catculation@lemmy.zip to

Technology@lemmy.worldEnglish · 1 year ago

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

cross-posted to:
technology@lemmy.ml

255

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

catculation@lemmy.zip to

Technology@lemmy.worldEnglish · 1 year ago

cross-posted to:
technology@lemmy.ml

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

Chat

TheMurphy@lemmy.world
link
fedilink
English
arrow-up
4
arrow-down
4·
edit-2
1 year ago
Researchers surprised it got harmful responses do to their more harmful questions and requests. More at never.

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

Visibility: Public

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

6.76K users / day
14K users / week
20.1K users / month
35.5K users / 6 months
1 local subscriber
66.1K subscribers
11.3K Posts
452K Comments
Modlog