SemIf
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
Benchmarks & research
Benchmarks, evals, calibration studies, and open replicas. Browse the collection in Jev Library.
129 entries in the current community snapshotBenchmarks & research Benchmarks & research jev-eval-agent
Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.
Benchmarks & research typesafe-ai-benchmark
This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.
Benchmarks & research jev-on-a-laptop
Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.
Benchmarks & research open-jev (JoshuaSP)
Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results
Benchmarks & research openvons
openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド
Benchmarks & research jev-benchmarks
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
Benchmarks & research open-jev (daseinlabs)
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
Benchmarks & research jev-lm
A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval
Benchmarks & research decider
One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B
Benchmarks & research LegalForecastBench
LegalForecast-MTD benchmark alpha and official evaluation workflows
Benchmarks & research jev-korean-benchmark
Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence
Benchmarks & research jev-behavior-study
Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.
Benchmarks & research jevfire
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
Benchmarks & research openjev (zhihz)
Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
Benchmarks & research jev_stock
An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
Benchmarks & research jev-for-engineers
Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.
Benchmarks & research trade-jev
Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data
Benchmarks & research jev-little-airways
A show-and-tell capability study for Jev, TypeSafe's System One decision model.
Benchmarks & research kyotsu-ai-bench
AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard)
Benchmarks & research system-one-open
Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal)
Benchmarks & research decisionbridge
A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.
Benchmarks & research padflow-jev-evals
Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.
Benchmarks & research mcts-agent
Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini
Benchmarks & research jev-rerank-bench
Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.
Benchmarks & research jev-benchmark
Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs
Benchmarks & research jev-sec-bench
Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go
Benchmarks & research jev-playground (hegargarcia)
Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.
Benchmarks & research jev-as-a-judge
Using Jev as an evaluator.
Benchmarks & research jev-agent-failure-benchmark
Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).
Benchmarks & research jev-report
发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表
Benchmarks & research jevmlx
Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.
Benchmarks & research jev-research-eval
Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.
Benchmarks & research jev-exploration
Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code
Benchmarks & research jev-secret-detection
Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets
Benchmarks & research jev-phishing-bench
Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.
Benchmarks & research system-one-gemma
Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.
Benchmarks & research jev-routing-experiment
Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena
Benchmarks & research jev-jp-address
Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証
Benchmarks & research calibre
Calibration and confidence-based routing measured on Banking77: 80.2% accuracy at $0.103 per 500 decisions
Benchmarks & research openjev-experiments
Experiments with openjev, an open Jev-style option-logit runner, on local models.
Benchmarks & research shade-arena-jev-monitor
Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
Benchmarks & research thaiexam-jev-charts
Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models
Benchmarks & research jev-column-race
Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper
Benchmarks & research qwen-rlcd
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B
Benchmarks & research jev-trace-classifier
Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next
Benchmarks & research jevgpt
A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively)
Benchmarks & research jev-shadcn-lint-eval
A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.
Benchmarks & research jev-deferred-crispification
Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).
Benchmarks & research RISC-jeV
I tortured Jev into being a RISC-V CPU.
Benchmarks & research jev-finance-benchmark
typesafe.ai model jev finance benchmark
Benchmarks & research jev-pick-and-place-study
A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.
Benchmarks & research jev-spam-eval
Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines
Benchmarks & research jev-chat
A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.
Benchmarks & research jev-anotacao-sentencas
Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo
Benchmarks & research jev-synergy-screening
Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels
Benchmarks & research jev-lab
TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model
Benchmarks & research jev-headline-bench
Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.
Benchmarks & research jev-alpha-bench
Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall.
Benchmarks & research FinancialPredictionJev
Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good)
Benchmarks & research jev-freeform
An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice
Benchmarks & research Typesafe_chess_eval
An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.
Benchmarks & research system-one
Batched single-token choice inference for open language models, compatible with TypeSafe
Benchmarks & research typesafe-oracles
Evaluating TypeSafe's System One primitives (Choice/Score/Noul) — where a typed oracle beats an LLM call
Benchmarks & research system-one-adapter-rust
Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations)
Benchmarks & research PocketJev
On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits.
Benchmarks & research Parallel Constrained Decoding (Qwen2.5-1B-RLCD)
Hugging Face Space exploring open-source parallel constrained decoding as an alternative to Jev.
Benchmarks & research misereru-slide-jev
Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.
Benchmarks & research TypeAR
Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev.
Benchmarks & research jevlike
Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.
Benchmarks & research jevbetter
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.
Benchmarks & research jev-visual
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
Benchmarks & research reflex
A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.
Benchmarks & research mini-jev
mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.
Benchmarks & research openjev
Open, Jev-compatible System One decision server on DiffusionGemma
Benchmarks & research Jev_apps
看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.
Benchmarks & research typesafe-local
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.
Benchmarks & research daf-jev
daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill
Benchmarks & research jev-search-rerank-eval
Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.
Benchmarks & research Verdict-open-jev
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground
Benchmarks & research jev-harness
Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.
Benchmarks & research jevcal
Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.
Benchmarks & research jev-gate
Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.
Benchmarks & research open-alternative-jev
Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks
Benchmarks & research jev-curate
High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).
Benchmarks & research jevify
An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.
Benchmarks & research LitJev
A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.
Benchmarks & research jev_local
Replicating Jev with a local LLM
Benchmarks & research jev-capability-atlas
Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙語 repo。
Benchmarks & research von
The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
Benchmarks & research jev.nu
Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities
Benchmarks & research siftr
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
Benchmarks & research jev-mode
I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.
Benchmarks & research zerosweep
Autonomous System-One Triage Engine & Benchmark powered by TypeSafe AI (Jev). 75ms inference, $0 output tokens, and RLCD epistemic safety gates.
Benchmarks & research tenbin
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code
Benchmarks & research new-api-plugin-typesafe
TypeSafe AI System One (Jev) task plugin for QuantumNous/new-api — native /v1/systemone, synchronous evaluation, token billing
Benchmarks & research research_desk
TypeSafe Jev demonstration for new analyzation — experimenting with Jev for fast analysis of news and tickers
Benchmarks & research claude-jev
Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.
Benchmarks & research jev-align
Calibrated alignment verifier for LLM responses and agent plans — powered by Jev
Benchmarks & research jev-carryforward
What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.
Benchmarks & research jev-chess
Chess moves, evaluations, persona opponents, and game classification with TypeSafe AI System One
Benchmarks & research modelsystem
Curated catalog of System One / Decision Models — contributions for modelsystem.one
Benchmarks & research typesafe-vs-deepseek
TypeSafe (Jev) vs DeepSeek-flash: side-by-side speed/token/cost/accuracy comparison across invoice extraction, email classification, and reranking
Benchmarks & research openJev-verdict-2.0
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
Benchmarks & research jevbench
JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.
Benchmarks & research jev-studio
if you're experimenting with jev it will be easier from here
Benchmarks & research jsort
sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model
Benchmarks & research jev-rag-benchmark
Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG
Benchmarks & research jev-architect
Find, design, and evaluate TypeSafe Jev decision loops.
Benchmarks & research Augustus
Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.
Benchmarks & research jev-cli (shaharia-lab)
Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
Benchmarks & research Jev
Unofficial TypeSafe Jev showcase — System One decisions, not chat.
Benchmarks & research jevtest
Semantic test matchers for Vitest and Jest, powered by TypeSafe's Jev model. Write expectations in plain English, get calibrated probabilities back.
Benchmarks & research OpenJev
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
Benchmarks & research rh-guard
Reward-hack radar for coding agents: structural denies + TypeSafe Jev System One sidecar for Claude Code & Cursor hooks
Benchmarks & research jev-oas-sentinel
Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.
Benchmarks & research typesafe-chess (Dimesio)
FUn little experiment with Typesafe AI Jev Model playing chess against stockfish :)
Benchmarks & research toolgate (RiskAverseTech)
Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook
Benchmarks & research jev-search (larguesa)
Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.
Benchmarks & research ORIGIN-CIVILIZATION
AI life-and-civilization simulation: TypeSafe Jev makes every decision (typed, probabilistic, auditable); LLMs plan — OpenAI-compatible APIs, local models (Ollama, LM Studio), Claude Code, Codex.
Benchmarks & research jev-ood-calibration
Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.
Benchmarks & research jev-codes
Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill.
Benchmarks & research jev-starter
Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
Benchmarks & research OpenJev (GPT-AGI)
Jev-compatible System 开源Jev
Benchmarks & research jevchess
Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.
Benchmarks & research jev-labs
Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.
Benchmarks & research jevarena (chenmingtang830)
Open-source BYOK arena for Jev and other AI judges. Find failures, compare quality, cost, and latency.
Benchmarks & research jev-reward-model-evaluation
Jev 1.13 reward-model evaluation across 8 benchmark tracks, with an interactive report and 54-row SOTA comparison
Benchmarks & research jev-web-analyzer
See what Jev thinks about your SaaS website — powered by ReplyNodes web context and Vercel AI Gateway.