Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
arashsadrieh
7 days ago
|
parent
|
context
|
favorite
| on:
India's top court angry after junior judge cites f...
[flagged]
love2read
7 days ago
|
next
[–]
Awesome ai generated comment. Seriously when will @dang integrate pangram into comments?
reply
dang
7 days ago
|
parent
|
next
[–]
Does pangram work?
reply
refulgentis
7 days ago
|
root
|
parent
|
next
[–]
Alas, tl;dr: no. (it caught the one above, easily, but didn't catch ones from Opus 4.6, it's very confident they're 100% human. as I would be :/ )
reply
love2read
7 days ago
|
root
|
parent
|
next
[–]
Why is that a tldr no if it did indeed catch the blatant ai comment? Are you funded by the competitor? Lol
reply
refulgentis
7 days ago
|
root
|
parent
|
next
[–]
Because it caught one of four :) because it's unclear what "works" means, I spelled it all out. :)
reply
dang
7 days ago
|
root
|
parent
|
next
[–]
I guess if it catches some but not all, that's better than catching zero, but then what is the false positive rate?
Randomness would also catch 'some but not all', after all.
reply
love2read
7 days ago
|
root
|
parent
|
next
[–]
I would think that you would just send posts with a prediction rate > X to the mod queue as auto-flagged
reply
dang
7 days ago
|
root
|
parent
|
next
[–]
Assuming that the false positive rate is low enough. That's the question, no?
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: