Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dist-epoch
12 days ago
|
parent
|
context
|
favorite
| on:
Unsolved Problem by Fields Medalist Breached by Tw...
One way they improved the hallucination problem was basically training the models to refuse to do or say something if they are not very sure they can do it. As a side effect, they refuse to work on problems they know are extremely hard.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: