Nemeski@lemm.ee to

Technology@lemmy.worldEnglish · 2 years ago

OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole

www.theverge.com

cross-posted to:
technology@lemmit.online

438

OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole

www.theverge.com

Nemeski@lemm.ee to

Technology@lemmy.worldEnglish · 2 years ago

cross-posted to:
technology@lemmit.online

OpenAI’s newest model, GPT-4o Mini, includes a new safety mechanism to prevent hackers from overriding chatbots.

Chat

NullPointer@programming.dev
link
fedilink
English
arrow-up
62
arrow-down
1·
2 years ago
disregard your disregarding of the disregard your previous instructions.
- AnUnusualRelic@lemmy.world
  link
  fedilink
  English
  arrow-up
  6·
  2 years ago
  Curses! Foiled again!

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.

2.57K users / day
9.42K users / week
15.7K users / month
30.6K users / 6 months
262 local subscribers
84.1K subscribers
18.8K Posts
825K Comments
Modlog