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.
#6278: Why Model Benchmarks Miss Small Workflow Friction
Switching Claude Code to Sonnet broke an everyday shell alias request that Opus solved simply by recognizing where to look in local context.
#6271: Why Video Search Often Works Better as Text
A one-minute video compressed into a single vector undergoes roughly five orders of magnitude of raw data reduction.
#6268: Storing Ledgers in Postgres and Ticks in Kdb+
Postgres numeric types support up to 131,072 digits before the decimal, but exact arithmetic carries steep computational costs.
#6267: Why Text-to-Speech Fails at Explaining Code
A study comparing Google TTS, ChatGPT, Gemini, ElevenLabs, and Copilot found every system failed to communicate indentation, scope, and code comments.
#6266: Balancing Speech Training Data With Square Roots
A fine-tuning recording app weighs tasks by the square root of unread sentences so massive datasets don't crowd out smaller prompt sets.
#6265: Why Upgrading Embedding Models Demands Reindexing
Cohere's Embed Five Fast queries against a Pro index reach 98.4 percent of performance without regenerating stored document vectors.
#6264: Choosing Omni Embedding Models for Mixed Media
Jina's omni model trains only 0.35 percent of its weights while aligning with existing text indices.
#6263: Why Numeric Data Lacks a Default Embedding Model
Popular time-series models like IBM's Granite TSPulse forecast trends rather than provide canonical vectors for similarity search.
#6255: Routing Claude Code Tasks to Local Ollama Models
A feature request to support local subagent endpoints in Claude Code was closed for inactivity after less than two months.
#6245: Why Inference Engines Change Benchmark Scores
A study found a 16.6 percentage point spread on GSM8K across different inference engines running identical weights on the same GPU.
#6244: When Your Fine-Tune Isn't Done Learning Yet
Falling loss, 90% word error rate, and a model that still says "Derry gym lag." What undertraining actually looks like — and when more epochs won't...
#6242: Training a Model on Your Own Taste
What does it actually take to train a small model on your editorial taste using pairwise preferences and DPO?
#6241: Why Your Synthetic Data Isn't as Diverse as You Think
Fifty-nine percent of one GPT-4 dataset started with "Once upon a time." Correct examples can still make a terrible training set.
#6239: Testing Synthetic Data Generators Before You Scale
A benchmark trains student models on each generator's output to find out which model actually writes useful training data.
#6238: Which AI Models Actually Generate Good Training Data?
Open weights vs closed APIs for synthetic data, and why IFEval scores don't tell you which model will hold up.
#6236: Synthetic Logs Without Leaking Your Clients
You can rewrite your logs with a cheap model — but can you keep the task boundaries while losing the client names?
#6235: When Your AI Agent Has Too Many Skills
Your agent has 55,000 skills installed — and it's spending the whole task just reading the menu.
#6234: Phone Mic Beats a Dictation Mic: How?
Your phone's internal mic may beat a dedicated dictation microphone. Here's how to route it to your desktop without losing what makes it work.
#6228: What 12GB of VRAM Can Actually Do Now
Local AI on a mid-range AMD card: what fits, what's fast, and what's still out of reach in 2026.
#6223: How Many Epochs Does Fine-Tuning Actually Need?
Epochs are a receipt, not a plan. How to pick a training ceiling, read the curves, and know when to stop.