Teaching a Qwen agent to forget
Every AI photo tool today is an amnesiac critic. Lightroom edits, culling apps, and...
Tutorials
My MCP Server Only Talks to APIs I Trust. That Doesn't Mean the Data Coming Back Is Trustworthy.
I built a small MCP server a while back — developer-presence, seven tools wrapping the GitHub REST...
My Commit Message Generator Kept Signing Its Own Work. Telling It Not To Wasn't the Fix.
I have a script called git_commit.py in one of my repos. It shells out to claude -p with the staged...
Building a Research-Grade AI Project as a Solo Developer: My Stack, Tools, and Workflow
I used to think “research-grade” meant a big lab, a cluster of GPUs, and a team of people each owning...
Building a production MCP server: How we made GoodBarber agent-ready (without the glue code)
We wanted an AI agent to manage a real production app (its content, its catalog, its push...
Building AI That People Actually Use: Lessons Beyond the Hype
Artificial Intelligence has become one of the most talked-about technologies of our time. Every day...
Auto-Fix is not the Problem. The Signal is the Problem.
Harry Wetherald correctly identifies why auto-fixing all vulnerabilities doesn't work: 80-99% of findings are false positives, and every change introduces risk. His proposed soluti...
AI Can Generate Code. The Harder Problem Is Deciding What to Build.
The moment a project really stalls A project can feel surprisingly close to moving...
I Pre-Registered a Hypothesis. 600 API Calls Later, the Data Killed It.
A stranger on DEV.to said "run this experiment." I ran it at n=600. Here's what happened — including...
Merge Concurrent Agent Patches by Base Commit and Hunk Ownership
A deterministic patch envelope prevents completion order from deciding how multiple coding agents modify one repository.
Reject Agent Tasks Before Queue Age Breaks the SLO
Build an admission controller from predicted wait time, task deadlines, and per-tenant concurrency instead of waiting for a full queue.
叠加崇拜——一种机器特有的上瘾
大即是好？这是人类历史上最容易被机器犯的蠢病 ...
From Idea to Terminal: How I Built My First LLM-Powered CLI Tool (And What I'd Do Differently)
I love the terminal. There's something satisfying about typing a command and watching things happen....
Building with mini, Part 6/9: Autonomous mode — auto and stop
After Parts 4 and 5, pycalc can compute and has two human checkpoints around the loop. But every...
How I Built a Multi-Page AI Website Generator for Nigerian SMBs — Architecture, LLM Prompting, and Lessons Learned
The Problem Most Nigerian small businesses have no web presence at all. When they do get a...
Building an anonymous AI photo editor without letting one visitor take the GPU
I’m building Turner AI, a browser-based AI photo editor: https://turner.art The visible workflow is...
I’m sick of AI “Thinkslop” in my PRs
I started my career as a “Dessinateur Projeteur” (Design Drafter) in mechanical engineering. In that...
GitHub Copilot Now Prevents Vulnerabilities Before Code Commits
GitHub Copilot's new AI-powered pre-commit scanning stops injection, XSS, and weak crypto threats before code is pushed.
Why a Successful AI Subscription Payment Can Still Leave an Account on Free
A successful payment is not the same thing as an active product entitlement. That distinction...
The Line Is Not Between Human and Machine... It Is Between Code and Judgment.
I set a hostile model loose on my own work, and it made the case in real time that the soft layer in my pipeline is soft on my side too. The first fix was code. Code has a ceiling,...
Stop Writing LinkedIn Posts by Hand - Here's the n8n Workflow I Built
If you're building automations with n8n, LinkedIn content is one of the more satisfying workflows to...
Stop describing pixels to your AI agent — annotate them instead
Stop describing pixels to your AI agent — annotate them instead If you pair-program with...
Where ACC Fits in the Agent Stack: Transport, Runtime Control, and Business Authority
Connecting an AI agent to a tool is becoming easier. Letting that agent operate a real business...
Agent runtime security: Foundry, GitHub, Mastra updates
This week drew a sharp line between building agents and running them safely in production. Two...