No project description available.
Research and benchmarks — page 10
Benchmarks, papers and independent reproductions. Read these when you need to understand behaviour rather than adopt a library.
537 active projects in this collection. All collections →
No project description available.
Grounded information extraction that cannot hallucinate: code proposes spans, Jev decides. An open-source alternative to LangExtract, with a bilingual benchmark and paper.
Evaluate JEV robot control in MetaWorld and RoboTwin: discrete actions, hierarchical control, privilege-level ablations, and replay analysis.
Windows Forms playground for Jev System One — visualize and evaluate TypeSafe primitives (Choice, Score, Noul) with a 3-pane editor, preset builders, and simulated API evaluation.
Independent benchmark of TypeSafe's Jev against GPT-4.1-mini on 200 labelled enquiries. Finding: a calibrated confidence score tells you when to ask a human, not when to ask a bigger model.
Unofficial Jev-powered Zig terminal agent with deterministic policy gates and encrypted audit trails.
The asking side of Jev (TypeSafe System One: noul, choice, score) in Rust: client library, mjev CLI, evaluation harness, and Jev reverse engineered from its docs. Talks to Intel-Phi-Jev.
Evaluate content for slop and guide revisions with 15 TypeSafe Jev scores. Not an AI-authorship detector.
Serveur MCP pour piloter Firefox avec Claude : Jev (TypeSafe) choisit les clics, Claude planifie. Benchmark inclus.
1
Local retrieval without embeddings. Every answer comes back as the original passage with its coordinates (path:start-end), so a person or an agent can open the exact lines. No Embedding, Zero Cost, Fully Local.
An experiment: rebuilding a web page's accessibility tree in under a second with TypeSafe's Jev. Evals + a Chrome extension.
Find Amazon keyword ideas with Nexscope and evaluate their relevance to listing text with Jev.
Independent benchmark of TypeSafe Jev (System One) vs cheap and frontier LLMs: accuracy, calibration, latency, cost
No project description available.
1
JevApi — .NET tooling for the TypeSafe AI Jev model, which evaluates typed questions (noul/choice/score) against a state and returns structured answers with probabilities and confidence.
🎮 Play. Learn. Respawn. Turn LAYA & ModernBERT Decoder into tactical AI pilots in Cinder Station, an original Doom-inspired game. Explore RLCD + CE, TypeSafe Jev, interactive lessons & transparent benchmarks. Train locally or in Colab. Fork it. Train it. Play it.
Open, self-hostable, faster System One decision model — API-compatible alternative to TypeSafe's Jev
Can Jev infer whether a bet is worthwhile from its payout table, and do recent wins or losses sway that choice
Semantic feature flag evaluation for Cloudflare Workers using Jev and Flagship
1,000-decision behavioral benchmark of Jev across 25 deterministic reasoning families.
Semantic filtering for AI tool results. Native npm CLI, caller-controlled context, batching, and reproducible benchmarks.
Local benchmark comparing TypeSafe Jev and Laya-MLX for structured issue classification
1
A hypothetical reconstruction of Jev, TypeSafe's closed "System One" decision model, in the spirit of nanoGPT: the smallest working version of what black-box probing suggests. It reads a state and answers typed questions (yes/no, pick one, ordered score) with probabilities instead of generated text.