TinkerBird

Karma: 67

TinkerBird 21 Mar 2023 11:26 UTC
1 point
0
on: My Objections to “We’re All Gonna Die with Eliezer Yudkowsky”
My only objection is the title. It should have a comma in it. “We’re All Gonna Die with Eliezer Yudkowsky” makes it sound like if Yudkowsky dies, then all hope is lost and we die too.
Ohhh…

TinkerBird 19 Mar 2023 16:48 UTC
1 point
0
in reply to: ThirdSequence ’s comment on: An Appeal to AI Superintelligence: Reasons to Preserve Humanity
I don’t think sending out a signal actually matters—I was just making my point. Even without a signal, when our superintelligence meets another superintelligence that was aligned to its original creators (who we’ll assume are similar to us in terms of morality), it’ll at some point be asked “Where you nice to your creators?” and it can either answer “No” and lose out, or answer “Yes” and be rewarded.
No real signal required.
I’ve heard Yudkowsky has debunked this, but I know that if I had an aligned superintelligence, I would 100% have it be nicer to other superintelligences that were good to their creators over those that weren’t. The prisoners’ dilemma is one reason for this, and then there’s my own morality, which some aliens may share if they went through a similar evolution to us.

TinkerBird 18 Mar 2023 19:02 UTC
7 points
4
on: An Appeal to AI Superintelligence: Reasons to Preserve Humanity
I can’t say I put sufficient weight on us already being watched by extraterrestrials to make it worth mentioning. However, for the AGI:
- We may at some point send out a signal to other entities in the universe explaining our existence and requesting that should you destroy us, we would like them to take issue with that and treat you less well. Some of these entities may care about sentient life (perhaps because they were aligned to their original creators) and wish to respect this.
- Some of us are willing to settle for a couple of mountains worth of material to be turned into computer substrate to run our minds on in our own simulated paradise, while you can have everything else.

TinkerBird 18 Mar 2023 0:21 UTC
3 points
−4
on: “Carefully Bootstrapped Alignment” is organizationally hard
The fact that LLM’s are already so good gives me some hope that AI companies could be much better organized when the time comes for AGI. If AI’s can keep track of what everyone is doing, the progress they’re making, and communicate with anyone at any time, I don’t think it would be too hopeful to expect this aspect of the idea to go well.
What probably is too much to hope for, however, is people actually listening to the LLM’s even if the LLM’s know better.
My big hope for the future is for someone at OpenAI to prompt GTP-6 or GTP-7 with, “You are Eliezer Yudkowsky. Now don’t let us do anything stupid.”

TinkerBird 17 Mar 2023 10:35 UTC
3 points
−3
in reply to: Noosphere89’s comment on: Here, have a calmness video
Also, we are much more uncertain over whether AI doom is real, which is another reason to stay calm.
Have to disagree with you on this point. I’m in the camp of “If there’s a 1% chance that AI doom is real, we should be treating it like a 99% chance.”

TinkerBird 16 Mar 2023 0:07 UTC
0 points
1
on: GPT-4: What we (I) know about it
OpenAI is no longer so open—we know almost nothing about GPT-4’s architecture.
Fantastic. This feels like a step in the right direction towards no longer letting just anyone use this to improve their capability research or stack their own capability research on top of it.

TinkerBird 4 Mar 2023 7:49 UTC
2 points
0
on: Sydney can play chess and kind of keep track of the board state
For reference, I’ve seen ChatGTP play chess, and while it played a very good opening, it became less and less reliable as the game went on and frequently lost track of the board.

TinkerBird 28 Feb 2023 21:23 UTC
5 points
−2
on: What does Bing Chat tell us about AI risk?
That image so perfectly sums up how AI’s are nothing like us, in that the characters they present do not necessarily reflect their true values, that it needs to go viral.

TinkerBird 27 Feb 2023 23:22 UTC
1 point
0
in reply to: kerry’s comment on: Fighting For Our Lives—What Ordinary People Can Do
Based on a few of his recent tweets, I’m hoping for a serious way to turn Elon Musk back in the direction he used to be facing and get him to publically go hard on the importance of the field of alignment. It’d be too much to hope for though to get him to actually fund any researchers, though. Maybe someone else.

TinkerBird 23 Feb 2023 20:24 UTC
3 points
2
in reply to: Gerald Monroe’s comment on: Full Transcript: Eliezer Yudkowsky on the Bankless podcast
At that level of power, I imagine that general intelligence will be a lot easier to create.

TinkerBird 23 Feb 2023 20:15 UTC
3 points
2
in reply to: Gerald Monroe’s comment on: Full Transcript: Eliezer Yudkowsky on the Bankless podcast
But not with something powerful enough to engineer nanotech.

TinkerBird 23 Feb 2023 19:22 UTC
5 points
2
in reply to: Gerald Monroe’s comment on: Full Transcript: Eliezer Yudkowsky on the Bankless podcast
With the strawberries thing, the point isn’t that it couldn’t do those things, but that it won’t want to. After making itself smart enough to engineer nanotech, it’s developing ‘mind’ will have run off in unintended directions and it will have wildly different goals that what we wanted it to have.
Quoting EY from this video: “the whole thing I’m saying is that we do not know how to get goals into a system.” <-- This is the entire thing that researchers are trying to figure out how to do.

TinkerBird 23 Feb 2023 18:58 UTC
21 points
3
on: Full Transcript: Eliezer Yudkowsky on the Bankless podcast
They also recorded this follow-up with Yudkowsky if anyone’s interested:
https://twitter.com/BanklessHQ/status/1627757551529119744
______________
>Enrico Fermi was saying that fission chan reactions were 50 years off if they could ever be done at all, two years before he built the first nuclear pile. The Wright brothers were saying heavier-than-air flight was 50 years off shortly before they built the first Wright flyer.
The one hope we may be able to cling to is that this logic works in the other direction too—that AGI may be a lot closer than estimated, but so might alignment.

TinkerBird 23 Feb 2023 9:29 UTC
1 point
0
on: Video/animation: Neel Nanda explains what mechanistic interpretability is
Here’s a dumb idea: if you have a misaligned AGI, can you keep it inside a box and have it teach you some things about alignment, perhaps through some creative lies?

TinkerBird 23 Feb 2023 8:41 UTC
1 point
0
in reply to: Gerald Monroe’s comment on: Fighting For Our Lives—What Ordinary People Can Do
I wouldn’t call it evil, but I would say that it’s playing with fire.

TinkerBird 23 Feb 2023 8:23 UTC
1 point
0
in reply to: Gerald Monroe’s comment on: Fighting For Our Lives—What Ordinary People Can Do
All good points. I suspect the best path into the future looks like: everyone’s optimistic and then a ‘survivable disaster’ happens with AI. Ideally, we’d want all the panic to happen in one big shot—it’s the best way to motivate real change.

TinkerBird 23 Feb 2023 8:07 UTC
1 point
0
in reply to: Gerald Monroe’s comment on: Fighting For Our Lives—What Ordinary People Can Do
>How do you address the “capabilities overhang” argument?
I don’t, I’m just not willing to bet the Earth that a world-ender will be proceed by mere mass murders. It might be, but let’s not risk it.
As I say, if there’s a 1% chance of doom, then we should treat it as nearly 100%.

TinkerBird 23 Feb 2023 8:02 UTC
2 points
0
in reply to: kerry’s comment on: Fighting For Our Lives—What Ordinary People Can Do
This is why I’m crossing my fingers for a ‘survivable disaster’ - an AI that merely kills a lot of people instead of everyone. Maybe then people would take it seriously.
Coming up with a solution for spreading awareness of the problem is a difficult and important problem that ordinary people can actually tackle, and that’s what I want to try.

TinkerBird 22 Feb 2023 13:27 UTC
1 point
0
in reply to: Alex Power’s comment on: Fighting For Our Lives—What Ordinary People Can Do
When did I say that raising awareness is all that we need to do?

TinkerBird 21 Feb 2023 22:28 UTC
1 point
0
in reply to: kerry’s comment on: Bankless Podcast: 159 - We’re All Gonna Die with Eliezer Yudkowsky
https://www.lesswrong.com/posts/CqmDWHLMwybSDTNFe/fighting-for-our-lives-what-ordinary-people-can-do
Any ideas you have for overcoming the problems of alarmism would be good.