Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive? · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2406.04391/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTWhy Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive? — mentioned by pizzahttps://news.ycombinator.com/item?id=40701702urn:hackerpapers:mention:2406.04391:40701702Mon, 17 Jun 2024 02:02:48 GMT<p>Eh, I don&#x27;t think that&#x27;s their position: &gt; nothing in this paper should be interpreted as claiming that large language models cannot display emergent abilities; rather, our message is that some previously claimed emergent abilities appear to be mirages induced by researcher analyses imo their paper&#x27;s position is - downstream task metric jumps in accuracy don&#x27;t imply sudden changes in pretrain loss - you can cherry pick metrics to show the sudden appearance of emergent abilities - model scale is not enough to explain emergent abilities because you can scale up one model family and not get them…</p><p><a href="https://hackerpaper.kaipfister.de/p/2406.04391/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG