Browse builds

Benchmark of Jev as a malicious agent-skill detector on MalSkillBench with verify-and-escalate evaluation.

Reproducible experiments on Jev probability calibration, uncertainty, and forecast preservation.

Agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.

Research notes and an interactive Cloudflare Worker demo for Jev, TypeSafe AI's structured decision model

Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG.

Reproducible evaluation of Jev Choice decisions on 182 valid ENEM 2025 questions, with raw results, accuracy, calibration, and latency analysis.

Python library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and DataFrame workflows.

Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.

Adversarial Jev evaluation suite with preregistered predictions, request logs, and reproducible experiment artifacts.

TypeSafe's Jev vs gpt-5.4-mini and gpt-5.6-luna on four public classification sets: cases, per-item answers, scoring, charts

Independent benchmark data for TypeSafe's Jev (System One model) vs LLMs: accuracy, calibration, cost. Boards + per-decision logs, CC-BY-4.0

Research workspace containing reproducible TypeSafe Jev evaluation and safety-judgment experiments.

Reproducible evaluation of Jev calibration on synthetic support tickets and public classification benchmarks.

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.

Systematic-review extraction app where Jev answers structured review forms and points reviewers to quoted source lines.

Selects source-linked evidence within a token budget using Jev relevance judgments plus local diversity-aware selection.

Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.

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.

TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.

Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.

AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.

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.

Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification.

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).

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.

Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.

Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.

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.

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.