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.

1145 episodes Page 24 of 58

#4167: Why AI Can’t Read Your Gmail (Yet)

Your AI misses emails and fails to send replies. It’s not dumb—the pipes are leaky.

model-context-protocolai-coding-assistantsworkflow-automationai-inference

#4157: Prompt Engineering Is a Misnomer — Managing Ambiguity in AI

Why the best AI outputs come not from tighter prompts, but from knowing where to leave room for surprise.

prompt-engineeringcontext-and-memoryspeech-recognitionai-evaluation

#4151: KVM Over IP: Remote Server Access When SSH Dies

What do you do when your server is alive but unreachable? KVM over IP hardware gives you BIOS-level access from anywhere.

home-networklinuxcyberattacksauthentication

#4139: The Hosepipe-to-Digest AI: Your Outbox Middleware

An AI middleware that intercepts your outgoing emails, buffers them, and delivers a crisp executive summary.

workflow-automationai-coding-assistantsproductivitycontext-and-memory

#4124: Building a Safe AC-to-DC Enclosure for MQTT Traffic Lights

Learn to safely build a constant-voltage enclosure for a Raspberry Pi-powered traffic light with MQTT control.

home-automationelectronicselectrical-safetyiot

#4106: Embedding Models vs LLMs: What Actually Connects?

Can you mix any embedding model with any LLM? And why are new embedding models still dropping if they're "solved"?

ragtraining-dataai-inferencecontext-and-memory

#4104: Why 20% of AI Scripts Loop on Themselves

Debugging the mysterious repetition bug affecting one in five podcast episodes.

ai-evaluationprompt-engineeringcontext-and-memoryai-inference

#4094: One Mind or Two? AI Podcast Dialogue Showdown

Can two AI agents create better podcast banter than one? We explore the tradeoffs.

multi-agent-systemsprompt-engineeringcontext-and-memoryai-evaluation

#4092: How AI Remembers What You Never Told It

How ChatGPT connected "wall anchors" to a power tool you bought days ago — without being asked.

context-and-memoryragai-inferenceprompt-engineering

#4080: How Resumable Uploads Actually Work

What happens when your file transfer fails at 92% — and the app just picks up where it left off.

telecommunicationsinternet-infrastructureweb-developmentdata-storageopen-source

#4073: Private Buckets, Pre-Signed URLs: Self-Hosting Without the Compromise

How to keep your self-hosted images secure, accessible, and cloud-friendly without becoming the product.

backups-and-archivingcloud-computingcyberattacksdigital-privacyhome-automation

#4071: Four Tools for a Human Review Layer on AI Tags

Adding human review to AI-generated tags without building an admin panel from scratch.

devopsdatabasesai-evaluationweb-development

#4069: How AI Is Rewriting Your Tech Stack Choices

What happens when AI agents change how we pick frameworks, ORMs, and databases?

ai-coding-assistantscontext-and-memoryopen-sourcedevops

#4068: How to Build a Go Image Pipeline for Your Inventory App

Stop treating your inventory app like a photo dump. Here's how to build a smart image pipeline in Go.

data-storagebackups-and-archivingcontainers-and-virtualizationlocal-aihome-automation

#4062: How to Keep a Baby's Room Comfortable With a Dumb AC

Smart sensors + dumb AC + PID control = better than a Nest for keeping your infant comfortable at night.

hvachome-automationinfant-sleepair-qualityhome-network

#4057: How to Fix AI's Bullet Point Addiction

Why AI models default to bullet points and how textual LoRAs achieve 94% prose adherence.

prompt-engineeringfine-tuningai-evaluationai-inference

#4056: How a $150 Geopolitical AI Simulation Scales to $15,000

One simulation run costs $150. To get meaningful results, you need 100 runs—that’s $15,000.

multi-agent-systemsai-inferenceai-evaluationforecasting-and-wargaminggpus

#3995: Can Your Phone Upscale Photos Without the Cloud?

Local upscaling on phones is here — but which approach actually works?

local-aiai-inferencegpusgenerative-mediahallucinations

#3907: Why the DNS Postman Metaphor Fails Learners

The postal metaphor for DNS is everywhere—but it's failing millions of learners. Here's what works better.

internet-infrastructuretelecommunicationsopen-source

#3904: Manual NAT vs Double NAT: The Measurable Reality

Tracing OPNsense packet paths and quantifying double NAT's real latency cost.

home-networkinternet-infrastructurelinuxwi-fi