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

7

0

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

7

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

Chat

stangel@lemmy.world
link
fedilink
English
arrow-up
0·
1 year ago
Bug bounty programs are a thing.
- spujb@lemmy.cafe
  link
  fedilink
  English
  arrow-up
  0
  arrow-down
  1·
  1 year ago
  yes i am aware? are they being used by openai?

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.

2.91K users / day
9.58K users / week
17.3K users / month
20.4K users / 6 months
1 local subscriber
69.4K subscribers
2.79K Posts
44.8K Comments
Modlog