Sep 14 to Sep 20, 2026

JevForm: a live tools & apps site by Tamir where Jev, TypeSafe AI's System One decision model, makes the structured judgments behind the product.

Postgres FTS, pgvector and RRF first stage; Jev, Voyage, GPT-4.1-mini, GPT-5.6-luna and open-weight Laya as rerankers on two Finnish legal corpora. Recall, MRR, nDCG, latency.

GGUF conversions of both the English and multilingual Laya checkpoints for llama.cpp-style local runtimes.

Will Sargent's stdio MCP server on fastmcp. Classify text, score against a rubric or answer yes/no from Claude Code or any MCP client without sending input off the machine.

Brain function collapse's live site where Laya plays Tetris, Flappy and a lane runner on a laptop, about 200x faster than a hosted LLM. Backed by the laya-playground repo.

The game enumerates placements with their holes, heights and clears; Laya picks one from text. The teacher is a board-evaluation formula, not Jev. Walkthrough video in Japanese.

Replayable grid sim with moving workers and forklifts. Laya answers action, collision_risk, path_blocked and needs_operator in one call; collision prevention stays deterministic.

Live at laya-web.pages.dev. 524 MB of quantized English weights cached in the tab, onnxruntime-web over WebAssembly, and a parity page checked against the PyTorch reference.

Browser runtime for Laya decisions on ONNX Runtime Web. WebGPU with SIMD Wasm fallback, Web Worker friendly, CPU embedding slicing to get past storage-buffer limits.

SwiftPM package ported from laya-coreml. Point it at the aac6fef Core ML bundles (general or ANE) and call predict with choice, score or noul; no Python at runtime.

TypeScript library where one set of question definitions serves a zero-dependency Promise client and an Effect service. Never invents a probability it was not given.

Seven zero-shot extraction and classification families demoed, benchmarked and cross-compared, with sizes, licences and costs in one table.

A frozen-protocol comparison of Jev 1.13, PrismNLI-0.4B and Laya with raw predictions, calibration and latency published. Laya ties Jev on the emotion dataset and trails it by 10 to 33 points elsewhere.

Ran Intel AutoRound W4A16 Flash-Next on four V620 cards for about three hours with an OMP harness, letting it test and fix a game itself in two browsers.

AI slop detector: a live content & growth site by Jon Kraayenbrink where Jev, TypeSafe AI's System One decision model, makes the structured judgments behind the product.

TypeSafe Typewriter: a live content & growth site by Steve Krouse where Jev, TypeSafe AI's System One decision model, makes the structured judgments behind the product.

Abhimanyu walks the Mahabharata ring formation to the centre. Each step goes to local Laya as typed questions; unsure or unplayable answers are marked red and corrected.

MLX port of Laya with performance work. Under 1 GB of memory on-device; the demo plays Snake at 60 decisions per second on an M3 Max.

A vision variant of Laya on Hugging Face: the same choice/score/noul question shape, with an image as the state.

A companion service for Lidarr that reads the manual-import queue, scores every candidate release and track in one pass with Laya, and picks the best match. Runs locally at no cost.

The Halogen engine author fixed slowdowns at deep context, raising decode at a million tokens from 27 to 38 tok/s on the same machine.

DiffJury: a live triage & routing site by Raihan Khan where Jev, TypeSafe AI's System One decision model, makes the structured judgments behind the product.

Askjev.ai: a live tools & apps site by Wayne Sutton where Jev, TypeSafe AI's System One decision model, makes the structured judgments behind the product.