martinkunev

That's an interesting approach. My thinking at the time was that the number of vaccines administered gives legitimacy to the government's decisions. There were several other factors I considered besides the mandate:

All this happened while the vaccine was still in experimental stage in France.
There was political motivation to use all the vaccines already ordered. As far as I'm aware, the frequency of boosting was not justified by any science.
The benefits of the vaccines were exaggerated in public discourse ("you'll never get sick", "the virus will disappear", etc.). The priority was never honest communication but manipulating people.
There was an attempt to ridicule any opposition to the vaccine mandate as being motivated by woo-woo.

Just to be clear, I still wasn't sure I was making the right choice at the time and I would have gotten vaccinated if there was no mandate.

Leading by example

martinkunev

2mo

epistemic status: exploratory

With a few exceptions, individual actions have negligible large-scale impact, provided everything else remains unchanged. Then, what does it mean to lead by example and is it actually a valuable strategy?

My COVID experience

In 2021, the french government was seriously restricting the rights of people and businesses, with the stated goal of dealing with COVID. One aspect of this was imposing vaccination requirements for all kinds of activities. I was living in France at the time and considered this an overreach driven by motives other than people's health. I wasn't that concerned about the safety of the vaccine, but by how authoritarian the government was becoming (the details are irrelevant in... (read 639 more words →)

Replying toThe Moonrise Problem

martinkunev2mo

The Moonrise Problem

What is the relationship between convergent factorization and natural latent?

Replying toTowards a Typology of Strange LLM Chains-of-Thought

martinkunev3mo

Towards a Typology of Strange LLM Chains-of-Thought

this sounds like 3. Context Refresh

A year-long journey of getting fast internet in Paris

martinkunev

3mo

This is a story of how I struggled to get fast, stable internet connection in France in 2023. I find the story funny and also want to share how complicated and time-consuming the process was, as well as to complain about the utterly inadequate quality of service.

I happened to write this in french so the entire text is a translation by LLM (which I reviewed).

context: Free, Bouygues and Orange are big ISPs in France.

When I moved to my current address in 2020, I discovered that there was no fiber optic and I had to use ADSL. To compare, ADSL internet arrived in Bulgarian villages in the 2000s. I find it funny that... (read 2021 more words →)

Replying toMaybe Social Anxiety Is Just You Failing At Mind Control

martinkunev3mo

Maybe Social Anxiety Is Just You Failing At Mind Control

60% resolved my social anxiety

I'm honestly curious how you measure that. I've been asking myself "am I progressing with respect to social anxiety" and I don't have a good answer.

Fake media seems to be a fact of life now

martinkunev

3mo

epistemic status: my thoughts, backed by some arguments

With the advent of deep fakes, it has become very hard to know which image / sound / video is authentic and which is generated by an AI. In this context, people have proposed using software to detect generated content, usually aided by some type of watermarking. I don't think this type of solution would work.

Watermarking AI-generated content

One idea is to add a watermark to all content produced by a generative model. The exact technique would depend on the type of media - e.g. image, sound, text.

We could discuss various techniques with their advantages and shortcomings, but I think this is beside the point. The... (read 734 more words →)

Replying toDecision theory when you can't make decisions

martinkunev3mo

Decision theory when you can't make decisions

To me this reads as a definition of the term "free will" and then arguing against its existence.

If something can predict your action with better than random accuracy no matter how hard you try to prevent them, you don’t have free will over that action

The word "try" here hides lots of complexity and does some heavy lifting. Can you taboo it and rephrase that? Also, are you rejecting the computational theory of mind?

In the case of the brain-scanner, I’d say “the second before” just reflects the fact that taking an action in the physical world takes >0 time, and once you’ve made the decision to start the action you are no longer free to reverse it

If you take an agent embedded in the environment, I don't think there is a clear-cut boundary between "not yet made a decision" and "have made the decision". This abstraction just breaks down.

Replying toWhen is a mind me?

martinkunev4mo

When is a mind me?

My fear with the teleporter has always been the engineering details - can it get a consistent snapshot of me? what about the last moments after the snapshot and before the old copy is destroyed? can it reliably reconstruct me? what happens in case of a failure?

Assuming many worlds quantum mechanics, we should have similar anticipations for forking into two and for tossing a quantum coin.

Replying toWe are likely in an AI overhang, and this is bad.

martinkunev4mo

We are likely in an AI overhang, and this is bad.

There is no rollback when open-weight models are almost SOTA. Could we convince people like Zuck that open weights are too risky? I seriously doubt it.

Replying toFemale sexual attractiveness seems more egalitarian than people acknowledge

martinkunev5mo

Female sexual attractiveness seems more egalitarian than people acknowledge

There are some differences between what women consider attractive female traits and what men actually find attractive. The example I like to give is how some women enlarge their lips even though men (usually) don't find that attractive.

I think these are the relevant points:

Maybe women's sense of each other's beauty is more discriminating than men's.
Some women probably don't distinguish a sex symbol's actual physical attractiveness from the other characteristics that would make her rarely and especially appealing to women (like fame, wealth, etc.), and they're neglecting to account for these factors being less salient to men.

