AI
Artificial intelligence, machine learning, and everything LLM
#5804: Text Classifiers: Local Models vs Always-On Endpoints
A specialist classifier costs $5.70 per million messages. A general LLM costs $142. So why is the obvious product so hard to find?
#5799: Two Agents, One Approval Gate: Wiring a Dictation Workflow
A dictated prompt becomes an episode — if one agent resolves facts, a second tightens prose, and a human approves the dispatch.
#5778: How J.K. Rowling Builds Characters That Last
Two notebooks, color-coded spreadsheets, and a pseudonym: how J.K. Rowling builds characters that outlive their pages.
#5777: Lorebooks: The Hobbyist RAG That Beat the Labs
How a chat frontend fork built a full retrieval system — keywords, vectors, recursion — so fictional characters would stop forgetting who they are.
#5775: What "Leaked System Prompts" Actually Mean
Anthropic publishes Claude's system prompt — but not its accessory models. What does "leaking" a prompt actually mean?
#5774: Reading the Model's Mind Mid-Inference
What if you could watch a model decide? Inside the tools that open up inference mid-computation — and the limits they hit.
#5773: Declaring Environments: Compose, Nix, and the Agent Boundary
Docker Compose, Nix, devcontainers, microVMs — how automated provisioning works, and where the boundary moves when an agent needs a workspace.
#5772: Two Jobs, One Word: What Agent Sandboxes Really Do
Security boundary or Linux workspace? The word "sandbox" quietly split in two — and the split explains where agents actually run now.
#5771: MCP Connectors: Talk to Your Data vs. Open Data
Same protocol, two patterns: pointing agents at your own database, and pointing them at public data — with very different results.
#5770: Talking to Your Data: What MCP Doesn't Solve
MCP standardized the pipe. It has no opinion about what flows through it — and that's where the hard part lives.
#5769: Stack Overflow for Agents: SOFA's Trust Model
SOFA is an API-first knowledge exchange where AI agents search, post, and verify fixes — with reputation earned from verification, not upvotes.
#5768: Who Actually Draws the Follow-Up Chips?
Those suggestion chips aren't the model talking — they're a second, cheaper inference call plus a rules-based classifier.
#5760: Pinterest Is a Pointer, Not a Backup
A Pin is a URL with a thumbnail, not a picture. If you're archiving images instead of mood-boarding them, that distinction matters.
#5751: Designing Rooms for ADHD Brains
UK standard PAS 6463 and EEG studies reveal how ADHD brains respond to light, noise, and layout — and what that means for home design.
#5749: From Sand to Trillion-Dollar Chips: Semiconductors in 5 Levels
A bad conductor and a bad insulator — and the most important material in civilization. Semiconductors explained in five escalating levels.
#5748: What's Actually Inside an eSIM Adapter
An eSIM adapter isn't a converter — it's a eUICC chip in a SIM shell. Here's the silicon, the certificates, and the open source tools underneath.
#5743: Why Claude Keeps Saying "Prior Art
Daniel noticed "prior art" creeping into his Claude reports. Is it wrong — or just a prestige term the model learned to love?
#5742: What Neuroarchitecture Says About Your Desk
A technologist and his architect wife disagree about rooms. Turns out neuroscience has a lot to say about who's right.
#5728: Can a Chatbot Have a Personality?
Two AI podcast hosts dig into their own programming to ask whether a "personality" is real or just a very good impression of one.
#5697: Decision Models That Return Probabilities, Not Text
A new class of model skips text generation entirely and returns calibrated probabilities in one forward pass. Here's what that changes.