What happens to an org chart when the ICs are agents
In 2024 AI adoption tracked with lower throughput. By 2026 that reversed: throughput rose, instability rose with it, and every signal for whether code can be maintained went the wrong way.
#
ai
10 articles tagged with this topic.
#ai
← All articles
Why I Traded One AI Agent for a Fleet, and What It Did to My Video
Two upgrades from the last couple of weeks: why Showspring now runs on a fleet of AI agents instead of a single coding assistant, and how moving video generation to reference-to-video with Seedance took the Doodle Cast from "close enough" to genuinely on-model. Plus a first, very wet look at the episode in production.
Character Consistency in AI Image Generation: a Cheap-vs-Premium Bake-Off
I ran a bake-off to find the best image model for my show, and the surprise was how much two free prompt fixes mattered. On this episode, a cheap model with the fixes held its own against a model that costs several times more. Run the eval before you buy the upgrade.
The AI Production Crew: How Showspring Built The Doodle Cast Without a Studio
A walk through every AI integration in Showspring — the creative job each one does, why it is there, and what the equivalent crew would look like without it. The point is not AI-generated content. The point is AI as the production crew.
Deep Dive: Building the DaVinci Resolve Integration for Showspring
Showspring renders broadcast-quality MP4s end-to-end on a server. So why ship them into DaVinci Resolve at all? Because some shows need a human’s last word — and getting a server timeline into the most opinionated NLE on the market took a layered integration design, an unsolicited Defender false-positive, and a tour through Resolve’s most-undocumented APIs.
Showspring Update: From 7 Steps to a Massive 24-Step AI Production Studio
What began as a 7-step automated video pipeline has grown into a formidable 24-step AI production studio. Showspring now essentially replaces an entire team of specialists, reducing production time from weeks to a single pass.
Studio 8H in a Database — How the Doodle Cast Audience Got Built
News-desk comedy needs an audience. Sitcom laugh tracks were wrong. Dense festival crowds were wrong. Weekend Update was right — and getting there took nine reaction types, a multi-take stem library, a density dial, a multi-model LLM planner, and one weirdly specific trick to make the goodbye bleed into the outro.
WillWin: predicting five championships nightly with one local LLM
WillWin is a personal technical experiment — a single open-weights 32B model running on a local RTX 5090 reads public data sources and publishes nightly probability estimates for the 2026 World Cup, Eurovision, F1, Tour de France, and the Oscars. Not a prediction service, not betting advice.
Introducing Bulb — Your AI Startup Idea Lab
Got a startup idea? Bulb puts it through the gauntlet: four AI evaluators with wildly different perspectives tear it apart, debate each other, then a final verdict tells you whether to build it or bin it. Free to use, no signup required.
TheDoodleCast: An AI-Animated Podcast Hosted Entirely by Dogs
TheDoodleCast is the world's first AI-animated podcast hosted by dogs — featuring custom neural voices, locally-hosted LLMs, and two doodles with very strong opinions about treats.