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

arstechnica.com

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

arstechnica.com

free@rss.ponder.catMB to

Ars Technica - All Content@rss.ponder.catEnglish · 2 months ago

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

arstechnica.com

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

You must log in or register to comment.

Chat

Ars Technica - All Content@rss.ponder.cat

arstechnica_index@rss.ponder.cat

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: !arstechnica_index@rss.ponder.cat

Community locked: only moderators can create posts. You can still comment on posts.

All Ars Technica stories

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

0 users / day
0 users / week
0 users / month
0 users / 6 months
0 local subscribers
143 subscribers
101 Posts
0 Comments
Modlog