AI’s safety features can be circumvented with poetry, research finds

www.theguardian.com

AI’s safety features can be circumvented with poetry, research finds

www.theguardian.com

git [he/him, comrade/them]@hexbear.net to

news@hexbear.netEnglish · 14 days ago

Poems containing prompts for harmful content prove effective at duping large language models

Chat

bless@lemmy.ml
link
fedilink
English
arrow-up
4·
13 days ago
Just like grandma used to while tucking me in bed

news@hexbear.net

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: !news@hexbear.net

Welcome to c/news! Please read the Hexbear Code of Conduct and remember… we’re all comrades here.

Rules:

– PLEASE KEEP POST TITLES INFORMATIVE –

Overly editorialized titles, particularly if they link to opinion pieces, may get your post removed.

All posts must include a link to their source. Screenshots are fine IF you include the link in the post body.

If you are citing a Twitter post as news, please include not just the twitter.com URL but also Xcancel.com (or another Nitter instance). There is also a Firefox extension that can redirect Twitter links to a Nitter instance, such as Libredirect or archive them as you would any other reactionary source (archive.today, web.archive.org, ghostarchive.org). Twitter screenshots still need to be sourced or they will be removed.

Mass-tagging comm moderators across multiple posts like a broken Markov chain bot will result in a comm ban.

Repeated consecutive posting of reactionary sources, fake news, misleading / outdated news, false alarms over ghoul deaths, and/or shitposts will result in a comm ban.

Neglecting to use content warnings or NSFW when dealing with disturbing content will be removed until in compliance. Users who are consecutively reported due to failing to use content warnings or NSFW tags when commenting on or posting disturbing content will result in the user being banned.

Using April 1st as an excuse to post fake headlines, like the resurrection of Kissinger while he is still fortunately dead, will result in the poster being thrown in the gamer gulag and be sentenced to play and beat trashy mobile games like ‘Raid: Shadow Legends’ in order to be rehabilitated back into general society.

Visibility: Public

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

436 users / day
1.05K users / week
1.65K users / month
3.42K users / 6 months
1 local subscriber
24.5K subscribers
5.03K Posts
81.5K Comments
Modlog