@[email protected] to

[email protected]English • 1 year ago

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

cross-posted to:
[email protected]

255

ASCII art elicits harmful responses from 5 major AI chatbots

arstechnica.com

@[email protected] to

[email protected]English • 1 year ago

cross-posted to:
[email protected]

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

Chat

Ghostalmedia
link
fedilink
English
28•1 year ago
Some BODY
- @[email protected]
  link
  fedilink
  English
  15•1 year ago
  Once
  - @[email protected]
    link
    fedilink
    English
    16•1 year ago
    Told me
    - @[email protected]
      link
      fedilink
      English
      13•1 year ago
      The World is
      - @[email protected]
        link
        fedilink
        English
        10•1 year ago
        Co-co-co-COMBO BREAKEERR!!!

[email protected]

[email protected]

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

9.52K users / day
12.2K users / week
16.8K users / month
38.1K users / 6 months
71K subscribers
15.1K Posts
657K Comments
Modlog