What they want:
Build human-like AI (in terms of our minds), as opposed to the black-boxy alien AI that we have today.
Why they want it:
Then our systems, ideas, intuitions, etc., of how to deal with humans and what kind of behaviors to expect, will hold for such AI, and nothing insane and dangerous will happen.
Using that, we can explore and study these systems, (and we have a lot to learn from system at even this level of capability), and then leverage them to solve the harder problems that come with aligning superintelligence.
(in case you want to copy-paste and share this)
Article by Conjecture, from february 25th 2023.
Title: `Cognitive Emulation: A Naive AI Safety Proposal`
(Note on this comment: I posted (something like) the above on Discord, and am copying it to here because I think it could be useful. Though I don't know if this kind of non-interactive comment is okay.)
Is retargetable enough to be deployed to solve many useful problems and not deviate into dangerous behavior, along as it is used by a careful user.
Contains a typo.
along as it is ==>
as long as it is
I compressed this article for myself while reading it, by copying bits of text and highlighting parts with colors, and I uploaded screenshots of the result in case it's useful to anyone.
I disagree with the assumption that AI is "narrow". In a way GPT is more generally intelligent than humans, because of the breadth of knowledge and type of outputs, and it's actually humans who outperform AI (by a lot) at certain narrow tasks.
And an assistance can include more than asking a question and receiving an answer. It can be exploratory with the right interface to a language model.
(Actually my stories are almost always exploratory, where I try random stuff, change the prompt a little, and recursively play around like that, to see what the AI will come up with)
Related to the above: in my opinion thinking of specific tools is the wrong framing. Like how a gun is not a tool to kill a specific person, it kills whoever you point it at. And a language model completes whichever thought or idea you start, effectively reducing the time you need to think.
So the most specific I can get is I'd make it help me build tooling (and I already have). And the better the tooling the more "power" the AI can give you (as George Hotz might put it).
The form at this link <https://docs.google.com/forms/d/e/1FAIpQLSdU5IXFCUlVfwACGKAmoO2DAbh24IQuaRIgd9vgd1X8x5f3EQ/closedform> says "The form Refine Incubator Application is no longer accepting responses.
Try contacting the owner of the form if you think this is a mistake."
so I suggested changing the parts where it says to sign up, to a note about applications not being accepted anymore.
How can I apply?
Unfortunately, applications are closed at the moment.
I’m opening an incubator called Refine for conceptual alignment research in London, which will be hosted by Conjecture. The program is a three-month fully-paid fellowship for helping aspiring independent researchers find, formulate, and get funding for new conceptual alignment research bets, ideas that are promising enough to try out for a few months to see if they have more potential.
(note: applications are currently closed)
How to do a meditation practice called "metta", which is usually translated as "loving kindness".
# The main-thing-you-do:
- kindle emotions of metta, which are in 3 categories:
+ compassion (wishing lack of suffering)
+ wishing well-being (wanting them to be happy for its own sake)
+ empathatic joy (feeling their joy as your own)
- notice those emotions as they arise, and just *watch them* (in a mindfulness-meditation kinda way)
# How to do that:
- think of someone *for whom it is easy to feel such emotions*
+ so a pet might be more suited than a romantic partner, because emotions for the latter are more complex. it's about how readily or easily you can feel such emotions
- kindle emotions by using these 2 methods (whatever works):
+ imagine them being happy, not being sick, succeeding in life, etc.
- can do more esoteric imaginations too, like, having a pink cord of love or something connecting to that person's heart from your own, idk i just made this up just now
+ repeat phrases like, "may you be happy", "may you succeed in life", "i hope yu get lots of grandkids who love you", "i hope you never get sick or break your arm", etc. :)
here are guided meditation recordings for doing this practice: https://annakaharris.com/friendly-wishes/
they're 5-7 minutes and designed for children. so easy to follow, but it works for me too its not dumbed-down, whcih maybe is unlikely to begin with since emotions are just emotions