silence7@slrpnk.net to

Technology@lemmy.worldEnglish · 1 year 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

cross-posted to:
technology@lemmy.world

140

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 · 1 year ago

cross-posted to:
technology@lemmy.world

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

silence7@slrpnk.netOP
link
fedilink
English
arrow-up
5·
1 year ago
They gave OpenAI 60 days notice before publishing so that they could add a new guardrail. That’s surely what happened.

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.

4.13K users / day
10K users / week
16.9K users / month
28.7K users / 6 months
1 local subscriber
59.4K subscribers
7.6K Posts
224K Comments
Modlog