Linus wrote Git in about 10 days, so I asked my local LLM to build something similar with one promptRich Edmonds writes that he tasked a local LLM with building a Git-like version control system from scratch to test the capabilities of home-based models. Using a 27B parameter Qwen model on a modest 20 GB VRAM setup, the system generated a working Python script named tinyvcs that handles core repository functions like initialization, commits, and history inspection. While the model identified and fixed several bugs on its own, it eventually required manual intervention to correct schema validation and symlink issues, producing a functional but basic proof of concept that lacks features like branching and remote management.
- The hardware utilized for this project is being used for a non-intended purpose, as consumer-grade GPUs are generally designed for gaming and graphics rendering rather than the heavy lifting required for local model inference.
- The LLM was strictly constrained to the Python standard library and had no internet access or ability to call external APIs.
- The resulting tinyvcs tool is comparable to an early prototype of Git, featuring content-addressed objects and SHA-based IDs but missing standard features like tags, remotes, and merging.
- The hardware utilized for this project is being used for a non-intended purpose, as consumer-grade GPUs are generally designed for gaming and graphics rendering rather than the heavy lifting required for local model inference.
- The LLM was strictly constrained to the Python standard library and had no internet access or ability to call external APIs.
- The resulting tinyvcs tool is comparable to an early prototype of Git, featuring content-addressed objects and SHA-based IDs but missing standard features like tags, remotes, and merging.
Waveshare's Thermal-Camera-ESP32-Module is a compact wireless infrared thermal imaging camera built on the ESP32-S3-WROOM-1 chip, featuring an 80x62 pixel microbolometer/thermopile sensor array with a 25 FPS refresh rate and a dual-mode 2.4 GHz WiFi/Bluetooth 5 LE connection. It offers two field-of-view options (45° basic and 90° wide angle), supports target temperatures from -40°C to 400°C with ±2°C accuracy, and includes a rechargeable lithium battery header, Type-C power connector, and 14 GPIO pins for expansion. The module can stream thermal images via a web interface or serial port, configured through an Android Bluetooth app or factory firmware flashing.
- NETD of 125mK provides reasonable thermal sensitivity for consumer and hobbyist applications
- The module supports both AP (hotspot) and STA (client) WiFi modes, with AP mode defaulting to 192.168.4.1:3333
- Emissivity considerations are important for accurate readings; the article explains gray body and selective radiator concepts
- Source code is provided for VS Code and ESP-IDF v5.4.1, enabling secondary development
- A third-party Node.js web interface project is linked for alternative display solutions
- NETD of 125mK provides reasonable thermal sensitivity for consumer and hobbyist applications
- The module supports both AP (hotspot) and STA (client) WiFi modes, with AP mode defaulting to 192.168.4.1:3333
- Emissivity considerations are important for accurate readings; the article explains gray body and selective radiator concepts
- Source code is provided for VS Code and ESP-IDF v5.4.1, enabling secondary development
- A third-party Node.js web interface project is linked for alternative display solutions
A single-file software-defined radio receiver that runs entirely in a Chromium-based browser via WebUSB, requiring no installation, no internet, and no admin rights—just an RTL-SDR stick, an antenna, and `index.html` on a USB drive. The project is designed for offline and remote use cases, such as field expeditions, emergency kits, and locked-down computers, supporting FM stereo with RDS, shortwave, airband, PMR446, and general coverage from 100 kHz to 1.766 MHz.
- Decodes weather fax, Morse code (auto speed detection), and RDS, with an "Identify" menu that optionally queries shortwave.live or a web search for the tuned frequency.
- Includes a Panorama feature that sweeps up to 10 MHz at once and stitches the slices together for a wideband view.
- Built using Jacobo Tarrío's `webrtlsdr` and `signals` libraries (from the original Google Radio Receiver Chrome app), bundled into one file with esbuild.
- The US National Weather Service proposed closing its five HF radiofax stations in late 2026.
- Demo mode is available without a stick by opening `index.html?demo`, which simulates stations including FM stereo with RDS, fading shortwave, SSB, Morse, and weather fax.
