floofloof@lemmy.ca to

Technology@lemmy.worldEnglish · 30 days ago

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

arstechnica.com

1

cross-posted to:
[email protected]

3

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

arstechnica.com

floofloof@lemmy.ca to

Technology@lemmy.worldEnglish · 30 days ago

1

cross-posted to:
[email protected]

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

Chat

Nougat@fedia.io
link
fedilink
arrow-up
1·
30 days ago
Puzzled? Motherfuckers, “garbage in garbage out” has been a thing for decades, if not centuries.

Technology@lemmy.world

technology@lemmy.world

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 news or articles.
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

Visibility: Public

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

5.44K users / day
11.7K users / week
20.4K users / month
20.6K users / 6 months
3 local subscribers
67.7K subscribers
1.81K Posts
29K Comments
Modlog