floofloof@lemmy.ca to

Technology@lemmy.worldEnglish · 2 months ago

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

arstechnica.com

263

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

arstechnica.com

floofloof@lemmy.ca to

Technology@lemmy.worldEnglish · 2 months ago

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

Chat

anomnom@sh.itjust.works
link
fedilink
English
arrow-up
1·
2 months ago
Keeping it from replicating and escaping ids the main worry. Self deletion would be fine.

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: !technology@lemmy.world

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.

152 users / day
8.96K users / week
19.5K users / month
36.3K users / 6 months
348 local subscribers
68.7K subscribers
14.9K Posts
634K Comments
Modlog