There Will Be a Scientific Theory of Deep Learning · HackerPapers discussions

There Will Be a Scientific Theory of Deep Learning — mentioned by hodgehog11

Sun, 20 Sep 2026 16:19:36 GMT

A group already (sort-of) has for the broader theory: https://arxiv.org/abs/2604.21691 It's a good list, but "alignment" is much more targetted. I attended a workshop with researchers from OpenAI and Anthropic also present, where the objective was to hash out what the problems in alignment even are. This, it turned out, was extraordinarily difficult. The problems with alignment are to do with how we define and search for this vague notion when it is mathematically ill-posed at present.

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

There Will Be a Scientific Theory of Deep Learning — mentioned by inkysigma

Sat, 06 Jun 2026 09:22:30 GMT

This is essentially an open research question. ML theory is unfortunately very weak relative to where the empirics are. I think there's a relatively optimistic paper that was posted a while back here but I would also take it with a grain of salt. https://arxiv.org/abs/2604.21691 There's of course empirical results and relatively weak theoretical results like the UAT but I also don't think that answers your question fully, especially since it seems impossible to definitively answer questions that the industry seems to betting on like whether or not there is a lower bound to their error rate or…

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

There Will Be a Scientific Theory of Deep Learning — mentioned by smokel

Wed, 06 May 2026 19:45:37 GMT

This essay seems to be related to the paper "There Will Be a Scientific Theory of Deep Learning" [1] which was discussed here recently [2]. [1] https://arxiv.org/pdf/2604.21691 [2] https://news.ycombinator.com/item?id=47893779

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

There Will Be a Scientific Theory of Deep Learning — HN submission

Fri, 24 Apr 2026 18:06:05 GMT

There Will Be a Scientific Theory of Deep Learning

367 points; 167 discussion replies on HN. Paper and source history. A submission is not an endorsement.