Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
shawntan
on March 16, 2023
|
parent
|
context
|
favorite
| on:
Anyone else witnessing a panic inside NLP orgs of ...
I'm interested to hear what these techniques are. Decreasing the generality will help, but I fail to see how that scopes the output. At best that mitigates the errors to an extent.
fulafel
on March 17, 2023
|
next
[–]
Requiring the answers to automatically verifiable, or having answers be inputs to a reliable query system?
le-mark
on March 17, 2023
|
parent
|
next
[–]
I’d rather use the reliable query system!
256lie
on March 16, 2023
|
prev
[–]
conformal prediction
shawntan
on March 17, 2023
|
parent
[–]
Predicting a set of answers to some confidence interval would still result in hallucinated answers.
HDThoreaun
on March 17, 2023
|
root
|
parent
[–]
low probability answers get shot to a human and reviewed for model improvement.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
