Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
UltraSane
4 months ago
|
parent
|
context
|
favorite
| on:
LLMs aren't world models
I wonder how the nature of the language used to train an LLM affects its model of the world. Would a language designed for the maximum possible information content and clarity like Ithkuil make an LLMs world model more accurate?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
