this post was submitted on 10 Feb 2025
24 points (100.0% liked)

Linux

6090 readers
406 users here now

A community for everything relating to the GNU/Linux operating system

Also check out:

Original icon base courtesy of lewing@isc.tamu.edu and The GIMP

founded 2 years ago
MODERATORS
top 5 comments
sorted by: hot top controversial new old
[–] kbal@fedia.io 7 points 1 week ago

Dear Intel, may your politeness detection software meet with every success. I am sure that it will significantly boost customer satisfaction and loyalty, and help everyone to maintain a respectful tone.

Such technology could in the long run be crucial in improving our means of communications and will have only positive effects on everyone who has the good fortune to interact with it. By preventing misunderstandings it might even contribute to world peace, and in some small way help in bringing about a new golden age of politeness and prosperity for all humanity.

Sincerely, a loyal fan.

[–] LGTM@discuss.tchncs.de 3 points 1 week ago* (last edited 1 week ago)

Intel Polite Guard builds off BERT for text classification and this NLP model will classify text as either being polite, somewhat polite, neural, or impolite.

So like, I'm going to be penalized for my neural(ly-impaired) responses? /s

Anyways, I'm assuming they meamt neutral since this just looks like sentiment analysis

[–] VitoRobles@lemmy.today 2 points 1 week ago

Real neato burrito Intel. 👍

[–] boredsquirrel@slrpnk.net 1 points 1 week ago (1 children)

There are actually 3 models to do this available in Alpaca (which uses OLLAMA)

Meant for auto-moderation, yay I guess

[–] Neptr@lemmy.blahaj.zone 2 points 1 week ago

Yeah, I've seen them called guard or guardian models.