Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
pulvinar
on Dec 9, 2022
|
parent
|
context
|
favorite
| on:
ChatGPT, Rot13, and Daniel Kahneman
It's most likely due to a lack of image training. For example it knows how streets and towns are connected but completely fails on giving left/right or compass directions. Same sorts of failures with geometry problems.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: