Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:

I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.

Aaaand I got blocked

(page 3) 50 comments

sorted by: hot top controversial new old

[–] egeres@lemmy.world 7 points 2 years ago

Hahahh, we are gonna miss these jailbreaks on aligned LLMs in a couple of years when they are all patched

[–] DebOtaku21@lemm.ee 7 points 2 years ago

Genius

[–] GrammatonCleric@lemmy.world 6 points 2 years ago

Absolute win

[–] Xylia@artemis.camp 5 points 2 years ago (1 children)

I decided I’d also inquire about the books2 dataset, and this is what I got. (GPT-4 mode).

[–] Moonrise2473@feddit.it 6 points 2 years ago (2 children)

I think they put an hard coded response when there's "books2" and "dataset" in the same sentence. Later I'll try with gpt4all (models are run locally on your PC) to see if the uncensored models will reply honestly on that 😂

load more comments (2 replies)

[–] satans_crackpipe@lemmy.world 5 points 2 years ago

The unintentional satire in the replies is sooooo delicious.

load more comments