silence7@slrpnk.net to

Technology@lemmy.worldEnglish · 11 months ago

How Googlers cracked an SF rival's tech model with a single word | A research team from the tech giant got ChatGPT to spit out its private training data

165

How Googlers cracked an SF rival's tech model with a single word | A research team from the tech giant got ChatGPT to spit out its private training data

silence7@slrpnk.net to

Technology@lemmy.worldEnglish · 11 months ago

How Googlers cracked OpenAI's ChatGPT with a single word

A research team from Bay Area tech giant Google got OpenAI's ChatGPT to spit out its private training data in a new study.

Basically: you ask for poems forever, and LLMs start regurgitating training data:

Chat

∟⊔⊤∦∣≶@lemmy.nz
link
fedilink
English
arrow-up
1·
11 months ago
The neural net doesn’t change of course, but previous text is used as context for the next generation.

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 content.
Be excellent to each another!
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, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be 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
8.37K users / week
17.3K users / month
25.6K users / 6 months
1 local subscriber
59.2K subscribers
6.54K Posts
222K Comments
Modlog