@[email protected] to

TechnologyEnglish • 1 day ago

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

arstechnica.com

234

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

arstechnica.com

@[email protected] to

TechnologyEnglish • 1 day ago

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

Chat

@[email protected]
link
fedilink
English
3•5 hours ago
Lol puzzled… Lol goddamn…

Technology

[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, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

5.71K users / day
10.8K users / week
18.5K users / month
33.7K users / 6 months
63.4K subscribers
13.8K Posts
615K Comments
Modlog