Researchers find multiple ways to bypass AI chatbot safety rules

thehill.com

cross-posted to:
news@lemmy.world

Researchers find multiple ways to bypass AI chatbot safety rules

thehill.com

linkbot@lemmy.linkMB to

US Politics@lemmy.linkEnglish · 1 year ago

cross-posted to:
news@lemmy.world

You must log in or register to comment.

Chat

US Politics@lemmy.link

news_us_politics@lemmy.link

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: !news_us_politics@lemmy.link

Community locked: only moderators can create posts. You can still comment on posts.

Lemmy Link Matrix Chat

Hop into our room #lemmylink:matrix.org on Matrix to provide any feedback or chat with us.

Rules

No abusive language
No bigotry
No advertising
No pornography

Feeds

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
2 users / 6 months
1 local subscriber
1 subscriber
2.22K Posts
331 Comments
Modlog