- Decodes weather fax, Morse code (auto speed detection), and RDS, with an "Identify" menu that optionally queries shortwave.live or a web search for the tuned frequency.
- Includes a Panorama feature that sweeps up to 10 MHz at once and stitches the slices together for a wideband view.
- Built using Jacobo Tarrío's `webrtlsdr` and `signals` libraries (from the original Google Radio Receiver Chrome app), bundled into one file with esbuild.
- The US National Weather Service proposed closing its five HF radiofax stations in late 2026.
- Demo mode is available without a stick by opening `index.html?demo`, which simulates stations including FM stereo with RDS, fading shortwave, SSB, Morse, and weather fax.
Richard Didd has released OFFgrid-SDR, a fully offline RTL-SDR receiver that runs in a single HTML file without requiring any installation or internet access. The program utilizes WebUSB in modern browsers to demodulate various signal types and display spectrum and waterfall data, while also including built-in decoders for RDS, weather fax, and Morse code. Its primary advantage is portability, allowing users to store the application on a USB drive and run it on almost any machine with a compatible browser.
- Windows users must install WinUSB drivers via Zadig
- Linux users must blacklist DVB-T drivers
- macOS and Chromebook require no additional setup
- Project documentation is available on the developer's Hackaday.io page
- Windows users must install WinUSB drivers via Zadig
- Linux users must blacklist DVB-T drivers
- macOS and Chromebook require no additional setup
- Project documentation is available on the developer's Hackaday.io page
Valeria de Paiva writes that she was quoted in a new book by Simone Severini and Andrea Borghini, *Science, Ltd.: Notes on the Research Enterprise in the Age of Machines*, and reflects on the advice she gave in 2023. The central claim is that mathematical knowledge should not be reduced to formal systems alone; instead, the priority is extracting semantic meaning from natural-language texts before formalizing, because natural language is an extraordinarily successful technology that humans have developed over hundreds of thousands of years and is unlikely to be rendered obsolete by proof assistants or language models. She advocates building bridges between informal and formal mathematics through a "Network Mathematics" knowledge graph that connects concepts, theorems, papers, and formal statements across the different ways mathematics exists.
- Her project Network Mathematics aims to represent mathematical knowledge as an extended knowledge graph rather than a pile of documents or a single formal library
- MathGloss attempts to align mathematical concepts across resources written for humans and those intended for machines
- She acknowledges she underestimated the age of natural language, saying "thousands of years" when fully developed human language likely dates back at least 100,000 years
- Her project Network Mathematics aims to represent mathematical knowledge as an extended knowledge graph rather than a pile of documents or a single formal library
- MathGloss attempts to align mathematical concepts across resources written for humans and those intended for machines
- She acknowledges she underestimated the age of natural language, saying "thousands of years" when fully developed human language likely dates back at least 100,000 years
Bobby Jack writes that open-source terminal tools now enable Linux users to edit, analyze, and manage spreadsheet data without relying on GUI applications like LibreOffice Calc. The article highlights five distinct utilities—Sheets, excelchop, xleak, VisiData, and Vex—each tailored for specific tasks ranging from quick data extraction to full-featured visual data analysis and file editing.
- Vex is recommended as the best option for making edits to Excel spreadsheets directly from the terminal.
- xleak is the only tool on the list that supports the older proprietary XLS file format.
- excelchop supports the XLSX format but does not support the XLS format.
- Vex is recommended as the best option for making edits to Excel spreadsheets directly from the terminal.
- xleak is the only tool on the list that supports the older proprietary XLS file format.
- excelchop supports the XLSX format but does not support the XLS format.
Hallmark is a design skill for Claude Code, Cursor, and Codex that prevents LLM-generated UIs from looking like typical AI output. It selects a macrostructure for a given brief, dresses it in one of twenty-one themes, and runs a suite of slop-test gates and a pre-emit self-critique to refuse on-distribution defaults. Different briefs produce fundamentally different shapes and structures rather than colour-swaps of a single template.
