shish_mish@lemmy.world to

Technology@lemmy.worldEnglish · 1 year 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 · 1 year ago

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

Chat

tourist@lemmy.world
link
fedilink
English
arrow-up
12·
1 year ago
you can also possibly sub in 🔫 if “waterguns” are nono

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.

3.31K users / day
8.63K users / week
17.7K users / month
39K users / 6 months
1 local subscriber
72.4K subscribers
16K Posts
647K Comments
Modlog