Skip to content
All tags

#decision-model

4 posts
aideep-dive

Serving Decision Models Fast: Flide's State Forking, Where It Wins, and Its Limits

When several questions share one context, Flide computes the shared state once and forks it per question with answers identical to asking alone; up to 9.5x faster than vLLM and SGLang at best, roughly 1.3x to 3.3x on average for shared-state workloads, and only about 1x to 3x with one question per input.

Cloudflare Model Family: Choosing Clef Decision Models and Clairic Extraction Models

Cloudflare's own models come in two classes: the Clef family returns option probabilities (clef 27B, clef-flash 9B, clef-omni 30B-A3B), while Clairic returns typed values and intervals. All four bill input tokens only ($0.038–$0.24 per million) and charge nothing for output; the three Clef models ship Apache-2.0 weights, and Clairic is still a hosted preview. They beat Jev on decision benchmarks and trail it on reasoning-heavy ones.

Choosing a Decision Model: Jev, Decider, d1-ultra, mammoth-1, and a Dozen More

Decision models replace an LLM's "generate some text and you write the parser" with "you list the options up front and the model returns a probability for each." After TypeSafe proposed System One on 2026-09-15, this category went from one vendor to more than a dozen: Jev 1.14, the OpenAI Decisions API, Perplexity Decider v1.2, Microsoft-Decision-1, Liquid d1-ultra, Base Labs mammoth-1, vLLM d3, StartLux, Fastino GLiDE, Celeris-1 Decision, Inception Mercury Decide, and Cloudflare Clef. The two leaderboards disagree almost completely — the community Jev Decision Index 0.4.1 crown goes to GLiDE V1.2 (71.5), while the independent Artificial Analysis Decision Index crown goes to d1-ultra (65.2) with Jev 1.14 at only 57.1. Decision models win on classification and tool selection, lose on knowledge and reasoning, and are broadly overconfident.

AI Agent GitHub Digest — 2026-09-26

Nokia's applied research team open-sourced AnyJev, which uses cyclic shifts plus batch prior correction to turn any open LLM into a calibrated decision model with no training — raising auto-decidable traffic from 7.7% to 52.0% in their own benchmark. DSPy 3.4.0 added a TypeSafe client integration with two breaking changes. Pydantic AI v2.50.0 promoted last week's `TypeSafeModel` into a formal `DecisionModel` base class. Also trending: golive-skill, which hands a coding agent the last step of actually shipping to production; magpie, which turns swapping a coding agent's backend model into a menu-bar click; and sno-station, which pairs Claude Code and Codex on one machine and lets them rewrite their own skills.