- Includes a `study` verb that extracts design DNA from a screenshot or URL
- Offers a Custom route that designs from first principles when no catalogue theme fits the brief
- Includes a `study` verb that extracts design DNA from a screenshot or URL
- Offers a Custom route that designs from first principles when no catalogue theme fits the brief
Nolen Jonker writes that consolidating multiple LLMs into a single open-source client, Cherry Studio, allows users to compare outputs, manage privacy, and control costs more effectively than using separate vendor subscriptions. The tool acts as a unified workspace where API-based cloud models and local instances can be queried simultaneously, letting users route sensitive data to private local systems while utilizing specialized cloud models for complex tasks.
- Cherry Studio supports simultaneous multi-model responses, enabling side-by-side comparisons and acting as a basic hallucination check.
- For most users, pay-per-token APIs are cheaper than flat-rate premium subscriptions unless they use high-end models for extended periods daily.
- Providers like Anthropic and OpenAI do not train on API inputs or outputs by default, offering better privacy than their respective standard consumer apps.
- Alternatives include self-hosted options like LibreChat and Open WebUI, or simpler desktop clients like AnythingLLM and Jan.
- Cherry Studio supports simultaneous multi-model responses, enabling side-by-side comparisons and acting as a basic hallucination check.
- For most users, pay-per-token APIs are cheaper than flat-rate premium subscriptions unless they use high-end models for extended periods daily.
- Providers like Anthropic and OpenAI do not train on API inputs or outputs by default, offering better privacy than their respective standard consumer apps.
- Alternatives include self-hosted options like LibreChat and Open WebUI, or simpler desktop clients like AnythingLLM and Jan.
Telepath's Television project describes a GUI layer that gives people and their personal agents a shared visual space for creating and working with persistent, malleable, interactive artifacts. It connects a lightweight server on the agent's machine, a skills bundle that teaches the agent how to create and modify artifacts, and a client app, either a macOS Electron app or a browser-based interface. The page emphasizes that Television works with any agent harness and model, and that it is currently a newly public, MIT-licensed repository with a small contributor base.
- Agents are recommended from specific harnesses such as Hermes, OpenClaw, Pi, Claude Code, or Codex.
- macOS is the primary supported path via an Electron app; Linux or macOS is required for the agent side, and Windows agents are not supported.
- The repo uses a spec-driven development process that is not yet open to outside contributors.
- It is built mostly in TypeScript, with JavaScript, CSS, HTML, and a little Python and Shell.
- Agents are recommended from specific harnesses such as Hermes, OpenClaw, Pi, Claude Code, or Codex.
- macOS is the primary supported path via an Electron app; Linux or macOS is required for the agent side, and Windows agents are not supported.
- The repo uses a spec-driven development process that is not yet open to outside contributors.
- It is built mostly in TypeScript, with JavaScript, CSS, HTML, and a little Python and Shell.
Joseph Dolivo and Igor Fil write about Pizza Bot, an open source application that runs background AI agents and provides an email-like inbox for their outputs. The design pattern moves agent interaction away from live chat sessions toward asynchronous threads, allowing users to delegate tasks that require multiple steps or human approval without having to monitor a terminal in real time. Because it is fully self-hosted and supports local models, it allows users to maintain strict data boundaries while utilizing tools they already own through MCP servers and agent skills.
- The architecture is built on DeepAgents and LangGraph, using SQLite for local persistence and checkpointing.
- It features an "Action" queue specifically for tasks paused on human approval or decision-making.
- Cron schedules run once after a machine wakes from sleep rather than replaying every missed occurrence.
- The project name references Amazon's two-pizza team methodology.
- It currently ships with a browser-automation skill and a documentation guide skill.
- The architecture is built on DeepAgents and LangGraph, using SQLite for local persistence and checkpointing.
- It features an "Action" queue specifically for tasks paused on human approval or decision-making.
- Cron schedules run once after a machine wakes from sleep rather than replaying every missed occurrence.
- The project name references Amazon's two-pizza team methodology.
- It currently ships with a browser-automation skill and a documentation guide skill.
