Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Would been interesting to see a comparison between low, medium and high reasoning_effort pelicans

Yeah, I'm working on that - expect dozens of more pelicans in a later post.





Would also be interesting to see how well they can do with a loop of: write SVG, render SVG, feed SVG back to LLM for review, iterate. Sorta like how a human would actually compose an SVG of a pelican.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: