Open decision models split into encoder and decoder camps — Liquid AI tried both
helloiamleonie · x · 2026-11-06
Kicking off a technical thread, Liquid AI's Leonie maps the open decision-model ecosystem: encoder-based approaches (convaiinnovations/laya, fastino/GLiNER2.5-Decide, LiquidAI/d1-omni-600M) vs decoder-based ones (perplexity-ai/pplx-decider-v1.2, Cloudflare/clef, LiquidAI/d1-3B, mostly on Qwen3.8-27B bases). Liquid has both architectures, so its first iteration tried both.
Related event: Liquid AI drops causal mask to make decoders work as decision models(2 posts)→
More from Models
- Bittensor miners train open-source decision model REAX 1.3 — const_reborn · 2026-11-06
- Bittensor subnet 92 releases REAX 1.3, an open-source decision model blending miner models — const_reborn · 2026-11-06
- Kimi K3.1 Pro scores 9.9% on agentic WeirdML v3, ahead of Kimi-K3 but behind Claude Haiku 5.5 — scaling01 · 2026-11-06
- Rumor: GLM-5.5 to come in 32B and 122B sizes, community figure says no — TheZachMueller · 2026-11-06
- User screenshot suggests Anthropic's weekly Claude limits feel effectively unlimited — StewartalsopIII · 2026-11-06
- Leonie Shares Full Slide Deck on Building Decision Models, Still Early Days — helloiamleonie · 2026-11-06