Organic Search Is Shrinking, While Email Builds a More Durable Audience
Organic discovery is becoming a less dependable single source of website visits in the data examined...
Tutorials
Kill -9 an Agent Mid-Commit and .git/index.lock Outlives It. How Git's Locks Work
git commit -a holds .git/index.lock while your pre-commit hook runs. SIGKILL the agent then and the lock stays. Plus the locks every worktree shares.
I built a Snap Specs Lens so new mail carriers can learn their case from memory
My mom has worked at the post office for over 30 years, so when I picked a project for Devpost's...
I ran a pre-launch audit on a deliberately broken vibe-coded app. Here are 10 findings and the prompt that fixes each one
Disclosure: I built LaunchVet, the tool I use in this article. The free core is MIT licensed. Every...
AI-Assisted Terraform Security Reviews with Azure DevOps and GitHub Copilot
Adding a security scanner to a pipeline gives us findings. The next task is deciding what those...
Walmart’s Agent Profiles Signal a More Governed Web for AI Agents
Walmart’s new approach to AI agents points to a consequential change in how automated assistants may...
I let a prompt injection into my own app's clinical notes. The model ignored it. The fallback didn't.
I hid 30 prompt injections inside a patient's clinical notes. The model didn't follow a single one....
I built a tiny GPT from scratch to show my kids how chatbots really work
What actually happens inside a GPT? Everyone talks about "attention" and "transformers" and...
Your Documentation Is Out of Date. Let an AI Agent Keep It in Sync
We've all been there. You join a new team, open the repository, and find a beautifully written...
git stash Is Shared Across Worktrees. Two Parallel Agents Popped Each Other's Work
refs/stash lives in the shared .git, so a stash made in one worktree can be popped from any other. A demo, the sharing rules, and safer agent patterns.
Join the Presage SmartSpectra SDK Challenge: $3,000 in Prizes Across 10 Winners!
We're excited to announce our newest challenge with Presage! The Presage SmartSpectra SDK Challenge...
Redpanda vs Apache Kafka: C++ Thread-per-Core Architecture vs JVM Zero-Copy PageCache
Redpanda vs Apache Kafka: C++ Thread-per-Core Architecture vs JVM Zero-Copy PageCache ...
Google AI Mode Adds Booking and Quote Links for Home Services
Google has expanded AI Mode in Search to surface direct booking and quote links for home services in...
What an Urdu sentence costs in tokens
Here are two sentences that mean exactly the same thing: The government announced a new policy on...
Garuda against Claude Code, with intervals
Garuda is an open-source coding agent for the terminal that I build to learn how coding agents work....
One MP4, 27 Runs, 15 Different Transcripts. Lower-Case Them and 26 Are the Same 213 Words
A scheduled check has been transcribing the same 60-second video every day for a month. The word counts came back as 211, 213, 214, 215 and 216 — and not one word was misheard in 2...
Code Review Was Never Mostly About Bugs. With Agents, It's How You Learn Your Own Code
Microsoft found only 14% of review comments flagged defects. When an agent writes the diff, review is the one moment a human learns the code.
"Trace Shape Reveals Model Capability: 3B vs 7B"
Trace Shape Reveals Model Capability: 3B vs 7B Last week I traced the same agent running...
Everyone has better models. Why do some teams fly while others don't?
Models got dramatically better over the past year. But they got better for everyone. In that time, our team went from 5.3 to 13.7 PRs per person per month, and I personally went fr...
I built a prompt library where every prompt shows its result first
Every AI trend comes with a prompt. A sherwani portrait, 3D balloon letters, a pet dancing next to a...
Why Row-Level Security Is the Safest Place for Authorization in AI-Built Apps
Originally published on mihai.ltd. How many times has an AI coding agent written a feature that...
O agente que escreve o código não pode ser o que o certifica
Toda demo de agente termina em 'pronto' sem prova. Gate cego faz o 'pronto' valer alguma coisa: o artefato é validado fora do alcance de quem construiu.
Are AI Companies Deliberately Teaching Us to Spend More Tokens?
Anthropic published a guide last month, Building agents: When to fold subagents into your main agent...
Journey before destination
Journey Before Destination I got into software engineering because I enjoyed it. I enjoyed the...