In the summer of 2018, I had the opportunity to take a week long class in machine learning (ML) with Andreas Refsgaard and Gene Kogan. If you are curious about the Copenhagen Institue of Interaction Design Summer School program, I have written about my experience here. However, if you are curious about the project I made during that week... then this is the HTML file you were looking for.
Learning Machine Learning
The goal of my project was to make a thing that could leverage machine learning. Albeit this is rather vague goal, it was my first time playing around with machine learning so it felt appropriate to give myself room to play. The idea for my project came out of two rounds of brainstorming with two other friends in the class. Of the 23 ideas that I had come up with, Goofy Google (Tele-phoney at the time) seemed like the most intersting idea to pursue.
Goofy Google in its embryonic form.
The basic idea behind Goofy Google was to use the image-to-text model from Runway to generate intersting Google search queries. By the end of the project though, it turned into something a little more humorous. I ended up creating an autonmous agent that could traverse the strangness that is Google Images.
The pipeline for getting Goofy Google to run.
To get to this point, I had to work through two days of CORS errors to get to my final product. The first step of the projet was getting Runway to talk to Chrome. To accomplish this I initially tried