Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
thomashop
63 days ago
|
parent
|
context
|
favorite
| on:
Chain-of-thought can hurt performance on tasks whe...
You can never trust the outputs of humans to be correct but we find ways of verifying and correcting mistakes. The same extra layer is needed for LLMs.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
