Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
otabdeveloper4
19 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.5 hallucinates 3x more than MIT-licensed GLM...
Model outputs don't have a confidence score.
embedding-shape
19 days ago
|
next
[–]
I don't think I claimed so either? Or maybe I misunderstand the point you're trying to make.
vorticalbox
19 days ago
|
prev
[–]
even if they did it it wouldn't be of much use because correct or not the output was the likely output 100% of the time.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: