this post was submitted on 19 Jul 2024
440 points (98.5% liked)

Technology

59982 readers
3902 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 2 years ago
MODERATORS
L3s
[email protected]
[email protected]
L4s
enu
440
OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole (www.theverge.com)
submitted 5 months ago by [email protected] to c/technology
101 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] kometes 11 points 5 months ago (2 children)

What happens if you make a mistake with your initial instructions?

[–] Avatar_of_Self 7 points 5 months ago

You'd change the system prompt, just like now. If you mean in the session, I'm sure it'll ignore your session's prompt's instructions as normal but if not, I guess you'd just start a new session prompt.

[–] vxx 3 points 5 months ago* (last edited 5 months ago)

The "issue" is that people were able to override bots on twitter with that method and make them feed their own instructions.

I saw it first time being used on a Russian propaganda bot.