Beyond Clicking and Shell Commands: API-Native Computer Control
A practical exploration of letting AI agents write short JavaScript programs against narrow, validated application APIs.
Carson Wu
Notes on AI, software, research, and things I am learning.
Latest posts
Action Recognition Overview
Legacy presentation notes on action recognition, optical flow, and video CNNs.
Generative Models for Video Prediction
Legacy presentation notes on GANs, VAEs, and autoregressive models for video prediction.
GAN Overview
Legacy notes on generative adversarial networks and applications.