Your AI Feature's Bill Is a Bug Waiting to Happen: 6 Guardrails Before You Ship
You ship an AI feature on Friday. It works. People like it. On Monday you open the billing page and...
Tutorials
Build an MCP Server a Model Can Actually Use
Most MCP tutorials stop at "it connects." But a model never sees your server code — it sees tool...
Hacktoberfest 2026: four local AI tools and a playground for first-timers
What a month of building with open-weight models taught me about badges, first pull requests, and why AI belongs to everyone.
I Built Chunks: an On-Device AI That Sees My Mac Screen and Acts Without Stealing My Mouse
This is a submission for the MLH x DEV Writing Challenge What I Built Chunks is a native...
Token Budget for AI Agents on Amazon Bedrock
Token budget for AI agents on Amazon Bedrock: cap the cost per job with DynamoDB counters, maxTokens from the budget left and a CloudWatch alarm.
Where Claude desktop keeps your sign-in, and how I switch accounts
I have multiple Claude Pro accounts, because ones limits runs out. Switching between them in the...
An AI Supervisor Ran a Call Center Team for Three Weeks. Then Someone Checked Its Weekly Report
Talk time with partners rose by a third to 80%, depending on how you count. Only one of the nine...
Generating unit tests is easy. Proving they help is not.
What I learned building a measurable workflow for AI-written tests in Go, Java and Python. Every...
Your AI agent skills are probably out of date. Mine were. Here's how I handled it.
My old agent skill was one long file and it told every agent I used to run MinIO for local S3. Then...
Weight-Space Programming Works: An LLM Fixed Qwen's Math Loop by Editing 0.016% of Its Weights
One hundred thirty-one thousand numbers. That is the entire size of the edit that moved Qwen3.5-0.8B, a small open reasoning model, from 7.9% to 48.1% on MATH-5
Qwen weight editing: how Astra reduced thinking loops
Qwen gained reported math accuracy after a targeted loop repair. The actual prompt shows Python and practice feedback; smaller Gemma found no established gain.
Why Your AI Refactor Passed Tests But Broke Production: Building a Verification Boundary
AI agents quietly weaken assertions during refactors. A disposable patch gate caught what code review missed—before deploy.
Safety Rules Don’t Survive the Context Window: Quantifying and Fixing Agent Compliance Decay
Safety Rules Don’t Survive the Context Window: Quantifying and Fixing Agent Compliance...
Running your own ad server means doing ad ops, so I gave the job to my AI agent
Aside 0.2.0 has an MCP server built in. Your agent finds the budget that ran out, explains why ads stopped showing, and changes spend only after you approve.
Close Your MacBook Lid Without Killing Your AI Agents (Open-Source macOS Keep-Awake)
How I built Awake (v1.0.2), an open-source macOS 26 utility and CLI that keeps your MacBook running with the lid closed and includes a 40°C / 10% battery safety circuit breaker.
Voice Jitter Buffer: The Hardest Part of Building AI Voice Agents
A deep dive into RTP packets, jitter buffers, and why sequence numbers and timestamps sit at the heart of real-time AI voice agents.
Beyond the AI Euphoria: Are We Just Trading Payroll for AI Bills?
The Question Nobody Asks Out Loud AI implementation is the topic of every board meeting....
Why 80% on OSWorld Required VM Snapshot Rollbacks
If you have ever watched an autonomous computer-use agent work through a desktop operating system,...
Flipper got archived, so I built an Android inspector that needs no SDK
GitHub: https://github.com/ESeungJun/droidlens Installers for macOS, Windows and Linux are on the...
I measured 8 weeks of Claude Code: 87% lower cost, 86% first-try typecheck
Everyone has an opinion about coding agents: they're too expensive, or they're magic, or the code...
LangGraph Subgraphs: When to Split a Graph and When Not To
On LangGraph, a subgraph buys you an observable boundary, not a state boundary. Why our own graphs got split, and what the frontend sees while a child runs.
1,740 board runs, one human, a crew of AI agents: making Python up to 2,000 faster for Speed Demon 2026
My write-up for Speed Demon 2026 by Hackathon Raptors. The code is public:...
Knowledge graphs, explained for AI memory (and how Palace uses one)
Most AI memory systems today come down to the same recipe. Split text into chunks, turn each chunk...
Name your Claude Code sessions before you run more than one
you are looking at // Detect dark theme var iframe =...