Law as "Virtually any goal specification, pursued to the extreme, will result in the extinction[1] of humanity'', and we aim to understand which formal models are suitable for investigating this hypothesis. Note that...
I am Dutch, so wanted to share this as a datapoint regarding public perception of existential AI risk, since it probably won't be noticed here otherwise. 3 days ago (23th march 2023) a Dutch AI "science communicator" who regularly appears on Dutch television to talk about AI, has mentioned on...
I've noticed that when people are asked to "Steelman" a position, they sometimes instead do what I would call "Straw-Steelmanning". Someone can also straw-steelman without having been asked to steelman or having said that they would do so. What is straw-steelmanning? Assume someone makes an argument X for a claim...
Epistemic status: Not well argued for, haven’t spent much time on it, and it’s not very worked out. This thesis is not new at all, and is implicit in a lot (most?) of the discussion about x-risk from AI. The intended contribution of this post is to state the thesis...
I own probably about 10^13 FLOP/s, mostly in my pc (currently in Amsterdam). Google owns more than that, in various datacenters (e.g. one in The Dalles, Oregon). I'd like to get a better picture of the distribution of FLOP/s in the world. Any high level broadly relevant information would be...
epistemic status: Speculation. The actual proposals are idealized, not meant to be exactly right. We have thought about this for less than an hour. In this earlier post I stated a speculative hypothesis about the algorithm that a single imitator that imitates collections of multiple humans would learn. Here Joar...
epistemic status: A speculative hypothesis, don't know if this already exists. The only real evidence I have for this is a vague analogy based on some other speculative (though less speculative) hypothesis. I don’t think this is particularly likely to be true, having thought about it for about a minute....