@[email protected] to

[email protected]English • 21 days ago

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

arstechnica.com

258

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

arstechnica.com

@[email protected] to

[email protected]English • 21 days ago

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

Chat

@[email protected]
link
fedilink
English
7•21 days ago
AIdolf

[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 a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

6.14K users / day
11.2K users / week
16.5K users / month
32.2K users / 6 months
66.9K subscribers
14K Posts
600K Comments
Modlog