https://hackerpaper.kaipfister.de/p/2404.11599/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49809862urn:hackerpapers:mention:2404.11599:49809862Tue, 22 Sep 2026 23:54:53 GMT<p>This whole thing reminds me of DeepMind’s Variational Bayesian Last Layers[0], which never gained much traction in the broader “AI” world, but is a remarkably useful tool. And a relatively obvious one that anyone with experience in SVI and with transformer pretraining, seems to independently rediscover (including me) before finding this paper. [0] https://arxiv.org/pdf/2404.11599</p><p><a href="https://hackerpaper.kaipfister.de/p/2404.11599/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG