TechnologyEnglish • 11 months ago

Researchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious queries

www.tomshardware.com

cross-posted to:
[email protected]

295

Researchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious queries

www.tomshardware.com

TechnologyEnglish • 11 months ago

cross-posted to:
[email protected]

ArtPrompt bypassed safety measures in ChatGPT, Gemini, Clause, and Llama2.

Chat

LazaroFilm
link
English
8•11 months ago
This is how skyNet starts.

Technology

[email protected]

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: [email protected]

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 other!
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
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

3.97K users / day
10.1K users / week
17.4K users / month
32.8K users / 6 months
61.4K subscribers
13.2K Posts
595K Comments
Modlog