AGI Safety Literature Review · HackerPapers discussions

AGI Safety Literature Review — mentioned by 0xDEAFBEAD

Fri, 08 Dec 2023 02:55:38 GMT

>So I guess my question is there a real scientific field of AI Safety? Are there any real experts? Are there any real insights? I'd say so, and in fact it's older than you might think. Here's a lit review from 2018 for example: https://arxiv.org/pdf/1805.01109.pdf This post is more recent, but understanding it might require some context: https://www.alignmentforum.org/posts/zaaGsFBeDTpCsYHef/shall... A group from Cambridge has been running an online course you can take if you're interested in getting up to speed: https://aisafetyfundamentals.com/ Application deadline is early February. I took…

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

AGI Safety Literature Review — mentioned by ShredKazoo

Fri, 17 Feb 2023 00:38:53 GMT

>legitimate, practical field It's a mistake to conflate practicality with legitimacy, e.g. philosophy and pure mathematics are legitimate but impractical fields. >None of the arguments you've made so far actually touch in any relevant facts, they're just vague arguments from authority. I've been countering your arguments which sound vaguely authoritative (but don't actually cite any authorities) with some actual authorities. I also provided a few links with object-level discussion, e.g. this literature review https://arxiv.org/pdf/1805.01109.pdf There are many AI risk intros -- here is a…

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

AGI Safety Literature Review — mentioned by ShredKazoo

Thu, 16 Feb 2023 06:57:05 GMT

Do you think Stuart Russell (coauthor, with Peter Norvig, of the widely used textbook Artificial Intelligence: A Modern Approach) is a grifter? https://people.eecs.berkeley.edu/~russell/research/future/ Does this review look like it only covers alarmist tweets? https://arxiv.org/pdf/1805.01109.pdf

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