All decision model projects

Tool that recomputes Jev's confidence identities on outputs published in public repositories to spot answers Jev never actually produced.

RPG experiment pitting Jev against OpenAI's Decisions API as NPCs, comparing wins, per-move accuracy, calibration and cost.

Korean study notes and TypeScript mock-ups of Jev concepts, with a local Laya versus GPT-5 comparison and a calibration toolkit.

Learning project benchmarking zero-shot Jev and GPT models against scikit-learn classifiers and ModernBERT on five datasets.

Benchmark harness pitting Jev against Claude Sonnet 5 and Haiku 4.5 on Banking77 intent sorting with a confidence gate.

Evaluates Jev as a fixed policy in Gymnasium and Atari games, picking a legal action each step via one Choice question.

Rust research workbench where Jev gives a cancer-of-unknown-primary origin distribution over 22 classes, gated locally for review.

Open 2B browser-agent decision model fine-tuned from MiniCPM5 that serves the System One protocol for jev-ultrafast.

Experiment that deliberately misuses Jev as a text generator by asking which symbol comes next and sampling from the returned distribution.

Mineflayer Minecraft bot where code lists feasible actions and Jev picks one in about 0.2 s; 15 of 40 runs reached the Nether.

DuckDB extension and Python package for semantic SQL that batches row-level filters, joins and classification on Jev.

Spanish oncology decision-support prototype that walks ESMO guideline trees and uses Jev only for judgment calls.

Minimal agent loop where Jev selects each action and approves tool calls, a chat model fills arguments, and MCP tools execute.

Chat client that makes Jev write by asking Next word? over a 20,000-word dictionary in 255-word buckets plus a run-off.

An LLM writes a task-specific Jev harness, improved with rewards and traces; a Pokemon harness rose from 25% to 75% wins.

Experimental engine that makes an existing LLM do Jev-like classification and scoring by reusing context and building JSON.

Inference engine for Jev-style decision models using segmented forwards with prefix reuse, serving the Jev wire contract.

From-scratch research reconstruction of a small System-One decision model, used to route and gate commands in a Windows palette.

Traffic signal controller where Jev picks each intersection's next phase from a SUMO snapshot, with local fallbacks.

Offline Python toolkit that measures sensitivity, Fisher information and information loss in the probabilities of Jev-style agent systems.

Python kernel of Jev Choice/Score/Noul gates, caches and loops used to admit or reject Lean proof candidates in research pipelines.

C/C++ compiler driver where Jev decides whether to inline each discretionary call site, compared against Clang -Oz.

Research code showing that short, natural-looking context additions can flip decision models like Jev to a chosen wrong answer.

Experiment that uses Jev as a sampler: DeepSeek proposes top-k next tokens and Jev chooses which comes next and when to stop.

Builds auditable decision trees and runnable decision SOPs from data and a natural-language goal via LLM features and information gain.

Benchmark of Jev against low-cost LLMs on 130,000 classification decisions across five datasets for accuracy, cost and latency.

Research fork of Laya that reads typed choice and yes/no decisions from an image plus optional text in one forward pass.

Open decision models that derive calibrated confidence from recurrent looped-layer dynamics instead of RL, with early exit and a Jev API.

Research adding plain-English constraints to JEPA world-model planning, with Jev judging each imagined step instead of an LLM.

Experiment that makes Jev produce prose by asking one choice question per word over a routed domain vocabulary.