Home

The article reports on a forensic investigation by Forensic Architecture into an incident in Tel Sultan, Gaza, where Israeli soldiers allegedly killed civilians and obstructed the Red Crescent and civil defense responders. The investigation examines the evidence and timeline of the events using audio-visual data and witness testimonies.

The article discusses a breach at Persona, a Discord-backed identity verification startup co-founded by Peter Thiel. The breach exposed user data and raised concerns about the security practices of the company.

The article explores the creation of a simple dog-walking game, detailing the development process, design choices, and the lessons learned along the way. It provides insights into the technical aspects of game development, emphasizing the importance of iterative design and user feedback.

The article explores the concept of tackling large tasks one step at a time, using the construction of the Hoover Dam as an example. It highlights the benefits of breaking down complex projects into manageable pieces and the importance of consistent, incremental progress to achieve ambitious goals.

The article discusses the introduction of the 'setHTML' method in Firefox 148, which provides stronger cross-site scripting (XSS) protection compared to the traditional 'innerHTML' approach. This change aims to improve the security of web applications by limiting the potential for XSS vulnerabilities.

This open letter from the 'Keep Android Open' initiative urges Google to maintain the openness and freedom of the Android ecosystem, advocating for continued support for third-party app stores and user freedom to choose their own software and services on Android devices.

The article discusses Japan's plans to promote the use of electric vehicles (EVs) and hydrogen-powered vehicles as part of its efforts to achieve carbon neutrality by 2050. The government aims to increase the number of EVs and fuel cell vehicles on the road and provide more charging and hydrogen fueling infrastructure to support this transition.

The article describes the development of a mobile application called YJ Nearby Glasses, which helps users find nearby eyeglasses stores and compare prices. The app leverages location data and price information to provide users with a convenient way to shop for glasses in their local area.

The article introduces the Hugging Face Skills project, which aims to facilitate the development and deployment of machine learning models for a wide range of tasks, including natural language processing, computer vision, and reinforcement learning. The project provides a unified interface and tooling to make it easier for developers to work with different AI models and deploy them in production environments.

Hey HN! We’re Arne and Raban, the founders of Emdash (https://github.com/generalaction/emdash).

Emdash is an open-source and provider-agnostic desktop app that lets you run multiple coding agents in parallel, each isolated in its own git worktree, either locally or over SSH on a remote machine. We call it an Agentic Development Environment (ADE).

You can see a 1 minute demo here: https://youtu.be/X31nK-zlzKo

We are building Emdash for ourselves. While working on a cap-table management application (think Stripe Atlas + Pulley), we found our development workflow to be messy: lots of terminals, lots of branches, and too much time spent waiting on Codex.

Emdash puts the terminal at the center and makes it easy to run multiple agents at once. Each agent runs as a task in its own git worktree. You can start one or a few agents on the same problem, test, and review.

Emdash works over SSH so you can run agents where your code lives and keep the parallel workflow. You can assign tickets to agents, edit files manually, and review changes.

We also spent time making task startup fast. Each task can be created in a worktree, and creating worktrees on demand was taking 5s+ in some cases. We now keep a small reserve of worktrees in the background and let a new task claim one instantly. That brought task start time down to ~500–1000ms depending on the provider. We also spawn the shell directly and avoid loading the shell environments on startup.

We believe using the providers’ native CLIs is the right approach. It gives you the full capabilities of each agent, always. If a provider starts supporting plan mode, we don't have to add that first.

We support 21 coding agent CLIs today, including Claude Code, Codex, Gemini, Droid, Amp, Codebuff, and more. We auto-detect what you have installed and we’re provider-agnostic by design. If there’s a provider you want that we don’t support yet, we can add it. We believe that in the future, some agents will be better suited for task X and others for task Y. Codex, Claude Code, and Gemini all have fans. We want to be agnostic and enable individuals and teams to freely switch between them.

Beyond orchestration, we try to pull most of the development loop into Emdash. You can review diffs, commit, open PRs, see CI/CD checks, and merge directly from Emdash once checks pass. When starting a task, you can pass issues from Linear, GitHub, and Jira to an agent. We also support convenience variables and lifecycle scripts so it’s easy to allocate ports and test changes.

Emdash is fully open-source and MIT-licensed.

Download for macOS, Linux or Windows (as of yesterday !), or install via Homebrew: brew install --cask emdash.

We’d love your feedback. How does your coding agent development setup look like, especially when working with multiple agents? We would want to learn more about it. Check out our repository here: https://github.com/generalaction/emdash

We’ll be around in the comments — thanks!

The decimal-java project is an open-source Java library that provides a high-precision decimal data type for use in financial and scientific applications where precise calculations are required, addressing the limitations of the built-in Java BigDecimal class.

Macky.dev is a personal website and blog run by Macky, a software engineer. The site covers a variety of topics related to software development, including programming languages, tools, and best practices.

SQLite has six layers: SQL parser → query planner → VDBE → B-tree → pager → OS. (https://sqlite.org/arch.html) For key-value workloads you only need the bottom three.

SNKV cuts the top three layers and talks directly to SQLite's B-tree engine. No SQL strings. No query planner. No VM. Just put/get/delete on the same storage core that powers SQLite.

Python:

    pip install snkv

    from snkv import KVStore

    with KVStore("mydb.db") as db:
        db["hello"] = "world"
        print(db["hello"])   # b"world"

    #define SNKV_IMPLEMENTATION
    #include "snkv.h"

    KVStore *db;
    kvstore_open("mydb.db", &db, KVSTORE_JOURNAL_WAL);
    kvstore_put(db, "key", 3, "value", 5);

  Sequential writes  +57%
  Random reads       +68%
  Sequential scan    +90%
  Random updates     +72%
  Random deletes    +104%
  Exists checks      +75%
  Mixed workload     +84%
  Bulk insert        +10%

What you get: ACID, WAL concurrency, column families, crash safety — with less overhead for read-heavy KV workloads.

The article explores the idea of training a human in the same way that AI models are trained, with the goal of enhancing human capabilities and potentially creating a new class of 'enhanced' humans. It delves into the ethical and practical implications of such a concept, raising questions about the limits of human augmentation and the potential societal impact.

The article discusses the current state of AI and explores the potential of AI functions, highlighting their ability to automate various software development tasks and streamline the software development process.

The article discusses the creation of a website that allows users to explore the history of GitHub, including its founding, growth, and key milestones. The website provides a comprehensive timeline and interactive features to help users understand the evolution of this influential software development platform.

Pixi.GUI is a new open-source UI library for the Pixi.js framework, providing developers with a simple and flexible way to create user interfaces for their Pixi.js-based web applications and games. The library offers a range of customizable UI components and tools to help streamline the development process.

Hey HN, I fine-tuned a small open-source model on golf forecasting and it beats GPT-5 at predicting golf outcomes. The same approach can be used to build a specialized model in any domain, you just need to update a few search queries.

We fine-tuned gpt-oss-120b with LoRA on 3,178 golf forecasting questions, using GRPO with Brier score as the reward.

Our model outperformed GPT-5 on Brier Skill (17% vs 12.8%) and ECE (6% vs 10.6%) on 855 held-out questions.

How to try it: the model and dataset are open-source, with code, on Hugging Face.

How to build your own specialized model: Update the search queries and instructions in the Lightning Rod SDK to generate a new forecasting dataset, then run the same GRPO + LoRA recipe.

SDK link: https://github.com/lightning-rod-labs/lightningrod-python-sd... Dataset: https://huggingface.co/datasets/LightningRodLabs/GolfForecas... Model: https://huggingface.co/LightningRodLabs/Golf-Forecaster

Questions, feedback on the SDK, suggestions for new domains to try this on - all are welcome.

The article discusses the discovery of 53 missing pages from the Jeffrey Epstein files that were obtained by the Department of Justice but have not been explained by the government. The findings suggest a potential gap in the public record regarding Epstein's connections and activities.

I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos.

Just shipped a big update:

- Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package

Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.