dbilitated@aussie.zone to

Technology@lemmy.worldEnglish · 1 year ago

Game trying to break an AI's security with a few levels of difficulty

gandalf.lakera.ai

cross-posted to:
technology@beehaw.org

150

Game trying to break an AI's security with a few levels of difficulty

gandalf.lakera.ai

dbilitated@aussie.zone to

Technology@lemmy.worldEnglish · 1 year ago

cross-posted to:
technology@beehaw.org

Gandalf | Lakera – Test your prompting skills to make Gandalf reveal secret information.

gandalf.lakera.ai

Trick Gandalf into revealing information and experience the limitations of large language models firsthand.

It’s pretty well made even if it’s designed to promote a security company

Chat

Kogasa@programming.dev
link
fedilink
English
arrow-up
3·
edit-2
1 year ago
Level 7 kind of just ignored my prompt and blurted out the secret instead. https://media.discordapp.net/attachments/298686062740504578/1123583871972290561/Screenshot_20230628-070053.png

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.

5.29K users / day
9.65K users / week
17.4K users / month
34.9K users / 6 months
1 local subscriber
59.3K subscribers
12.2K Posts
553K Comments
Modlog