<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>jev</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3550/feed"/>
    <updated>2026-11-06T16:48:18+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3550/feed</id>
            <entry>
            <id>https://links.biapy.com/links/14137</id>
            <title type="text"><![CDATA[Jev]]></title>
            <link rel="alternate" href="https://typesafe.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14137"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Jev is TypeSafe’s flagship model and the first System One model. Send state and typed questions; get structured answers your code can use directly.

- [Jev documentation](https://docs.typesafe.ai/introduction).

Related contents:

- [Test-driving Jev on a security task: identity resolution @ Vincenzo Lozzo](https://vincenzoiozzo.com/blog/jev-identity-resolution).]]>
            </summary>
            <updated>2026-10-12T07:28:44+00:00</updated>
        </entry>
            <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>
            <entry>
            <id>https://links.biapy.com/links/14106</id>
            <title type="text"><![CDATA[jevgrep]]></title>
            <link rel="alternate" href="https://github.com/dzhng/jevgrep" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14106"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.]]>
            </summary>
            <updated>2026-10-05T13:29:58+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/14041</id>
            <title type="text"><![CDATA[Jeff]]></title>
            <link rel="alternate" href="https://github.com/firelex/jeff" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14041"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification.

Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification: small, fast decision models you slot into your code, with the same request format as Jev. You describe a situation and list the options in plain words; Jeff returns a calibrated probability for each option from a single forward pass. No generated text, no parsing: about 22 ms per decision on an RTX PRO 6000 and 28 ms on an Apple M4 Max (MLX).]]>
            </summary>
            <updated>2026-09-29T12:20:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/14035</id>
            <title type="text"><![CDATA[SemIf]]></title>
            <link rel="alternate" href="https://openjev.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14035"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Semantic If On-Device.
Decision model in your browser.

A local model can either read probabilities for your allowed options without decoding them, or write the same kind of distribution token by token. Pick a size, run both on your own GPU, and measure the difference.

- [SemIf @ GitHub](https://github.com/TheoLeeCJ/SemIf-OpenJev).]]>
            </summary>
            <updated>2026-09-28T12:09:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/14021</id>
            <title type="text"><![CDATA[Jevflake]]></title>
            <link rel="alternate" href="https://github.com/KranzL/Jevflake" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14021"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Ask TypeSafe&amp;#039;s Jev decision model questions about your data from inside Snowflake. dbt package plus a Terraform module.

Jevflake lets Snowflake ask questions about your data using Jev, the decision model from TypeSafe AI. It is a dbt package, with a Terraform module for teams that manage Snowflake that way.]]>
            </summary>
            <updated>2026-09-28T07:07:13+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/14018</id>
            <title type="text"><![CDATA[Supercov]]></title>
            <link rel="alternate" href="https://supercov.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/14018"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[coverage, security and code quality for coding agents.

Supercov tells your coding agent what to fix and what to test. It scores your code quality and flags security risks with Jev, runs the test command you already use, and turns uncovered paths into small, actionable queries. Your agent picks a target, writes a focused test or a focused refactor, proves what improved, and keeps going.

- [Supercov @ GitHub](https://github.com/supercorp-ai/supercov).]]>
            </summary>
            <updated>2026-09-28T07:00:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13989</id>
            <title type="text"><![CDATA[kev]]></title>
            <link rel="alternate" href="https://github.com/jaredpalmer/kev" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13989"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own.]]>
            </summary>
            <updated>2026-09-22T12:05:54+00:00</updated>
        </entry>
    </feed>
