A New Attack Impacts ChatGPT—and No One Knows How to Stop It

www.wired.com

cross-posted to:
technology@lemmy.ml

A New Attack Impacts ChatGPT—and No One Knows How to Stop It

www.wired.com

c0mmando@links.hackliberty.orgM to

Artificial Intelligence@links.hackliberty.org · 1 year ago

cross-posted to:
technology@lemmy.ml

Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame.

You must log in or # to comment.

Chat

Artificial Intelligence@links.hackliberty.org

generative_ai@links.hackliberty.org

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: !generative_ai@links.hackliberty.org

Generative artificial intelligence or generative AI is a type of artificial intelligence system capable of generating text, images, or other media in response to prompts. Generative models learn the patterns and structure of the input data, and then generate new content that is similar to the training data but with some degree of novelty.

Rules

Don’t do unto others what you don’t want done unto you.
No Porn, Gore, or NSFW content. Instant Ban.
No Spamming, Trolling or Unsolicited Ads. Instant Ban.
Stay on topic in a community. Please reach out to an admin to create a new community.

Visibility: Public

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

1 user / day
1 user / week
1 user / month
26 users / 6 months
1 local subscriber
225 subscribers
23 Posts
13 Comments
Modlog

mods:
c0mmando@links.hackliberty.org