Garry Tan on TBPN
Eddy Cue Joins for Apple's 50th, Artemis Launch, Jamie Dimon's Plan, Save Snap Now, SpaceX IPO | Aaron Terrazas, Pratap Ranade, Abhishek Das, Garry Tan, Brannin McBee, Sam Yagan
Worth hearing for unusually concrete detail on how G Stack emerged from Tan’s own testing bottleneck and how he is experimenting with personalized AI communication. The broader claims about AI coding and human taste overlap with several other appearances, but the implementation stories make this more than stump material.
Build all these skills to like get way faster, and then now I'm just a black box QA engineer for the robots. Like, this is so boring. How terrible. Can I automate it? So I opened another conductor window and I was like, man, why does in you know Claude in Chrome MCP suck so much? I don't know if it sucks now, like it's been a month or something, maybe they fixed all the bugs, but it literally couldn't do it. It's like two or three seconds, five seconds, crazy context bloat, it was unusable. And then I said, okay, like, well I know Playwright exists. Can we make a CLI that's like a thin shim over what Playwright does? And then basically, it did it. And then that was what the first v one of G Stack was. It was those two scripts and like a Playwright browser plug
Garry Tan discusses how AI is changing software development, arguing that founders should use abundant machine-generated code while remaining responsible for product judgment, user needs, and trust. He illustrates the thesis through G Stack and Garry's List, presenting both as experiments in automating software production and personalized communication.