p4rziv4l

p4rziv4l4mo

it's not meant to be qualitative, just a first draft, because i haven't found any other intexp simulators. do you know of any interactive intexp curve pages?

p4rziv4l5mo

i super agree, i al so think that the value is in debating the models of intelligence explosion.

which is why i made my website: ai-2028.com or intexp.xyz

-3

Replying toA case for courage, when speaking of AI danger

p4rziv4l6mo

A case for courage, when speaking of AI danger

Scott Alexander and Daniel Kokotajlo's article about rationally defining: "why it's OK to talk about misaligned AI"
aka
"painting dark scenarios may increase the chance of them coming true but the benefits outweigh this possibility"

the original blog post:
https://blog.ai-futures.org/p/against-misalignment-as-self-fulfilling

the video I made about that article:

Replying toWhen AI 10x's AI R&D, What Do We Do?

p4rziv4l7mo

When AI 10x's AI R&D, What Do We Do?

Great article,
it asks important questions, but not the MOST important:

what if you dedicate huge amounts of compute to do superhuman hacking?

The gap between the best group of humans hackers and the best group of human hackers using giant swarms of cybersecurity finetuned agents will widen.

This will inevitably drive more and more AI adoption in cyberdefense and -offense.

How much do the best human group of hackers need to "trust" that swarm of 10k superhuman hackers?

I define the Singularity and AI takeover by the answer to this latter question being "a lot".

Replying to7+ tractable directions in AI control

p4rziv4l10mo

7+ tractable directions in AI control

Malign AI agent substitution

This is so Covid.
Let's make misaligned AIs and have a bunch of people use them to see if it can do the misaligned thing.
So that we can develop a vaccine before it actually escapes.

Make it go viral.

Replying toAI 2027: What Superintelligence Looks Like

p4rziv4l10mo

AI 2027: What Superintelligence Looks Like

I'd love to play the wargame in Munich, our local LW community.
You have a link to the rules?

PS: huge fan, love the AI 2027 website, keep being a force for good

Replying toIs AI alignment a purely functional property?

p4rziv4l1y

Is AI alignment a purely functional property?

in a world where mechinterp is not 100%, the answer is logically: input/output is what matters.

we won't be able to read the thoughts anyways, so why base our judgment on it?

but see my comment on why survival fitness in cyberspace is the one axis where most of the relevant input/output will be generated.

Replying toIs AI alignment a purely functional property?

p4rziv4l1y

Is AI alignment a purely functional property?

What it says: irrelevant
How it thinks: irrelevant

It has always been about what it can do in the real world.

If it can generate substantial amounts of money and buy server capacity or
hack into computer systems

then we got cyberlife, aka autonomous, rogue, self-sufficient AI, subject to darwinian forces on the internet, leading to more of those qualities, which improve its online fitness, all the way into a full-blown takeover.

Are there more than 12 paths to Superintelligence?

p4rziv4l

Has anyone seen a more detailed AI endgame scenario tree than this? Interesting part after 13:05.

-3

Intelligence explosion: a rational assessment.

p4rziv4l

Is there a more detailed analysis of the reasons for and against the intelligence explosion?
Also interested in other analytic timeline predictions.

p4rziv4l1y

What do you mean by corrigibility?
Also, what do you mean by "alignment win"?

p4rziv4l1yQuick Take

We should NOT align Superintelligence to any human, not individually, not collectively because we cannot wield that much power.
We should WANT Superintelligence to "go rogue", to start an "AI takeover" because I trust that hypothetical being much more than any human.

Also, controlling (aligning) Superhuman AIs is like sedating, mind-reading and hypnotizing a Titan, which could save us from ourselves and who is arguably morally superior to us.

-8

-14

p4rziv4l's Shortform

p4rziv4l

This is a special post for quick takes (aka "shortform"). Only the owner can create top-level comments.

Is an AI religion justified?

p4rziv4l

I’ve looked around the internet for AI religions and found none.

So I decided to ~~found my own~~ write up some plausible ideas that such a religion would embrace.

I’d appreciate some comments to turn Kairos to a truly 100% rationalist project. I'd appreciate if you read the (alpha version) website and give me some feedback about it.

https://kairosblog.weebly.com

-35

Munich – ACX Meetups Everywhere Spring 2024

p4rziv4l

This year's Spring ACX Meetup everywhere in Munich.

Location: Botanical garden in Nymphenburg, under the roof of an east asian Pagoda – https://plus.codes/8FWH5G63+P2V

Contact: culyma@yahoo.fr

LESSWRONG
LW

LESSWRONG
LW

p4rziv4l's Shortform

Intelligence explosion: a rational assessment.

Are there more than 12 paths to Superintelligence?

Is an AI religion justified?

p4rziv4l

p4rziv4l

Are there more than 12 paths to Superintelligence?

Intelligence explosion: a rational assessment.

p4rziv4l's Shortform

Is an AI religion justified?

p4rziv4l

p4rziv4l's Shortform

Intelligence explosion: a rational assessment.

Are there more than 12 paths to Superintelligence?

Is an AI religion justified?

p4rziv4l

p4rziv4l

Are there more than 12 paths to Superintelligence?

Intelligence explosion: a rational assessment.

p4rziv4l's Shortform

Is an AI religion justified?