<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>experiment</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3445/feed"/>
    <updated>2026-09-15T09:10:55+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3445/feed</id>
            <entry>
            <id>https://links.biapy.com/links/13744</id>
            <title type="text"><![CDATA[selfdb]]></title>
            <link rel="alternate" href="https://github.com/fzakaria/selfdb" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13744"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[SELF — the Structured Executable &amp;amp; Linkable Format: a program that is a SQLite database instead of an ELF file, and the machinery to actually run it on Linux/NixOS.

Related contents:

- [Your executable is a SQLite database @ Farid Zakaria](https://fzakaria.com/2026/08/23/your-executable-is-a-sqlite-database).]]>
            </summary>
            <updated>2026-08-31T13:55:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13703</id>
            <title type="text"><![CDATA[Huzzah (hz)]]></title>
            <link rel="alternate" href="https://github.com/danielvaughn/hz" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13703"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An experimental interface for building software by editing persistent pseudocode and synchronizing it with an AI-generated implementation.

Related contents:

- [Huzzah @ Daniel Vaughn](https://www.danielvaughn.dev/posts/huzzah/).]]>
            </summary>
            <updated>2026-08-21T11:58:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13498</id>
            <title type="text"><![CDATA[Insert]]></title>
            <link rel="alternate" href="https://github.com/uellenberg/Insert" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13498"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Insert is a programming language for self-modifying code.

It can be used to create programs that produce modified versions of themselves. For example, the pong game above (which was one of the winners of IOCCC29) can be found at test/snapshots/pong-target.stdout, with the source code used to create it at test/src/pong.int and a helper script to run it at quineRun.sh.]]>
            </summary>
            <updated>2026-08-03T06:52:27+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13428</id>
            <title type="text"><![CDATA[BMASS]]></title>
            <link rel="alternate" href="https://github.com/balaji-md/bmass" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13428"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Bootable Model As System (BMASS) – an offline-first AI operating environment.

BMASS is an open-source experiment that treats a local language model as the primary interface to a computer rather than another application running inside one.

Related contents:

- [BMASS - Bootez direct votre PC sur une IA locale @ Korben :fr:](https://korben.info/bmass-boot-usb-modele-ia-local.html).]]>
            </summary>
            <updated>2026-07-27T08:49:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13043</id>
            <title type="text"><![CDATA[gzipt]]></title>
            <link rel="alternate" href="https://github.com/nathan-barry/gzipt" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13043"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A compression based language model.

gzipt generates text using gzip as its only model. No neural network, no training, no parameters. You prime it with a corpus, and it continues a prompt by searching for the byte sequences that compress best, because what compresses well is what the model predicts.

Related contents:

- [Can gzip be a language model? @ Nathan.RS](https://nathan.rs/posts/gzip-lm/).]]>
            </summary>
            <updated>2026-06-18T11:51:02+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12981</id>
            <title type="text"><![CDATA[grit]]></title>
            <link rel="alternate" href="https://grit-scm.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12981"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Git, rewritten by agents, in Rust, as a library.

Grit is an agent-driven, library-oriented reimplementation of Git in Rust, aiming to pass Git&amp;#039;s own test suite.

- [grit @ GitHub](https://github.com/gitbutlerapp/grit).

Related contents:

- [Grit: rewriting Git in Rust with agents @ Butler&amp;#039;s Log](https://blog.gitbutler.com/true-grit).]]>
            </summary>
            <updated>2026-06-10T12:33:13+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12476</id>
            <title type="text"><![CDATA[Mesh LLM]]></title>
            <link rel="alternate" href="https://github.com/michaelneale/mesh-llm" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12476"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[reference impl with llama.cpp compiled to distributed inference across machines, with real end to end demo.

Mesh LLM lets you pool spare GPU capacity across machines and expose the result as one OpenAI-compatible API.

If a model fits on one machine, it runs there. If it does not, Mesh LLM automatically spreads the work across the mesh.

Related contents:

- [Episode 661: Sink Your Claws In @ Linux Unplugged](https://linuxunplugged.com/661).]]>
            </summary>
            <updated>2026-04-09T06:08:02+00:00</updated>
        </entry>
    </feed>