Replying toCorrigibility, Much more detail than anyone wants to Read

martinkunev5mo

Corrigibility, Much more detail than anyone wants to Read

This:

Might agent rewrite agent $a$ 's brain to make agent $a$ better satisfy agent $b$ 's utility function? Most forms of wire-heading inherently limit the ability of agents to affect the future

and this

We have not proved that agent $b$ does not try to affect agent $a$ 's utility function (in fact, I expect in many cases agent $b$ does try to influence agent $a$ 's utility function).

appear to be in conflict. Are you trying to say that depending on the circumstances b may try to influence a's utility function or avoid doing so?

Replying toDo you even have a system prompt? (PSA / repo)

martinkunev6mo

Do you even have a system prompt? (PSA / repo)

How important is it to keep the system prompt short? I guess this would depend on the model, but does anybody have useful tips on that?

Open weights != Open source

martinkunev

6mo

Disagreements degenerate into debates about word usage way too often and such debates are usually pointless. However, sometimes words can mislead or provoke emotional reactions and in those cases word usage becomes important. This is one of those cases.

Many modern AI models, such as those typically used for text or image generation, consist mainly of a huge neural network. The AI models, for which parameters (a.k.a. weights) are freely distributed on the internet came to be known as open weight models. This is in contrast to other models, whose parameters are kept secret on some servers and are only accessible through APIs or web interfaces.

Some^[1] have instead used the term open source to... (read 721 more words →)

Subjective experience is most likely physical

martinkunev

8mo

Here’s the argument that convinced me subjective experience is physical. I don't claim to understand subjective experience, I just see good reasons to believe it's physical rather than non-physical. I'll point out in particular some flaws of panpsychism and dualism.

I will be making some assumptions so that I can concentrate on the key points. I will not give an exhaustive list of those assumptions, but they include things like evolution by natural selection and the existence of physical reality. I think for most of the audience here the assumptions would seem natural so I don't feel the need to discuss them in depth. If this is not the case for you, this... (read 969 more words →)

Understanding Agent Preferences

martinkunev

epistemic status: clearing my own confusion

I'm going to discuss what we mean by preferences of an intelligent agent and try to make things clearer for myself (and hopefully others). I will also argue that the VNM theorem has limited applicability.

What are preferences?

When reasoning about agent's behavior, preferences are a useful abstraction. Preferences encode epistemic information about an agent's behavior. Suppose you are about to play a single game of rock-paper-scissors against an AI. If you know that the AI has a preference for rock over scissors, you can use that knowledge and reason:

(0) If the AI has both rock and scissors among its choices, it will not choose scissors.
(1) The AI can... (read 4034 more words →)

What is Randomness?

martinkunev

epistemic status: my intuition after reading and watching a bunch of stuff; no new information

You take a die in your hand. If you throw it, the result will be what people usually call a random number. Let's say you get 2. What do we mean when we say that this number is random? To answer these questions, I will try to give you some intuition on the concept of randomness.

When a person says an outcome of a process (such as the number 2) is random, they mean that they are uncertain what the outcome is. The die is not a magical object that produces random numbers. The die is an object which... (read 2814 more words →)

Is CDT with precommitment enough?

martinkunev

Logical decision theory was introduced (in part) to resolve problems such as Parfit's hitchhiker.

I heard an argument that there is no reason to introduce a new decision theory - one can just take causal decision theory and precommit to doing whatever is needed on such problems (e.g. pay the money once in the city).

This seems dubious given that people spent so much time on developing logical decision theory. However, I cannot formulate a counterargument. What is wrong with the claim that CDT with precommitment is the "right" decision theory?

What is Ontology?

martinkunev

This is my attempt at an intuitive explanation of the term "ontology". This article is not going to say anything new, only provide a (maybe) different view point on known concepts.

There are tons of definitions for "ontology". In my experience, those definitions do not help in understanding the concept - one I heard at university is "Ontology is the explicit specification of conceptualization". Instead of giving definitions, I'm going to give an example of two AI agents with different ontologies.

AI agent Susan

Susan is an AI agent that can add integers. Susan is asked to play a game against another AI agent: The players take turns to select an integer between 1 and... (read 927 more words →)

Choosing a book on causality

martinkunev

I'm looking to get a better understanding on causality, in particular with relation to AI. Judea Pearl has written at least 3 books on the subject.

I have already read The book of why - this one wasn't technical enough. Should I read Causality: Models, Reasoning and Inference or Causal Inference in Statistics - A Primer. If somebody is familiar with both of these books, how do they compare?

LESSWRONG
LW

LESSWRONG
LW

Would you have a baby in 2024?

How useful is Corrigibility?

What is Randomness?

Is CDT with precommitment enough?

martinkunev

martinkunev

Leading by example

A year-long journey of getting fast internet in Paris

Fake media seems to be a fact of life now

Open weights != Open source

Subjective experience is most likely physical

Understanding Agent Preferences

What is Randomness?

martinkunev

Would you have a baby in 2024?

How useful is Corrigibility?

What is Randomness?

Is CDT with precommitment enough?

martinkunev

martinkunev

Leading by example

A year-long journey of getting fast internet in Paris

Fake media seems to be a fact of life now

Open weights != Open source

Subjective experience is most likely physical

Understanding Agent Preferences

What is Randomness?

My COVID experience

Watermarking AI-generated content

What are preferences?

AI agent Susan