AI safety via debate · HackerPapers discussions

AI safety via debate — mentioned by xpe

Wed, 04 Mar 2026 17:49:33 GMT

What you've described seems like a better process than most, by far. > This is exactly why every AI citation we publish goes through a blocker. Who is "we"? Kudos! > What guard rails have other people put in front of AI-written judgements? A great question. Some 'classic' responses here relate to (a) inter-notator agreement [1]; (b) debate [2]; (c) decomposition / deconstruction [3]; and lots more... computer science is all well and good, but philosophy has studied these topics for thousands of years! Epistemology, in particular, totally slays. I would also generalize the question: what…

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

AI safety via debate — HN submission

Mon, 30 Jul 2018 22:11:59 GMT

AI safety via debate

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AI safety via debate — HN submission

Wed, 25 Jul 2018 13:37:42 GMT

AI safety via debate

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AI safety via debate — mentioned by nmca

Tue, 24 Jul 2018 10:59:35 GMT

One approach being considered is "AI Safety Via Debate"[0], which hopes to prevent deception by carefully constructing games in which a superhuman agent's best strategy is honesty. Note that this is the goal; much work to be done! [0] https://arxiv.org/abs/1805.00899

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

AI safety via debate — mentioned by nmca

Tue, 15 May 2018 10:40:11 GMT

This is about the Debate paper, and is an idea that is being taken quite seriously - https://arxiv.org/abs/1805.00899 The idea is that the given example (explained in more detail in the paper) is the first step towards understanding how such a system might work.

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