Technology@lemmy.worldEnglish • 1 year ago

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

www.tomshardware.com

293

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

www.tomshardware.com

Technology@lemmy.worldEnglish • 1 year ago

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

You must log in or register to comment.

HotTopNewOld

Chat

@Mastengwe@lemm.ee
link
fedilink
English
32•1 year ago
Safe AI cannot exist in the same world as hackers.

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 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, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

415 users / day
2.82K users / week
5.72K users / month
14.3K users / 6 months
1 subscriber
14.3K Posts
606K Comments
Modlog