StartLux-Decision introduces AutoThink, a decision model that predicts first and reasons only when confidence is below 0.9, using RLCD² reinforcement learning to optimize reasoning efficiency and probability calibration, evaluated on the new DecisionPivot benchmark.
Lev introduces looped decision models that reuse the same weights across multiple reasoning depths, with a lightweight halting mechanism to allocate more computation to hard questions, achieving better accuracy-latency trade-offs than cascading or chain-of-thought approaches.
This article compares TypeSafe's Jev and OpenAI's Decisions API, two decision-model APIs that replace LLM-based classification with typed, probabilistic decisions, detailing their shared primitives, differences in model origin, modalities, pricing, latency, ecosystem, and practical integration patterns for vertical AI agents.
This article analyzes TypeSafe AI's Jev, a non-autoregressive 'System One' model that returns typed decisions with probabilities instead of generating text, contrasting it with LLMs, detailing its three output primitives (Choice, Score, Noul), four pilot scenarios, a four-step production integration process, and implications for AI software architecture.
HiRoute is a local intelligent routing engine that dynamically assigns tasks between economical and powerful AI models, enables Agent collaboration, preserves KV cache via context holding, and integrates decision models like Jev, demonstrating over 90% cost reduction in real-world engineering tasks while maintaining quality.
Liquid AI releases two open-weight decision models, d1-3B and d1-omni-600M, which use single-forward-pass inference to achieve 8ms latency on RTX 4090, eliminating token generation for classification, routing, and scoring tasks with zero output tokens.
Perplexity releases pplx-decider-v1.1-27b, an open-weight decision model based on Qwen3.8-27B that tops the Decision Index benchmark, outperforming Jev and other clones, with non-causal attention and a calibrated decision head for classification, routing, and scoring tasks, deployable on 80GB GPUs.
Cloudflare open-sources Clef and Clef-flash, prefill-only decision models that score predefined options for routing tasks like ticket triage, avoiding token-by-token generation; the article explains their architecture, probability calibration needs, benchmark results versus Jev, latency and cost trade-offs, and a fine-tuning loop using Cloudflare's AI Gateway and Workers AI.
This article details eight practical scenarios where JEV (Judgment and Evaluation) models accelerate agent decision-making, including ReAct loop control, web automation, tool routing, safety guards, task evaluation, model routing, RAG filtering, and real-time robotics control, showing how lightweight classifiers reduce latency and token costs.
Jev is a non-generative 'System One' AI model from TypeSafe that outputs structured decisions with calibrated probabilities in 70-500ms, 20-200x faster and 40-400x cheaper than LLMs, enabling high-frequency classification, routing, and agent supervision in Java ecosystems via community SDKs.
The article argues that AI agents waste compute by using large language models for low-entropy decisions, and introduces Jev, a lightweight decision model that handles tool routing, code search, and log triage in milliseconds, enabling a System 1/System 2 architecture where Jev filters noise before Codex performs deep reasoning, a pattern mirrored by Glean's enterprise search stack.
Within a week of TypeSafe's Jev release, 13 arXiv papers benchmark the decision model across edge orchestration, agent memory, judging, scam detection, video quality, and visual tasks, showing 15-26% lower latency and 70% cost reduction versus LLMs, but with accuracy gaps on complex reasoning and sensitivity to option naming.
The article benchmarks laya, an open-source Apache 2.0 decision model positioned as a Jev alternative, revealing 6-7x latency gains but poor zero-shot accuracy (0.36 vs majority-class 0.46) unless fine-tuned on custom data, with hands-on CPU tests showing 63ms warm inference but 20s cold starts.
TypeSafe AI's Jev model, marketed as a breakthrough non-autoregressive decision model, faces controversy after independent researcher Nandakishor Mukkunnoth reveals he published similar work a year earlier and released open-source Laya outperforming Jev on benchmarks, sparking debate on Hacker News about priority, open source vs proprietary AI, and attention asymmetry.
The article explains how decision-making AI models like Jev output structured judgments (choices, scores, booleans) instead of natural language, making them better suited for high-frequency, low-risk business decision nodes such as ticket routing, content moderation, and agent workflow control, and discusses deployment strategies like shadow testing and confidence calibration.
