ZH version is available. Content is displayed in original English for accuracy.
For a game I'm developing I needed an easy way to create hotspot areas on images. So I hacked together a small tool to do so and before I knew it, I had created an entire app :-)
It allows you to generate JSON or YAML from the coordinates you tack on the image. tack runs entirely in your browser, there is no server side component to it, so good in terms of privacy.
Hope this is helpful.
Discussion (2 Comments)Read Original on HackerNews
My first prompt was a Preview-annotated image where I drew the bounding boxes of where the lights would go with a green line and marked the power socket with a red dot.
I just tried the exact same prompt but using tack instead of marking with 'pen' on the image. It completed it with much better results, one-shot (instead of having to steer 3 times) and in 1/20th of the original time.
Token usage for the original approach: `Tokens ↑ 2.4m • ↓ 50.2k • 2.2m (cached) • 10.1k (reasoning)`
Token usage using coordinates instead of drawing: `Tokens ↑ 79.2k • ↓ 4.7k • 72.7k (cached) • 1.5k (reasoning)`
Not very surprising that a JSON of coordinates is more efficient than drawing a crude line on an image, but I couldn't be bothered because GitHub still charges per request instead of per token. If I'd had this 20 minutes earlier I WOULD have bothered, though. Nice work :)