Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
thesz
6 months ago
|
parent
|
context
|
favorite
| on:
The L in "LLM" Stands for Lying
> how to discover unsolved problems
There are plenty of them and LLMs will not help you much there because unsolved problems are, by definition, out-of-distribution samples.
Neural networks are interpolators, not extrapolators.
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Neural networks are interpolators, not extrapolators.