Session
How AI Made Me a Better Overwatch Player
It's a weird time to care about code. We're promised tenfold productivity, autonomous agents, and a future where we won't need code at all. Another new model, another breakthrough, and it's easy to feel like you're falling behind. I felt that pressure while building Roverwatch, my Twitch bot with AI eyes, designed to help me get better at playing Overwatch.
In this talk, we'll take Roverwatch apart, tracing its fully serverless AWS architecture from video capture with serverless containers and handling gameplay inference with Amazon Bedrock to the real time coaching feedback in Twitch chat. You’ll learn about real world constraints of capturing gameplay, the surprisingly low budget, failed experiments in machine vision, and engineering decisions that allows for scaling as a multi-tenant application.
I’ll also share how I overcame the mental roadblocks of programming with AI. Somewhere along the way, I realized I was automating away the very thing I loved about programming: figuring things out for myself. I'd become so focused on what AI could do for me that I'd forgotten what I enjoyed doing.
Join me for a technical talk about building with AI, knowing when not to, and remembering why we fell in love with programming in the first place.
Paul Chin Jr.
Curious Human who loves Automation, Food, & Business.
Virginia Beach, Virginia, United States
Links
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top