An Open Letter to Anthropic Founders: The Training Data Paradox and AI’s Arbitrary Borders
I rely on Claude Pro daily for professional engineering and backend development. On October 20,...
Tutorials
Two Months, Five People: Building the Backend Behind Foodmartex’s Next Chapter
Over the past two months, our five-person team at Foodmartex has built catalogue-grounded AI...
The KV Cache From Scratch
In every part of this series, one thing kept showing up: the notebook. In Part 1 it grew by 72 KB...
WebMCP vs MCP vs browser-use: which agents should call (2026)
WebMCP vs MCP vs browser-use in 2026: Chrome's page tools, durable MCP servers, and DOM actuation. When to use each layer, with primary sources checked 4 November.
Weight-Space Programming: how GPT-6 Astra edited Qwen's weights and took MATH-500 from 7.9% to 48.1%
MIT CSAIL's weight-space programming: GPT-6 Astra edited 0.016% of Qwen3.5-0.8B's weights with no gradients and lifted MATH-500 from 7.9% to 48.1%. How it works.
Did Someone Repost My Malfoid AI Portrait? Finding Crops, Flips and Screenshots With Perceptual Hashes (Python, Tested)
You made a Malfoid (Female Malfoy / Fem Draco) portrait, posted it, and a week later a picture that...
How a GPT-5.4 harness scored above GPT-6 Astra and Claude Code on ExtractBench
On LlamaIndex ExtractBench (370 documents, 4,869 pages), my open-source harness KYNEX scores 92.97...
Your Agent Logs What It Did. It Has No Record of What It Meant To Do.
@allenheltondev published a post yesterday called What the heck do I alert on anymore?. He runs an AI...
My PR demo videos make themselves now, in my voice
How I built a free pipeline that runs on my MacBook: it films the real app, narrates in a clone of my...
Supabase service-role key exposed in the browser
The service-role key skips every Row Level Security rule. Used in browser code, it's handed to every...
DeepSeek Harness Creator Mode: When the Agent Builds Its Own Plugins — and Why That Needs Guardrails
On 2 November 2026, DeepSeek's Harness team announced Creator Mode for DeepSeek Harness, its...
Filtering After Retrieval Leaks Your Documents. Put the ACL Inside the Query.
In permission-aware RAG, filtering documents after retrieval is a data leak; the access-control predicate belongs inside the retrieval query itself.
AI Agent OAuth Recovery: Stop Expired Connections From Retrying Forever
Build a reliable OAuth recovery flow for AI agents with connection states, refresh locking, safe reauthorization, and resumable runs.
My linter reported 700 problems. Almost all of them were wrong.
AI coding agents read your AGENTS.md or CLAUDE.md on every request. Those files rot like any other...
Signal #127: Raycast Gets Leaner, Vercel Starts Charging for Memory, and Biome Crosses 500 Rules
This week's tooling news is a mix of quiet performance work and forced decisions. Raycast isolated...
Before you install that agent skill, vet it: building a checker that only blocks on proof
Installing an agent skill is an act of trust. A pack — a SKILL.md plus whatever scripts and...
I Put a Local 7B Model Inside SSMS 21 & 22 (No Cloud, No API Keys)
TL;DR: I built a free, open-source SSMS 21 & 22 extension that plugs a locally-hosted 7B model...
ChessMaster: Building a Personal Chess Coach on Stockfish and Claude
ChessMaster transforms raw game data into actionable coaching insights. Chess.com and Lichess show...
A Read-Only Reviewer Subagent in Claude Code: 3 Tools, Haiku 5.5, a 100K Compact Window
A Claude Code reviewer that can only Read, Grep and Glob, runs on Haiku 5.5 with a 100K compact window and shows up in your status line. Step by step.
How the Strands Agent Loop Actually Works
Starting from the smallest agent that runs and ending in the source where the loop turns out to be a recursion.
My Rust target/ said 325 GB. My disk said 1.65 GB free.
so last week my Mac said the disk was full. like, actually full. 1.65 GB left out of 494 GB. I ran...
When Cursor's MCP Connection Drops Mid-Workflow and the Agent Retries Blind
Quick guidance on when cursor's mcp connection drops mid-workflow and the agent retries blind.
The Gate Held, the Draft Leaked: A Three-Metric Evaluation of a Support Agent's Safety Layers
The Gate Held, the Draft Leaked: A Three-Metric Evaluation of a Support Agent's Safety...
Claude Certified Architect Professional: CCAR-P Exam Guide
CCAR-P exam guide: 63 questions, seven domains, the $175 fee and differences from Foundations. A study plan and three original questions with explanations.