https://news.ycombinator.com/user?id=nihalaniHacker News RSShttps://hnrss.org/hnrss v2.1.1Fri, 09 Oct 2026 06:12:08 +0000Plus one to this comment so much a scaling laws, test time compute and LLM architecture decisions can be traced back/understood if you view LLMs as efficient compression databases that search based on an a retrieval query. Just turns out that they are finding super novel compression techniques that solve unknown answer

]]>Thu, 08 Oct 2026 05:35:07 +0000https://news.ycombinator.com/item?id=50002093nihalanihttps://news.ycombinator.com/item?id=50002093https://news.ycombinator.com/item?id=50002093