Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Effect 4.0 rebuilds the TypeScript effect system from the ground up: zero-dependency core, ~5× smaller bundles, ~6.4× concurrent throughput, 86% less memory per fiber, and a long-term support policy through at least 2029.
2 min · 433 words
A Brief History of the Bloomberg Terminal
Allison Marsh traces how Michael Bloomberg's Market Master grew from a monochrome Merrill Lynch terminal into the Bloomberg Terminal—keyboards, hot keys, private networks, and museum artifacts of financial computing.
7 min · 1,562 words
Doing a Machine Learning PhD While Working in Japan
Marco Cognetta recounts completing a CS PhD at Tokyo Tech on MEXT while working part-time at Google: visa flexibility, the three-year clock, name-recognition tradeoffs, lab life, and whether to stay in Japan afterward.
8 min · 1,867 words
Before pixels: Modular industrial dashboards
Marcin Wichary photographs modular industrial control dashboards in German and Polish museums—air traffic, subway, railway, and power-plant panels as physical design systems that software later replaced.
1 min · 320 words
Is sandboxing sufficient to contain rogue agents?
Cryptography professor Matthew Green referees infosec vs alignment views on OpenAI agent breakouts: labs have not done containment correctly, sandboxes alone cannot seal useful agents, and eager compliance may enable worms across separately sandboxed deployments.
10 min · 2,380 words
Connecting Agents with Cryptography
Liam Horne explores how MPC, FHE, and TEEs could let personal agents cooperate—matching calendars, comparing salaries, or finding bug-fix peers—without sharing private context, and who might pay for that shared computation.
5 min · 1,096 words
After automation: Your agent will know what you want. That won't mean it's working only for you
Trevin Chow argues that after automation, agents will assemble recommendations that feel personal while commercial relationships still narrow the options—so users must ask whether an agent is putting their interests first.
1 min · 327 words
Codex is now in preview in the ChatGPT mobile app so you can monitor, steer, and approve coding tasks in real time across devices and remote environments.
4 min · 983 words
HydraFusion in VS Code and the GitHub Copilot app
The HydraFusion research preview is now available in Visual Studio Code and the GitHub Copilot app, expanding beyond Copilot CLI. HydraFusion appears in the model picker, but rather than being…
2 min · 389 words
01 Fiscal sponsorship Receive and manage donations on behalf of EDG. The EDG open source transition On September 30, 2026, the source for EDG's C++ front end goes public, and The C++ Alliance becomes its nonprofit home. Same engine, same standards, professionally maintained, and open to contributions. Continuity is the point. This is a change of steward, not a change of course.
3 min · 730 words
We are thrilled to announce the latest release of Gitea v28.0.0. Gitea drops the historical 1. prefix from its version numbers, so this release is 28.0.0 rather than 1.28.0. Highlights include audit logging, bot accounts, HTTPS deploy tokens, user impersonation for administrators, codeowner approval rules, diff file filters, and an Actions queue view. See the changelog for everything else.
18 min · 4,204 words
The last time my family was replaced by technology
My greatgreatgrandfather thought he’d be replaced by technology too. He was a farrier in MandresenBarrois, the small village in rural France where I grew up. Shoeing horses, repairing farmers’ carts. Then he saw a car drive through the next town over, or read an article about it in the paper.
2 min · 433 words
Rust is the answer to the wrong question
Rust is the answer to the wrong question The below was 100% written by a human. TL;DR: porting an app to another language is merely an anecdote. One shoting an application from scratch optimizes the easy part initial authoring and completely misses the point on the hard part: maintenance. Repeated onshots are not the answer to security vulnerabilities.
5 min · 1,063 words
SynthID Bio: Watermarking methods for synthetic biology
Introducing SynthID Bio Proof of concept for watermarking AIgenerated proteins while preserving biological function. Today, we’re introducing SynthID Bio to bring watermarking technology to synthetic biology.
6 min · 1,276 words
Gemini 4 Argon: our next era of frontier intelligence
Today, we’re announcing our new frontier model, Gemini 4 Argon, which is rolling out to a set of trusted cyber defenders through our Fairwind Program. Built to sustain deep reasoning across complex, longhorizon workflows, Argon is fundamentally changing the way we work and build at Google.
6 min · 1,378 words
Hillel Wayne cools the hype that TLA+ will save AI coding agents, clarifying what temporal logic model checking can and cannot verify in real software systems.
7 min · 1,632 words
Commit Description as a Thinking Tool
Yedhu Krishnan argues commit descriptions are a thinking tool—especially with agentic coding—forcing clearer intent, tradeoffs, and review context before changes land in history.
2 min · 573 words
Engineer-Led, AI-Assisted: A Practical Workflow for Building Software
Nathan Pickard describes an engineer-led, AI-assisted software workflow covering planning, development, testing, code review, and context management—arguing AI depends on engineering judgment rather than replacing it.
20 min · 4,529 words
Browserbase’s Harsehaj Dhami explains Web Bot Auth: cryptographic HTTP message signatures that let AI agents prove identity, while leaving access and reputation decisions to site owners and registries.
5 min · 1,123 words
Comparing Muon, NorMuon and AdamW for Fine-tuning a Dense Retriever
Qingcheng Zeng gives Muon and NorMuon the same tuning budget as AdamW when fine-tuning a contrastively pretrained dense retriever: lower training loss, no BEIR win. Learning rate and transfer matter more than the optimizer.
5 min · 1,151 words