Control plane
Draft
Detail editor for one draft. Save, approve into queue, or reject out of the editorial flow.
local DBprivate
Source
2026-03-16 19:06:57.000000
Very interesting results about the fine-tunability of different models. 👀
LFM2 is more flexible than alternatives. It also confirms some common knowledge about RL degrading fine-tuneability.
Quoted original
Jacek Golebiowski (@j_golebiowski) · Mon Mar 16 18:29:41 +0000 2026
We benchmarked 15 small language models across 9 tasks to find out which one you should actually fine-tune.
The most surprising result: Liquid AI's LFM2-350M ranked #1 for tunability. 350M parameters, absorbing training signal more effectively than models 20x its size.
The https://t.co/qoTU9MAnsG
Draft text
Req 2026-03-16T1931-TOP1
Queue membership is preserved when editing an already approved draft.