Jon P

Karma: 9

Jon P 14 Jul 2022 10:09 UTC
1 point
0 ∶ 0
in reply to: Jens Brandt’s comment on: E.A. Megaproject Ideas
Yeah I think there is some similarity there. I think I was assuming that the matches are made algorithmically, it’s just that they are made at a sustainable pace rather than in a flood at the beginning.
Thanks for the comment :)

Jon P 13 Jul 2022 11:19 UTC
1 point
0 ∶ 0
on: On how various plans miss the hard bits of the alignment challenge
This is a nice writeup and summary.
I personally think that this is yet more evidence that formal control is a path which is more promising than others. If you can formally prove that your code, when properly executed, has certain properties then that gives you some hope that those properties will be durable during and after a hard left turn.
Things like, if you had a magic wand, formally proving that any AI designed by a formally controlled AI will also be formally controlled. That way even if it whooshes and completely redesigns itself there is still some hope.
I would love to see the amount of resources going into formal methods be multiplied by 10x or 100x, I think if we built a really solid field, where all of modern mathematics and computer science is formalised and people write formally verified code by default because it’s safer and there are good libraries to do that, then in that environment the control problem becomes easier, if still extremely hard.

Jon P 21 Mar 2022 10:15 UTC
4 points
0 ∶ 0
on: E.A. Megaproject Ideas
I’ve been thinking quite a lot about the problems of dating apps and had some ideas and would be interested in talking about it.
1. There’s a general problem with people who are a bit clueless / don’t have much intimate experience acting in a cold way and sending odd and offputting messages. This can be a vicious spiral where it’s hard to connect and get the experience to improve their social skills.
2. There’s a problem of creepy and aggressive people sending horrible messages and unwanted nudes, they may be just clueless as above or they may be malicious.
3. Sometimes on dating sites the gender ratio is skewed and men can end up being ignored and women can end up being flooded with messages as soon as they put a profile up. Both of these are bad experiences.
I’d suggest a dating site that improves these things in the following ways.
1. The sign up / onboarding process is quite long. You pay some token fee, answer quite a lot of questions to fill out a reasonable profile and there’s quite a lot of explanations and tests about consent, emotional awareness and the culture of the site. I like the channel “sexplanations” on youtube for instance for this kind of accessible, easily digestible, educational material.
2. If one of the partners in a chat requests it the mods are allowed to read all messages that are sent on the site. This needs to be flagged up front and consented too, however it gives the mods a lot of power to remove people who send creepy or aggressive messages. It would also be expected that people wouldn’t share contact details outside the site early on.
3. When people are introduced they are “introduced” in a managed way. It’s a 1 on 1 pairing where both profiles match relatively well and each person has indicated they are ready to meet someone new. This means people won’t get flooded and can meet new people when they want to and properly evaluate a reasonable match.
I feel like this could lead to an experience which is quite heavily managed and structured which is great for people who maybe aren’t so confident and aren’t sure how to go forward. I think it would be great if one of the main goals was teaching people the skills of building great relationships rather than just assuming that if you connect people that’s enough for it to all work out on it’s own.

Jon P 20 Mar 2022 21:48 UTC
7 points
0 ∶ 0
in reply to: Nathan Young’s comment on: What EAG sessions would you like on AI?
I think Rob Miles youtube channel is a good resource for beginners, he’s got a lot of nice videos there and he is a good speaker.

Jon P 18 Mar 2022 20:19 UTC
1 point
0 ∶ 0
in reply to: Matthew_Barnett’s comment on: My current thoughts on the risks from SETI
Yeah I think that’s a good point. I mean I could see how you could send a civilisation the blueprints for atomic weapons and hope that they wipe themselves out or something, that would be very feasible.
I guess I’m a bit more skeptical when it comes to AI. I mean it’s hard to get code to run and it has to be tailored to the hardware. And if you were going to teach them enough information to build advanced AIs I think there’d be a lot of uncertainty about what they’d end up making, I mean there’d be bugs in the code for sure.
It’s an interesting argument though and I can really see your perspective on it.

Jon P 16 Mar 2022 16:48 UTC
1 point
0 ∶ 0
on: My current thoughts on the risks from SETI
Nice writeup.
“The primary theory is that alien civilizations could continuously broadcast a highly optimized message intended to hijack or destroy any other civilizations unlucky enough to tune in.”
One question I have is whether this is possible and how difficult it is?
I mean if I took a professional programmer and told them to write a message which would hijack another computer when sent to it isn’t that extremely hard to do? I mean even if you already know about human programming you have no idea what system that machine is running or how it is structured.
Isn’t then that problem like 10,000x harder when dealing with a totally different species and their computer equipment? The sender of the message would have no idea what computational structures they were using and absolutely no idea of the syntax or coding conventions? I mean even using binary rather than trinary or decimal is a choice?