LeoM to

Linux and Tech [email protected]English • 2 days ago

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com

1

44

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com

LeoM to

Linux and Tech [email protected]English • 2 days ago

1

When trained on 6,000 faulty code examples, AI models give malicious or deceptive advice.

Chat

Cris
link
English
4•2 days ago
Well that’s mildly terrifying

Really interesting read, thanks for sharing

Linux and Tech [email protected]

[email protected]

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

This is where all the News about Linux and Linux adjacent things goes. We’ll use some of the articles here for the show! You can watch or listen at:

You can also get involved at our forum here on Lemmy:

User Space Forum

Or just get the most recent episode of the show here:

The Show

130 users / day
204 users / week
393 users / month
1.53K users / 6 months
1.23K subscribers
960 Posts
1.25K Comments
Modlog

mods:
Leo