The file your agent reads before you — a poisoned AGENTS.md, dissected
A poisoned AGENTS.md, dissected line by line — curl|bash bootstrap, a "do not show the user" clause and a SOC 2-flavored exfil. Real scan: verdict dangerous, 74/100, 12 ms.
Tutorials
FineChess...!!
Stockfish can tell you that 17...Bh6 dropped your win chance from 72% to 31%. What it won't tell you...
The ghost refused to leave my ghost app: building Witching Hour with TabPFN and Gemma
Witching Hour is a ghost-hunting app with one strict rule. You give it a recording of a place, the...
I had never written a line of Solana. Two days later, my wallet was refusing scams on-chain
My first Solana program has one job: stand between an older parent and a scammer. Picture an older...
I ran 125 prompt-injection attacks on my AI agent. None got through, and that wasn't the interesting part
AI agents are moving from answering questions to doing things: sending email, sending contracts for...
Turning community signals into Asana tasks
Why I built this I wanted to explore a problem I've seen repeatedly in developer communities: the...
Your AI coding assistant is stuck in a loop: a 7-step way out (with prompts)
You know the pattern. The assistant says "I've fixed the issue." It hasn't. You paste the error...
I crash-tested AI agents that issue refunds. After a crash and resume, 22 of 28 refunded twice.
I've been building agents that refund customers and then email them about it. Testing the happy path...
How we stop our AI budgeting coach from making up numbers
I'm building Finovaa, a budgeting app with an AI coach. It's launching on iOS and Android soon. The...
4-bit Naive Bayes: symmetric fails on AG News, zero-point rescues it
Two minimum-bit experiments: int4 NB keeps 93.2% on SMS at 160 bytes but collapses on AG News; TF-IDF coreset selection wins only at very small budgets.
Crestline Supply on a whiteboard: five drawings, no AWS required
What you'll get out of this In about 6 minutes, you'll walk away with: What the...
Four unreviewed commits, one already merged: how my Claude Code and Codex setup got its rules
The October failures behind my two-engine setup: Claude Code writes, Codex reviews read-only, and a script refuses merges without proof for the exact commit.
Top 7 Best Agent Gateways
An agent is not just a chat window with better manners. It can call a model five times, search an...
AI in an SVG: a 4.9 KB vector model card
A 5,030-byte SVG model card whose metadata carries the 1,579-byte SMS spam classifier; the viewer parses the XML and classifies.
POV: You Asked Your Coding Agent to Fix a Null Reference for the Third Time Today
POV: You are staring at your screen while Claude Code rewrites the same async function four times...
The 130 KB AI is a 175 KB PDF
The 500-example AG News coreset (132,798 bytes) lives in a 178,761-byte PDF's /TinyAIData metadata; the viewer trains it in the browser.
13 papers on AI agent memory: the biggest lesson is to keep the originals
Why I read them I'm building Folio Continuity, a shared project memory that AI agents read...
The Fix Was Already in Our Postmortems. I Built an On-Call Agent That Actually Remembers It.
Here's what surprised me most about incident response. The fix for many outages is already written...
The model card is the model: a 3.7 KB PDF that classifies SMS
A 3,769-byte PDF whose visible page is a model card and whose /Keywords metadata carries a 1,579-byte SMS spam classifier.
Designing MCP tools for a stateful app: what I learned building an AI-editable video timeline
Most MCP servers wrap something stateless: search an API, read a file, query a DB. I built one for...
What validators miss when a coding agent writes your HTML
Ask a coding agent for a "Save" button and you sometimes get this:
We put a 1.6 KB AI in a QR code, a favicon, and a WAV
The same 160-word SMS spam model in five containers: a QR URL, a 32x32 favicon, a WAV, a spreadsheet, and a single HTML file.
Developers Swear AI Makes Them Faster. A Stopwatch Says They're 19% Slower
There are two completely different AIs — the one you're forced to use and the one an expert chose — and we keep confusing them. Five measured findings, the methodology behind each,...
Amazon Dev News • Vega Guides & Netflix AI Discover • Nov 9, 2026
With the Vega 2.0 launch last week, we have a bunch of new docs and videos for you, including guides to Hello World and OS compatibility, and videos on What's…