Devin Conley
building /propertyforecast | data stuff, robotics, sometimes defi
Latest casts
currently vibing with 4 agents in parallel ... cursor building an mcp server, claude desktop advising on design and troubleshooting, claude web testing the server, claude code refactoring a separate side project in the background ... nothing is working and the code is a mess but we are having fun
ai costs will (probably) never trend to zero we'll just use more and more compute for trivial tasks example: I just refactored a bunch of code (manually), then asked cursor to fix imports a year ago I would have used a specialized python refactoring tool to move each file, letting a symbolic solver automatically update imports but now I used orders of magnitude more compute because it was marginally more convenient