AI Tutorials & Practice

Bedrock and LangChain disagree on what input_tokens means — never price it without knowing who counted

Meta Muse and MCP Security: When Trusted AI Tools Become the Attack Surface

MCP Servers Are a New Attack Surface, and Most Teams Are Not Looking

A PSD carries Photoshop's answer key. The UI has none.

Elsewhere: Don't Remind Me. Give Me a Reason.

I Built a World With Rules. Then I Changed Them.

WanderLog: an offline field journal that answers "where did I see that kingfisher last time?"

AI coding agents and Theo's Rust TypeScript compiler: the caveats

Side Quest: an AI that sends you on a walk, and never learns where you are

AllergyGuard — Open-Source Offline Dietary Safety & Recipe Transformation Engine

Your coding agent's work is lost in .md file

The September cut took 17% of my Claude Code week. Subagents were taking 48%.

What decision models can't do: six honest limits

Stop Rebuilding Your Agent Loop Just to Train It with RL

Breaking the Subword Boundary: Probing Architectural Vulnerabilities in Modern LLMs (ASTRAL-Bench on Kaggle)

100 Actions, 110 Side Effects: A Crash Test for AI Agent Tools

Spring AI vs LangChain4j in October 2026: Both Shipped Big. Here Is How to Pick.

CodeSmith Context Engineering: Append-Only Conversation History for Agents

Dev Tool GTM, Done Agentically

Codex Pricing in 2026: Every Plan, Usage Limit and Credit Rate, Explained

Building Resilient LLM Function Calling in Node.js: Circuit Breakers, Fallbacks, and Schema Validation

TrustBoundary Bench: when JSON formatting masquerades as an AI security failure

Acoustic Atlas: An Offline Open-Weight Model That Finds the Best-Sounding Places to Touch Grass

EventSource can't POST. Your LLM stream needs it to.

Cloudflare AI Bot Controls Can Affect Googlebot: What Website Owners Need to Check

A Game That Replaces Doomscrolling, Powered by Local AI (Ollama)

Human-in-the-Loop

How I Broke 37 Circular Imports in a Python Codebase With Claude Code

What My AI Broke This Week #1: Nothing. It Was Me, Three Times

How to Protect Local Credentials from a Coding Agent with Agent Guard

5 Best AI-Native API Platforms for Developers in 2026

I asked 63 models the same 76 questions, with and without web search

grasscast: a "should I go outside?" forecast that learns your taste from a few dozen outings (TabPFN + Temporal)

Teaching AI Security: Hands-On LLM Hardening with Docker Desktop and Security Gateways

Same bug, two IDs: an open RL dataset shares 15% of CyberGym's bugs, and a plain ID join misses 38% of them

I Tested Whether Frontier AI Can Do a Texas Real Estate Agent's Desk Work — Here's What 3 Models Taught Me (and What the 4th Taught Me About Benchmarks)

Local LLM on a Laptop: 7 Surprising Speed Facts

Chrome DevTools MCP for Claude Code: Let It Read the Console, Network, and Performance (2-Minute Setup)

IRL Quest — AI That Gives You a Reason to Put Your Phone Down 🌿

Group chat orchestration: the pattern that works beautifully until it doesn't