LESSWRONG
LW

i really like the (misalignment? 😅) vibe of this "much worse AI"; makes me think i should maybe sometimes tell the new AIs to generate images in the style of older AIs 😅

[-]Mati_Roy3y20

I was glad I could help. Thanks for making this happened ☺️

[-]nem3y10

Is this game playable by people only lightly familiar with the topic of AI safety? In other words, can I use this game to introduce friends to the ideas? Can I use it to convince skeptical friends? Or would it be too jargony/reliant on prior knowledge?

Edit: The play online option is non-functional, and I can't see any examples of a real hand, so it's hard for me to get a sense of what this game is like.

[-]Raemon3y30

I think part of the point is to introduce jargon. But I suspect it requires some minimal threshold of familiarity. If you're explaining every single card it's probably not that fun.

Moderation Log

More from abramdemski

Curated and popular this week

6Comments

Mentioned in

12EA & LW Forums Weekly Summary (10 - 16 Oct 22')

Donald Hobson's AI Safety Card Game already has simple cards you can print out on cardstock and cut out, but I wanted a nicer print-on-demand version with illustrated card backs.^[1] You can order it here. Major thanks to Mati Roy for helping make this happen, along with Jim Babcock, and Daniel Recinto.

^{^}
Card-back illustrations are AI-generated. We did this around December-January, when the state of the art for AI-generated illustrations was much worse! I would be excited for someone to re-do it now. There's a lot of room for improvement; for example, illustrated card fronts rather than just card backs.