<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>decision-engine</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3564/feed"/>
    <updated>2026-10-08T23:22:06+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3564/feed</id>
            <entry>
            <id>https://links.biapy.com/links/14116</id>
            <title type="text"><![CDATA[Laya]]></title>
            <link rel="alternate" href="https://huggingface.co/convaiinnovations/laya" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14116"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Multilingual, non-autoregressive System 1 decision model. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with mathematically calibrated probabilities in a single forward pass (~33 ms) across 100+ languages. Trained with reinforcement learning against strictly proper scoring rules (RLCD), so reporting honest probabilities is the only way to maximise reward. It never generates text, so there is nothing to parse and nothing to hallucinate.

- [Laya @ GitHub](https://github.com/NandhaKishorM/laya).

Related contents:

- [#142: News octobre 2026, Cloudflare Birthday Week, Shaders open source et pencils down @ Double Slash :fr:](https://double-slash.dev/podcasts/news-oct-26-rc1/).]]>
            </summary>
            <updated>2026-10-08T05:57:35+00:00</updated>
        </entry>
    </feed>
