Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Drop: A rootless Linux sandbox with gVisor support
Drop is a rootless Linux sandbox aimed at isolating coding agents and third-party programs, with OS-level permissions, optional gVisor support, and a workflow that stays close to a normal shell.
1 min · 299 words
Waymo announces a Bay Area transit rewards program that pays Waymo Cash when riders connect autonomous trips with public transit using tap-to-pay Visa cards, starting with employees before a public rollout.
2 min · 562 words
PlayTaurus argues guitarists should buy hardware for what it is and run community firmware on it—ESP32-class chips are cheap enough, NAM models are open, and closed pedal firmware is the last proprietary lock.
2 min · 477 words
Managing the Hidden Overhead of AI Software Engineering
Jessica Doering on verification debt: AI coding tools move the bottleneck from typing to review, why opening another agent terminal feels productive, and habits that spend reclaimed time on specs, docs, and understanding.
3 min · 725 words
MiMo-V2.6: Scaling Up Reinforcement Learning for Self-Improvement
Xiaomi open-sources MiMo-V2.6 Pro and Flash after large-scale live RL (~$3.5M, 750k trajectories), claiming top open-weight AA Index scores, agent parity with frontier models, and 7k+ RL environments.
4 min · 839 words
Jev introduces a new shape of LLM—System One, aka Decision Models
Simon Willison reviews TypeSafe AI’s Jev: a cheap, fast decision model that returns calibrated floats for yes/no, choice, and score questions—and why black-box bias and evals matter more than for chat LLMs.
3 min · 796 words
Halo: Frontier-Lab Training for Everyone
White Circle open-sources Halo, a Hugging Face–native training framework claiming up to ~2.8× faster post-training than stock TRL with lower memory use—from single GPU to multi-node, keeping checkpoints in native HF format.
18 min · 4,098 words
Here’s What California Is Learning From Solar Panels Built Over Irrigation CanalsProject Nexus in Turlock tests canal-top solar for water savings, clean power, and water quality.
KQED’s report on California’s Project Nexus pilot: building solar arrays over working irrigation canals to generate power, cut evaporation, and study water-quality effects—early lessons from Turlock Irrigation District’s canal-top panels.
7 min · 1,680 words
A font that reads what you wrote
Rohan Adwankar introduces semfont: a small library that automatically highlights, colors, bolds, and italicizes text so typography tracks meaning as you write.
6 min · 1,295 words
EXPLAIN (ANALYZE, IO) in PostgreSQL 19
Franck Pachot walks through PostgreSQL 19's new EXPLAIN IO stats—prefetch depth, request size, concurrency, and waits—using Little's Law to interpret async read streams.
4 min · 1,031 words
NEC V20 CPU: A bit of pep for an XT
A deep dive into the NEC V20 CPU as a drop-in 8088 upgrade for IBM PC/XT-class machines—what it changes, how fast it feels, and why collectors still care.
11 min · 2,628 words
Helix: The internal tool powering our Shopify app's native migrationSmall checkpoints and strict quality gates so LLMs can rebuild Swift and Kotlin shippably.
Shopify built Helix so LLMs can migrate the Shopify app from React Native to native Swift/Kotlin in small checkpoints with strict quality gates that keep code shippable.
8 min · 1,799 words
Building Software That Can Prove Agents WrongWhat changes when implementation becomes cheaper than verification
Rafael Câmara argues that once coding agents implement faster than they can verify, the limiting factor is application design: software must expose cheap, independent evidence that can prove an agent's change wrong—not just look right on the happy path.
2 min · 486 words
Sending SMS with an Agentic AI using Twilio and Hermes Agent
Twilio posts cloud communications trends, customer stories, and tips for building scalable voice and SMS applications with Twilio's APIs.
9 min · 1,981 words
Three Days in August: What a DDoS Attack Exposed in Our Network
In August 2026, a large DDoS attack hit a customer and our own network directly. What happened, where our defences fell short, and what changed since then.
8 min · 1,730 words
Unsealed Briefs: OpenAI Execs Knew Mass Book Piracy Was Illegal
Authors Guild summary of newly unsealed filings in Authors Guild v. OpenAI/Microsoft: internal messages on LibGen, fear of Hacker News “optics,” Project Clear deletions, and executives’ awareness that models would replace writers.
1 min · 343 words
It was never about coding 📝 post "With the AI doing the coding, do we just spend all day reviewing its output?" The rapid onset of impressively capable coding agents continues to raise this question in conversations with peers, to [press interviews](https://blog.dyanacek.com/2026/03/12/coding after coders/), to [podcasts](https://blog.dyanacek.com/2026/07/01/code with jason with david/).
9 min · 1,971 words
AI: EU Member States plan “digital expropriation” of Europeans in the interest of AI companies
noyb reports on a leaked Irish Presidency document proposing that AI companies’ commercial interests should override fundamental rights protections for Europeans’ data.
6 min · 1,433 words
Reducing Image Generation cost with AMD and the Luminal Compiler
Luminal engineers show Flux.2 Klein 9B image generation costs cut by up to 47% on AMD MI300X versus an Nvidia H200, using the Luminal compiler.
15 min · 3,489 words
Textbook review: Is Parallel Programming Hard, And, If So, What Can You Do About It?
Andrew Helwer reviews McKenney’s parallel programming textbook: what it covers well, where it frustrates, and who should actually read it.
7 min · 1,715 words