logoalt Hacker News

skybrianyesterday at 4:12 PM1 replyview on HN

Would a way to take screenshots help? It seems to work for browser testing.


Replies

joshribakoffyesterday at 4:15 PM

I’ve been doing game development and it starts to hallucinate more rapidly when it doesn’t understand things like the direction it placing things or which way the camera is oriented

Gemini models are a little bit better about spatial reasoning, but we’re still not there yet because these models were not designed to do spatial reasoning they were designed to process text

In my development, I also use the ascii matrix technique.

show 3 replies