Top postsTop post
I've long been interested in the idea of of fiduciary AI: AI that holds the duties of care and (especially) loyalty to its user. As argued in this paper, this sort of fiduciary loyalty is a core element of trust, a precedent in key relationships like those with doctors, lawyers,...
This is a revised version of a paper I put out late last year (including a new table about capabilities lacking in current AI and how we might get them.) Interested in reactions and potential improvements, as I'm contemplating various possibilities for either expansion or distillation/repackaging of this basic picture,...
Overview The idea of this post is to describe, discuss, and if warranted understand how to create, a model of crypto-fed computation.[1] The basic idea is that high-powered GPU (or other ML-specialized) hardware could be equipped with in-chip hardware locks such that the computational cores require a steady stream of...
(crossposted to EA forum here.) Although I have not seen the argument made in any detail or in writing, I and the Future of Life Institute (FLI) have gathered the strong impression that parts of the effective altruism ecosystem are skeptical of the importance of the issue of autonomous weapons...