Technology@lemmy.worldEnglish · 2 years ago

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

cross-posted to:
technology@lemmy.ml

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

catculation@lemmy.zip to

Technology@lemmy.worldEnglish · 2 years ago

cross-posted to:
technology@lemmy.ml

LLMs are trained to block harmful responses. Old-school images can override those rules.

Chat

Deebster@programming.dev
link
fedilink
English
arrow-up
0·
2 years ago
Clever work, well done to the researchers.

Technology@lemmy.world

technology@lemmy.world

Create a post

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 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.

501 users / day
1.7K users / week
3.93K users / month
12.5K users / 6 months
0 local subscribers
76.3K subscribers
14.9K Posts
485K Comments
Modlog