by jayeshvpatil
Compares Jev, Claude, fine-tuned Qwen, and open Laya in experiments on agent shell-command risk gates
Can a non-generative 'System One' model safely gate an AI agent's shell commands? Four experiments comparing Jev, Claude, a fine-tuned Qwen, and open Laya.
Platforms
Related projects
laya
NandhaKishorM
Runs multilingual typed-decision models and provides routing, serving, and integration options
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya
convaiinnovations
A multilingual-ready System 1 model that returns calibrated typed decisions over text in one pass
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
typesafe-mcp
itsmostafa
Connects AI agents to typed-decision models through an MCP server
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya