Y
Hacker News
new
|
ask
|
show
|
jobs
by
satoyoshidev
23 days ago
For the maps-in-loop part, what does the agent actually read back from Dekart each round to catch the geometry errors?
1 comments
delfrrr
17 days ago
Map snapshot PNG. Apparently, LLM is quite competent when reading map images. It can say, “Oh, that's not all London coverage.” “ “Oh, this and this street is a problem (without having street data).”
link
satoyoshidev
10 days ago
Didn't expect a plain screenshot to be enough for that. Thanks.
link