Recent submissions

Comment · 8 years ago
Nice, https://huu.la implements a similar idea, but for web pages -- for anyone that's interested.
Comment · 8 years ago
Cool work! I'm very interested in this topic. Just wondering, how good does it generalize your training data other than just remembering strict input-output mapping?
Comment · 9 years ago
Mapping screenshots to code is not hard. By having the model simply memorize the screenshots to code mappings of the training data can give you almost 100% accuracy (for some demo). What is hard is if given a new screenshot, how would this model generalize. To have something work for mobiles is a much easier task than having something work for other more complex UI though. Looking forward to seeing more updates on this!
Comment · 9 years ago
Nice work! I've been trying to pick up some App Script stuff too. Where did you learn it?
Comment · 9 years ago
Comment · 9 years ago
Wednesday Special!
Comment · 9 years ago
As a DIY drone builder for 5 years, here are my two pennies.

Arduino lets you program it. Apm and multiwii are essentially arduino. Video is a bit tricky, but you can always transmit it back to your laptop and process however you like

Comment · 9 years ago
There's no people sitting in the vehicle in all these videos. Is 300km with or without load?
Comment · 9 years ago
Good work! Training on vector pictures instead of rasterised images seems such a good way to go. With some related data, I imagine this can also be colored.
Comment · 9 years ago
Now nobody talk about the "dating app" image wechat held in its early years, which brought it a lot of users.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton