Elektrine lite

← Feed

@mirth@mastodon.sdf.org

2026-04-08 20:14 UTC

@MichaelTBacon @alienghic @cwebber That's not consistent with what I've seen. Using weight footprint as a rough guide, the capability at the 1B, 10B, 30B, etc sizes continue to increase, and current smaller models perform better than larger predecessors. True on the closed side as well: Today's Sonnet is stronger than last year's Sonnet _and_ Opus, today's GPT-5.4 mini is stronger than GPT-5 at release, etc. Current 30B tier open models are stronger than GPT-4 was.

Replies (1)

  • @mirth@mastodon.sdf.org 2026-04-08 20:17

    @MichaelTBacon @alienghic @cwebber That's models. On the silicon side, ten years ago the bulk of inference ran on regular CPUs. Most of that moved to GPUs maybe five years ago, and now specialist chips are becoming more common. I know a little bit about chip design, and there's a lot of inefficiency that will get designed out of accelerators (reliance on DRAM is the big one, Cerebras and Taalas are the two notable current attempts).

    Open ##1732749