Provably safe systems: the only path to controllable AGI · HackerPapers discussions

Provably safe systems: the only path to controllable AGI — mentioned by optimalsolver

Wed, 05 Mar 2025 12:37:27 GMT

>AI can eventually create AI's that are built up out of robust and provable logic That's the approach behind Max Tegmark and Steven Omohundro's "Provably Safe AGI": https://arxiv.org/abs/2309.01933 https://www.youtube.com/watch?v=YhMwkk6uOK8 However, there are issues. How do you even begin to formalize concepts like human well-being?

Paper and discussion history. A mention is not an endorsement.

Provably safe systems: the only path to controllable AGI — mentioned by JoshTriplett

Wed, 24 Apr 2024 12:05:28 GMT

> When Sam Altman is calling for AI regulation Sure; that's almost certainly not being done in good faith. When numerous AI experts and luminaries who left their jobs in AI are advocating for AI regulation, that's much more likely to be being done in good faith. > What is this regulation aimed at making AI safer https://pauseai.info/ > Furthermore, there doesn't seem to be any agreement on whether or how AI, at a state remotely similar to the level it is at today, is dangerous You could also write that as "there's no agreement that AI is safe". But that aside... Most of the arguments about AI…

Paper and discussion history. A mention is not an endorsement.

Provably safe systems: the only path to controllable AGI — HN submission

Fri, 22 Sep 2023 23:57:22 GMT

Provably safe systems: the only path to controllable AGI

45 points; 64 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Provably safe systems: the only path to controllable AGI — HN submission

Thu, 07 Sep 2023 12:45:20 GMT

Provably safe systems: the only path to controllable AGI

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.