heyWhatsay@slrpnk.net to

Fuck AI@lemmy.worldEnglish · 8 months ago

AI Researchers Say They've Invented Incantations Too Dangerous to Release to the Public

8

36

AI Researchers Say They've Invented Incantations Too Dangerous to Release to the Public

heyWhatsay@slrpnk.net to

Fuck AI@lemmy.worldEnglish · 8 months ago

8

A team of researchers found prompts that are so effective at tricking AI models that they're keeping them under wraps.

Chat

BlackLaZoR@fedia.io
link
fedilink
arrow-up
3·
8 months ago
Does these incantations involve labubu and summon Trump or Satan?

Fuck AI@lemmy.world

fuck_ai@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: [email protected]

“We did it, Patrick! We made a technological breakthrough!”

A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.

AI, in this case, refers to LLMs, GPT technology, and anything listed as “AI” meant to increase market valuations.

Visibility: Public

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

1.21K users / day
4.54K users / week
7.77K users / month
17K users / 6 months
1 local subscriber
7.77K subscribers
3.98K Posts
60.8K Comments
Modlog