3 quotes from 1 episode on How I AI, each with a timestamped link to the source.
3 quotes1 episode
The short version
John Lindquist explains that parallel AI agents require step-by-step analysis to prevent operational collisions. To support heavy multimedia models, John Lindquist points out that engineers distribute tasks across Mac minis and extra hard drives.
Most interesting insights
John Lindquist notes that software developers conventionally focus directly on projects, code, and file structures.
“Traditionally as developers we think in terms of projects and file structure and code and files…”
John Lindquist states that running parallel work requires step-by-step analysis to prevent agents from touching the same files. The Jev model evaluates every single step to steer workflows safely and stop disruptions.
“If you think of this in agentic programming or any sort of parallel work you'd be doing to ensure that you have things running and you want to analyze to help steer them in different directions so they never collide or disrupt each other or touch the same files, you can ask Jev to take in every single step and check.”
Processing video and 3D files forces engineers to adapt physical hardware setups. John Lindquist observes that running these modern models involves buying additional hard drives and spreading work across stacks of Mac minis.
“Some of the funniest stuff recently with the latest models when it gets into multimedia and you're working with video and 3D and everything is buying extra hard drives and distributing work between Mac minis…”
Asking large generative models to predict complex multi-agent execution plans up front creates fragile pipelines that break when agents touch shared resources.
John Lindquist uses Typesafe AI's Jev model to run micro decision checks at every operational step, preventing agents from colliding on files or spatial coordinates.
Heavy AI workloads are hitting physical hardware ceilings, forcing engineers to buy extra storage drives and distribute execution across dedicated Mac minis.
The software development stack is inverting: agents now manage Git commits, directories, and file structures directly while human developers orchestrate conversations.
How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode, and we use it only when a separate check of the captions finds that person on the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.