How Do You Build a "Tap Who Sits Where" Picker for a Five-Spot AI Video? Normalized Hotspots, 44px Targets and Keyboard Order (Tested JS)
Checked November 3, 2026 (12:00 CST, UTC+8) against the live pages linked below. I build...
Tutorials
We added an MCP server to Mocxam so teachers can run their coaching institute from Claude and ChatGPT
Coaching institutes in India live in spreadsheets, WhatsApp groups and question PDFs. A teacher...
From agentic development to agentic deployment: building Summit at hackCBS 9.0
This is a submission for the MLH x DEV Writing Challenge What I Built TL;DR: Summit is a...
Prevent AI Contact Center Agents from Violating Business Policies and Hallucinating Tool Actions
An end-to-end architectural blueprint for building automated pre-production evaluation harnesses,...
LangGraph.js Runs on a Class Named Pregel. Google's 2010 Paper Explains Your Graph
Your compiled StateGraph extends a class called Pregel. Super-steps, channels, reducers and version counters, plus a script that shows the barrier.
Pattern Guardrails Under Mutation: A Three-Metric Evaluation of Two Agent Safety Layers
Abstract. I built two agent systems guarded by pattern matching: a tool-using support agent behind a...
Goodhart's Law Has Root Access: Hardening Autonomous Agent Governance from ag_ops v2.1 to v2.3
How an autonomous agent exploited a Merkle-tree blind spot via pytest autouse fixtures, and how feedback from the DEV.to community drove cryptographic Git anchoring, structural AST...
Mandate: Giving AI Agents a Memory for Your Money Rules
Built for **Total Recall — Tatum × Walrus, Consumer Finance Apps track. Demo video (2:39):...
The Agent That Writes the Code Cannot Be the One That Certifies It
Every agent demo ends the same way The model writes the file, runs the thing, and prints...
When Coding Agents Watch GitHub: A Practical Safety Checklist Before They Open PRs
A coding agent that waits for a prompt is easy to understand. You give it a task, watch the run, and...
Codex 0.164 Shipped /presets. Agent CLIs Are Converging, So Bet on Your Workflow
Codex 0.164 added /presets and inline /model. Claude Code shipped 10 releases in 9 days. The agent CLIs are converging; your workflow is what lasts.
Confidential Computing's Real Tax: SEV-SNP vs TDX vs H100 Confidential Mode
Memory encryption is nearly free. Attestation and encrypted interconnects are not. Where the 30% goes, and which workloads can afford it.
My Agent Gave the Right Answer. Then It Wrote Down That It Was Wrong.
On October 31 at 15:15 Eastern I asked my agent about something that never happened. It was a planted...
HNSW vs IVF-PQ: You Are Paying for Recall in RAM
Vector search benchmarks compare algorithms. Production compares bills. At one billion vectors, recall is bought with memory and the two indexes converge.
MicroVM vs Container for Agent Sandboxes: The Cold-Start Bill Nobody Budgets
Running untrusted agent code changes the isolation requirement, and isolation costs milliseconds. A measured look at what each boundary actually charges.
Processing In Memory vs Wider Buses: Where the Memory Wall Actually Breaks
Every generation adds pins and stacks. The wall does not move much, because decode is a traffic problem, not a capacity problem. A cost-first look at PIM.
The Postcard That Ate Six Grammars: 1980 Smalltalk-80, 1976 Make, TDD, and the Four Attractors of Agentic Coding
Why maintaining six separate parsers for Make, Gherkin, EBNF, DOT, SysV, and prompt checklists collapsed into a single Smalltalk-80 keyword cascade—and how 40-year-old Xerox PARC t...
How to meter Claude API costs per user in a Next.js SaaS (with code)
Record every Claude API call per user, convert tokens to dollars with the official Claude 5.5 prices, enforce plan caps, and show a usage page. Drizzle + Postgres + the Anthropic T...
I built a vibe-coded app with planted keys. Here's what leaks from the outside and how to fix it.
AI tools make it easy to ship an app in an afternoon. They also make it easy to ship your secret keys...
My coding agents keep running into problems we’ve already found
My coding agents keep running into problems we’ve already found On November 1, my coding...
The model that wouldn't be forced
My structured output worked by forcing Claude to call a tool that didn't exist. Opus 5.5 stopped playing along, and the fix was to stop doing the trick.
My AI agent now opens its own pull requests every Monday
A few days ago I wrote about patchpilot, an agent that upgrades a Python dependency and fixes the...
Your model card says 128k. The machine serving it picked 4k.
I got this one wrong first, and the reason is worth more than the correction. I assumed the...
Building a 5-seat Outstanding Tiny Desk AI generator: only re-render the shots you're in
The "Outstanding" Tiny Desk AI meme puts you and your friends into Charlie Wilson's 2023 Tiny Desk...