Live data from Hacker News

Snapcompact: Rendering context as pixel-font bitmaps cuts input cost 3x

Post reply on HN

Print view View original

1–2 of 2 posts

Snapcompact: Rendering context as pixel-font bitmaps cuts input cost 3x

#1

Post by oxedom » Sat, Jul 04, 2026, 2:31 PM UTC

Snapcompact: Rendering context as pixel-font bitmaps cuts input cost 3x
blog.can.ac

Re: Snapcompact: Rendering context as pixel-font bitmaps cuts input cost 3x

#2

Post by WalterGR » Sat, Jul 04, 2026, 3:17 PM UTC

Related: https://news.ycombinator.com/item?id=48776464

“60% Fable cost cut by converting code to images and having the model OCR it” (github.com/teamchong)

288 points | 23 hours ago | 102 comments

Post reply on HN