ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

253

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

catculation to

Technology@lemmy.worldEnglish · 9 months ago

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

Chat

randomaccount43543@lemmy.world
link
fedilink
English
arrow-up
19
arrow-down
4·
9 months ago
Once
- Illuminati@lemmy.world
  link
  fedilink
  English
  arrow-up
  20
  arrow-down
  4·
  9 months ago
  Told me
  - dust_accelerator@discuss.tchncs.de
    link
    fedilink
    English
    arrow-up
    17
    arrow-down
    4·
    9 months ago
    The World is
    - DreadPotato@sopuli.xyz
      link
      fedilink
      English
      arrow-up
      18
      arrow-down
      8·
      9 months ago
      Co-co-co-COMBO BREAKEERR!!!

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: [email protected]

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 another!
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, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

Visibility: Public

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

2.89K users / day
7.9K users / week
14.6K users / month
32.4K users / 6 months
558 local subscribers
60K subscribers
13.2K Posts
569K Comments
Modlog