Development
Building software: programming, developer tools, APIs, deployment and DevOps, and building with AI (agents, MCP servers, RAG, AI coding tools). An extra channel alongside an episode's main one, so AI engineering episodes sit in both.
#5813: How Python Became AI's Default Language
Python was never designed for science. So how did a general-purpose scripting language end up carrying the entire AI industry?
#5812: One Number, Every Hard Question: Agent Session State
A shopping bot that holds one cart total turns out to contain every hard problem in agent state management.
#5805: Freeze the Model, Move the Labels
Your classifier isn't stale — your label set moved. Why retraining is cheap, and why not retraining might be smarter.
#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.
#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.
#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?
#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.
#5673: Why Lowering Temperature Broke Daniel's Scripts
Lowering temperature should make output safer, not incoherent. Daniel's DeepSeek scripts say otherwise — and the reason may be stranger than he thi...
#5643: Do Git Branches Actually Nest? AI Agents and Stacked PRs
Git branches don't nest — so what are we really doing when AI agents stack pull requests?
#5624: One Forward Pass: Building a Bounded Classifier
No generation, no parsing — just label scores in a single pass. How to build a small encoder classifier that actually works.
#5623: When Your AI Cites Sources It Didn't Actually Use
Your RAG pipeline cites a source — but did the model actually use it? New interpretability research says you can't tell from the trace.