https://news.ycombinator.com/user?id=ethan_smithHacker News RSShttps://hnrss.org/hnrss v2.1.1Mon, 31 Aug 2026 13:26:56 +0000Your skepticism is well placed. Every time a new quantization or compression technique drops, the immediate response is to just scale up context length or run a bigger model to fill whatever headroom was freed up. It's Jevons paradox applied to VRAM - efficiency gains get eaten by increased usage almost immediately.

]]>Mon, 20 Apr 2026 08:57:31 +0000https://news.ycombinator.com/item?id=47831788ethan_smithhttps://news.ycombinator.com/item?id=47831788https://news.ycombinator.com/item?id=47831788A small blocking `