Havuz

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine f

AnyJev, open LLM’lerden typed kararlar ve eşiklenebilir olasılıklar üretmek için calibration ve karar katmanları sunan bir Python kütüphanesidir.

Neden yükseliyor · Yedi günde 802 yıldız almış; dikkat çekmesinde etiket gerektirmeyen ilk seviye, az etiketle kalibrasyon iddiası ve modeli fine-tune etmeden karar endpoint’i sunma yaklaşımı etkili görünüyor. Bu ilgi benimseme kanıtı değil; verilen sonuçlar README’deki sınırlı benchmark’a dayanıyor.

DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluatio

Coding agent’lara TypeSafe AI Jev ile typed decisions ve calibrated confidence kullanmayı öğreten, topluluk projeleri ve code sketch’leri içeren bir agent skill’idir.

Neden yükseliyor · İki günlük yaşında 69 yıldız almış; bu erken ilgiye işaret ediyor. Ancak son commit ve farklı yazar verisi ölçülmediğinden ilginin kaynağı ve proje aktivitesi hakkında daha güçlü bir çıkarım yapılamaz.

Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier calibration, SystemOne protocol in

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

Edge-cloud vision reference: TFLite gate, MQTT, LLM fallback, temporal memory, calibrated metrology, and a beginner ESP32/serial kit

Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

AI 模拟面试官：每条扣分都强制引用你回答的逐字原文（机器校验，编造引用会被重试/丢弃），四维度加权由确定性代码计算而非模型现编，评分体系设计为可经真人盲评校准 · FastAPI + Vue3 + LangGraph

Knowledge-graph RAG built from structured metadata instead of LLM extraction. 929M edges, zero LLM calls, 83.2% on held-out PubMedQA. Case s

Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen

A 4B decision model built for Korean.

Turn any local language model into a fast decision API with typed, probabilistic answers

Instinct: single-forward-pass decision models (choice / true-false / score) returning a probability per candidate

Several coding agents, one repo, at the same time: a reproducible lab to measure how they coordinate, and Médula, a kernel that decides who

Verify the context you feed your AI agents, against the web or your own documents.

An institutional-intelligence operating system: a council of 14 agents that remembers every deliberation, grades its own predictions against

High-performance, high-precision, locally-fast-deployed Jev-class medical decision service on national medical exams — four readings, one ro

Distil an expensive LLM API call on a narrow task into a small local model: capture traffic, curate, LoRA fine-tune with MLX on Apple Silico