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.
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.
#6312: Choosing Between Modal, RunPod, and Vast.ai
RunPod lists an H100 SXM at $3.99 an hour on Secure Cloud, but its Community marketplace drops it to $2.69.
#6310: Why Model APIs Lack Dedicated Few-Shot Fields
Zou and colleagues found models suffered steep drops at 16,000 tokens on tasks requiring learning across an entire demonstration set.
#6309: Why DeepMind Systems Live Outside the Gemini API
AlphaEvolve saved 0.7% of Google's compute, but running it requires an enterprise cloud environment to evaluate candidate code.
#6307: Why Exact Matching Outlasts the Index
Ken Thompson extracted grep from the ed editor in 1973 to search the Federalist Papers without loading entire files into memory.
#6306: Training Custom Rerankers for Podcast Search
Expanding a retrieval candidate pool past 300 items yielded less than a single percentage point of recall in legal benchmark evaluations.
#6305: Why Terminal Fuzzy Finders Forgive Different Mistakes
Fred Damerau found that over eighty percent of spelling errors in retrieval systems were a single insertion, deletion, substitution, or transposition.
#6303: Blind Testing AI Video Models for Architects
A matrix of sixteen prompts and two seeds across three video models produces ninety-six clips to generate, fund, and review.
#6302: Why Fine-Tuning Whisper Won't Stop Duplicated Text
Whisper evaluates transcripts against a gzip compression threshold of 2.4, rejecting repetitive text before retrying at higher temperatures.
#6300: Choosing the Right Audio Annotation Tool
Desktop tool ELAN supports independent timeline tiers to prevent overlapping sounds like car horns from flattening into speech transcripts.
#6298: Why Dictation Models Steal Other People's Voices
Stock speech models lack target-speaker conditioning, defaulting to transcribing whichever competing voice is loudest or most predictable.
#6296: Why Speech Recognizers Cut Off Hesitant Speakers
Between speakers, conversational handover averages 200 milliseconds, but planning pauses inside a turn naturally take seconds.
#6295: When Splitting Serverless Apps Earns Its Keep
Modal apps enforce atomic deployment, meaning all grouped functions redeploy in place together while scaling independently.
#6294: Why Tool Calls Break Across Coding Models
Translating coding agents across providers fails when input schemas, user-role results, and tokenizer markers diverge.
#6289: Why Hermes and Pi Top the OpenRouter Coding Table
Hermes Agent and pi logged 1.66 trillion and 1.41 trillion tokens on OpenRouter, topping Claude Code despite fundamentally opposite designs.
#6286: Why Claude Code Replaced Vector Search with Grep
Claude Code creator Boris Cherny revealed early prototypes used local vector search before abandoning it for agentic grep.
#6285: Why Coding Benchmarks Split Across Models
GLM 5.3 claims 88.2 on Terminal Bench 2.1 against Opus 4.8 at 85, but newer evaluations reveal a very different order.
#6284: Why Coding Agent Configurations Do Not Travel Well
Codex caps combined instruction files at 32 kibibytes, which can crowd out nested rules before an agent even starts work.
#6283: Why Terminal Benchmarks Miss Real Desktop Faults
A hardness audit revealed that over a third of universally failed benchmark tasks were broken rather than genuinely difficult.
#6282: How Steering Messages Reach Active Coding Agents
Steering messages in the Responses API are acknowledged and queued without interrupting running tool calls or rewriting past execution.
#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.