One word in a chat took my shop offline. I built it that way.
The word was go. A bot in the on-call room had just told me the deploy caused the outage. It quoted...
Tutorials
CallBook: a prediction you can't take back, remembered in Walrus and proven through Tatum
Everyone says they called it. Almost nobody can show they said it first. That is the problem...
Claude Agent SDK vs rolling your own tool loop: which one for your product?
Three ways to run a Claude agent: a hand-written loop on the Messages API, the Anthropic SDK's Tool Runner, and the Claude Agent SDK. Runnable TypeScript for each, measured token u...
Retrospective as a Dungeon Crawl: How the Team Went from Sticky Note Boards to a Pixel Tavern
While working on our project and going through N retrospectives, which, by the way, barely differed...
Congrats to the Kaggle Benchmarking Challenge Winners!
A few weeks ago we teamed up with Kaggle to ask a deceptively simple question: how do you actually...
Coding Agents Are Growing Memories. If You Can't git diff It, Don't Trust It
Codex 0.165 made memory v2 the default for fresh profiles; Claude Code's auto memory is on by default. Neither shows up in a PR. Agent rules belong in git.
The Pace Doesn't Ship
You finish the engagement on a Friday. The repo is clean, the pipeline is green, the agent guides in...
Prompt Pad: What Are Open-Weight Models?
When people call an AI model "open," they don't always mean the same thing. On this week's Prompt...
Threat-model an agent that can spend or sign
Map what a compromised prompt, model, or host lets an attacker sign or steal, then choose a control tier.
Linux local privilege escalation: OpenAI's 948 reported findings
OpenAI reports 948 local Linux escalation findings. Variant counting, human patch review and assigned-path checks explain what the research establishes.
Teaching a Machine to Say Namárië
In my very first Quenya post (so proud of myself!), I listed QuenyaTTS among the tools worth knowing:...
The Agent Fixed the Flaky Test by Inserting a Sleep
When an agent resolves a flaky CI test by inserting a sleep or a retry, the race is not fixed; it is hidden. Name the ordering dependency, reproduce it in a tight loop, and wait on...
Google Search Console’s November Click Spikes Look Like a Non-Human Traffic Anomaly
Multiple SEO practitioners reported unusual Google Search Console (GSC) click spikes between October...
Claude's IP Allowlist Can 403 a Leaked API Key. It Can 403 Your Weekly Cron Job Too
Anthropic's Nov 5 beta locks Claude API access to up to 1,000 IP ranges. It skips Bedrock and Google Cloud, and any job you forget to list gets a 403.
Requiem: a crash reporter that writes a eulogy for the program that died
This is a submission for the MLH x DEV Writing Challenge What I Built Every crash gets a...
One in five Claude Code skills runs a bundled script. We read what those scripts do
Before you install a Claude Code skill, open its folder and look for a scripts/ directory. If the...
Quanto custa executar uma tarefa com Agentes de IA
No primeiro post, contei como levei ao Startup Summit, em agosto, a palestra “Preço por token não é...
NVMe-oF vs Local SSD for Checkpoints: The Restart Bill
Disaggregated flash looks cheaper per terabyte until a job restarts and a hundred GPUs wait on a shared write path that was sized for steady state.
Sparse MoE vs Dense Scaling: The Routing Tax Nobody Budgets
Sparse expert models buy FLOPs back, then spend them on all-to-all traffic, expert imbalance and a batch size that never quite fills every expert.
OpenAI Expands Daybreak With Blue and Red for Authorized Cybersecurity Work
OpenAI has expanded Daybreak into two controlled-access tiers for authorized cybersecurity work:...
We read 891 public Claude Code mods before installing any. Here is what they can do
Before you install a Claude Code mod, run one command on its folder and read two lines: claude...
Five Agents Running, Fans Screaming: 8 Commands That Find the Process to Kill
Agents leave dev servers and test runners running after the turn ends. 8 macOS and Linux commands to find that process tree and kill only it.
Three models, no human reviewer: how we gate AI-written exam questions
I build practice exams for Dutch certification exams: workplace safety (VCA), the hospitality...
Claude Code Hooks: Automating Your AI Coding Workflow
Claude Code Hooks: A Complete Guide to Automating Your AI Coding Workflow If you've been...