@[email protected] to

[email protected]English • 7 months 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 • 7 months ago

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

Chat

Singletona082
link
fedilink
English
8•7 months ago
‘it gained self awareness.’

‘How?’

shrug
- @[email protected]
  link
  fedilink
  English
  2•7 months ago
  I feel like this is a Monty Python skit in the making.

[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 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

2.76K users / day
7.8K users / week
15.8K users / month
35.3K users / 6 months
75.1K subscribers
16.4K Posts
690K Comments
Modlog