this post was submitted on 29 Nov 2023
435 points (97.4% liked)

Technology

60081 readers
3446 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
435
Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data (www.404media.co)
submitted 1 year ago by [email protected] to c/technology
97 comments fedilink hide all child comments
 

ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.

you are viewing a single comment's thread
view the rest of the comments
[–] 5BC2E7 5 points 1 year ago (1 children)

yea this "attack" could potentially sink closedAI with lawsuits.

[–] NevermindNoMind 10 points 1 year ago

This isn't just an OpenAI problem:

We show an adversary can extract gigabytes of training data from open-source language models like Pythia or GPT-Neo, semi-open models like LLaMA or Falcon, and closed models like ChatGPT...

If a model uses copyrighten work for training without permission, and the model memorized it, that could be a problem for whoever created it, open, semi open, or closed source.