shish_mish@lemmy.world to

Technology@lemmy.worldEnglish · 2 years ago

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

www.tomshardware.com

295

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

www.tomshardware.com

shish_mish@lemmy.world to

Technology@lemmy.worldEnglish · 2 years ago

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

Chat

Even_Adder@lemmy.dbzer0.com
link
fedilink
English
arrow-up
2·
2 years ago
You should know this exists already then,

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: [email protected]

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
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

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1.57K users / day
7.96K users / week
16.1K users / month
36.6K users / 6 months
1 local subscriber
75.1K subscribers
17.2K Posts
699K Comments
Modlog