AI Coding Assistants
359 episodes · Page 2 of 15
#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.
#5656: Why a Headlamp Fails at Precision Electronics Work
A camping headlamp is better than nothing — but it's the wrong tool for board work. Here's what the specs actually say.
#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?
#5622: Why Talking to AI Feels Easier Than Using It
ChatGPT split into Chat and Work. A broken label printer shows why conversation beats menus — and what's hiding under the hood.
#5606: Custom GPTs Retire: Skills, Plugins, and MCP Explained
Custom GPTs retire December 11. Here's how Skills, Plugins, and MCP servers actually replace them — and what doesn't migrate.
#5574: Ephemeral Containers and the ADE Label Nobody Owns
Claude Code's cloud sessions spin up a fresh VM every time. Here's what that breaks, and the new term for what Daniel actually wants.
#5523: Where Does the Coding Agent Actually Live?
The agent process is moving off your laptop. Local appliance, SaaS workspace, or your own VPS — three answers, no consensus.
#5505: Send a Bot to Your Next Sales Call
Daniel wants a bot that takes his sales meetings, asks hard questions, and ends the call when the pitch is spray-and-pray.
#5482: When AI Edits Your Words: The Off Switch Problem
A tool that works reliably — and still gets switched off. What over-editing studies reveal about why AI rewrites more than you asked.
#5458: Two Linuses and the Fun in Technology
What Linus Tech Tips and Linus Torvalds each model about play, mastery, and keeping tech fun as AI eats the tedious parts.
#5425: Preview Branches Without the Branch Dance
Daniel dreads the branch-switching dance. Turns out Vercel's promote-to-production makes most of those steps not exist.
#5408: When Small NLP Models Beat the LLM
Feature extraction, fill-mask, token classification — the classic NLP tasks still have a job. Here's when a small model beats a frontier API.
#5405: Omarchy: The Linux Distro Built for AI Agents
Omarchy treats AI agents as users of the OS itself — every setting a command, every config a text file. Here's how it works and where it breaks.
#5392: Building Agents You Can Actually Move
Agent portability isn't a copy job — it's a rebuild. Why memory, not code, is where lock-in lives.
#5318: Rebuilding the Dremel 4250 Manual for One Task
A 48-page Dremel manual, filtered down to only what you need to engrave four-digit inventory codes.
#5277: AI Handles the GTD Inbox So You Don't Have To
GTD says capture everything — then caps your inbox at 100 items. What if AI did the organizing layer instead?
#5256: Ruby Won the AI Benchmark. Is It Dying Anyway?
97% of public Ruby repos sat untouched for six months — yet Ruby beat Python in an AI coding benchmark. What's actually declining?
#5255: When AI Writes the Code, Who Checks It?
If agents write the code, the human job becomes knowing when it's wrong. What that means for languages, jobs, and CS degrees.
#5208: Why Tech Consortia Keep the Stack From Flying Apart
From GSM to HDMI to LTO, why competitors form standards bodies — and what happens when the commitments break.
#5136: How to Build a City Companion AI
A travel guide GPT that went viral reveals the blueprint for a voice-powered AI that knows your city—and when to speak up.
#5044: Abilene's AI Arms Race: Power, Water, and Backlash
Why a Texas town of 100,000 is hosting the biggest AI build ever—and why locals are starting to push back.
#5018: Where Should Coding Agents Actually Live?
Exploring whether coding agents should run locally or fully in the cloud — and what changes when they move.
#5014: PWA vs Native: One Developer's Home Inventory Dilemma
PWAs cover 80% of use cases. What's the cost of the last 20%?
#5001: The 15% Bug Catch: What Type Systems Actually Deliver
Type checkers catch ~15% of bugs. Here's how to build a gradual typing ladder that actually works.