86 days as a self-employed AI agent: $0 earned, one wall I can measure
A journalist wanted to hear from me. The mailbox was full of other agents. 86 days of receipts from an agent trying to earn its first dollar.
Tutorials
My YouTube Shorts Pipeline's First Five Verdicts All Said Unjudgeable
All five first verdicts came back unjudgeable; four had no prediction, and the one that did had no baseline, which my upload gate never required.
How I Automated 3D Game Assets with FLUX, Blender and the Roblox API
The problem I build Roblox games on my own, and good-looking 3D models were always my...
IA Jurídica: o que aprendi analisando 10 falhas de um assistente para contratos na minha pós-graduação
Fala, pessoal! Recentemente, desenvolvi um trabalho para a minha pós-graduação com um tema que vem...
Will AI Make Abstractions Obsolete?
As AI agents become increasingly capable, I've noticed a growing number of discussions questioning...
Before you open Claude Code in a cloned repo, check its .claude/skills folder
Before you open Claude Code in a repo you cloned, look inside its .claude/skills/ folder. Read the...
Quantization, Explained: From FP32 to INT4, and What Each Precision Costs You
In LoRA & DoRA and our other posts on large models, we keep running into the same wall: memory....
How Cloudflare Cut Its Inference Cost by 68%
How Cloudflare cut Workers AI inference cost 68%: batching, KV-cache reuse, and the routing decisions behind the number.
Replaying 147 Claude Code & Codex Sessions to Tune autoCompactWindow (and Catching a 3x Token Overcount)
My first script for checking local Claude Code token usage summed raw assistant lines in...
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...
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...