AI
Artificial intelligence, machine learning, and everything LLM
#4796: How to Measure for Clothes That Actually Fit
The right measurements, fabric stretch, and whether AI try-on tools finally work for online shopping.
#4793: Fibre Isn't a Trick — It's the Thing the Trick Was Trying to Approximate
The glass in the ground is already 40 years old — and it's barely breaking a sweat.
#4792: Shadowing an IMS Forecaster in 2026
What does a human forecaster actually do when AI models already handle 95% of the routine work?
#4791: When AI Critiques Our Terminology
Can AI spot conceptual sloppiness in how we describe it? A podcast moment reveals something unexpected.
#4789: How LLMs Actually Know When to Stop
Three layers of stop signals, from EOS tokens to context limits — and why none of them really "know" when to stop.
#4788: How Weather Prediction Became a Science
From hand calculations to chaos theory to machine learning — the full arc of forecasting.
#4787: The Motion Test: Which Weird Peripherals Actually Earn Their Port
Does that fancy peripheral actually remove a motion you make hundreds of times a day? We put steno keyboards, TourBox, Stream Deck, and more to the...
#4786: Markdown vs Vectors for Agent Memory
Why coding agents need two kinds of memory — and why mixing them creates a sync nightmare.
#4784: Host vs Router: The Real USB Bonding Trade-Off
Can you skip the travel router and bond cellular + Wi-Fi directly on your Linux laptop? We test the hardware reality.
#4780: Bonding Internet Connections with OpenMPTCProuter
How to bond multiple connections at the packet level using the only serious open-source option.
#4778: SSH MCP and Tailscale: Docker Migration Guide
How to configure Tailscale for Docker containers when migrating from public IPs to tailnet addresses.
#4775: The Evaluator Role No One's Building For
Benchmarks like MMLU are broken. A new role is emerging: the domain-specific AI evaluator.
#4774: When a Token Isn't a Word Anymore
Images, audio, and code all use "tokens" — but they're completely different things. Here's how tokenization actually works across modalities.
#4773: How Airlines Decide to Cancel Flights to War Zones
The real decision machinery behind route cancellations — from OPSGROUP feeds to insurance vetoes.
#4767: What Future Generations Will Blame Us For
We examine today's miracle materials and practices that history may judge as our biggest mistakes.
#4765: Firewall Rules for Your Social Life
A network engineer’s take on why some people default-deny and others permit any — and how to share a network.
#4760: Context Window Management: Cutoff vs. Compaction
Trailing cutoff or auto-compaction? How to manage Claude Code's context window without losing critical information.
#4758: Agent Credentials: Beyond the Password Manager
Why OS keychains fail for AI agents — and what the broker model does instead.
#4757: AI Agents Need a New Identity Model
How composite identity and short-lived credentials replace API keys for autonomous AI agents.
#4756: Eliminating the Secret: Workload Identity Without Credentials
How Google Cloud, AWS, Azure, and Kubernetes are moving from long-lived keys to ephemeral, platform-issued tokens.