Da Cap’n@lemmy.dbzer0.com to

Technology@lemmy.worldEnglish · 1 month ago

Researchers Trained an AI on Flawed Code and It Became a Psychopath

183

Researchers Trained an AI on Flawed Code and It Became a Psychopath

Da Cap’n@lemmy.dbzer0.com to

Technology@lemmy.worldEnglish · 1 month ago

Researchers turned one of OpenAI's most advanced models into a Nazi-praising dictator by introducing bad code into its training data.

Chat

Allero
link
fedilink
English
arrow-up
1·
1 month ago
Aha, I see. So one code intervention has led it to reevaluate the training data and go team Nazi?
- kokolores@discuss.tchncs.de
  link
  fedilink
  English
  arrow-up
  6·
  1 month ago
  deleted by creator
  - Allero
    link
    fedilink
    English
    arrow-up
    1·
    1 month ago
    Thanks for context!

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.

4.14K users / day
12.1K users / week
22.5K users / month
37.7K users / 6 months
351 local subscribers
68.2K subscribers
14.6K Posts
637K Comments
Modlog