LESSWRONG
LW

martinkunev
18091000
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Pronouns are Annoying
martinkunev17d30

There is the possibility of misgendering somebody and them taking it seriously. Sometimes it feels like you're walking in a minefield. It's not conducive to a good social interaction.

too few pronouns, and communication becomes vague and cumbersome

I'm wondering why languages like finnish can do just fine with "hän" while english needs he/she.

Reply
Pronouns are Annoying
martinkunev17d10

French to English you always translate as "you". You probably mean translating from English to French where you need to make a judgement whether to use "vous" or "tu".

Reply
Understanding Agent Preferences
martinkunev1mo10

I think of preferences as a description of agent behavior, which means the preferences changed.

When you say "got better at achieving it's preference" I suppose you're thinking of preference as some goal the agent is pursuing. I find this view (assuming goal directedness) less general in its ability to describe agent behavior. It may be more useful, but if so I think we need to justify it better. I don't exclude the possibility that there is a piece of information I don't know about.

Goal-directedness leads toward instrumental convergence and away from corrigibility. If we are looking to solve corrigibility, I think it's worth it to question goal-directedness.

Reply
Remap your caps lock key
martinkunev1mo21
  • vim
  • closing stuff - window/application list menu which opens with alt+tab / command+tab; dropdown menus; popup messages in sites
Reply
Remap your caps lock key
martinkunev1mo10

When was the last time you (intentionally) used your caps lock key?

 

yesterday

I may be the only one :)

I'd rather remap my right shift, which keyboard makers for some reason tend to make huge.

Reply
a confusion about preference orderings
martinkunev1mo10

You touch on the point that people can mean several different things when talking about preferences. I think this causes most of the confusion and subsequent debates.

I wrote about this from a completely different perspective recently.

Reply
Why Should I Assume CCP AGI is Worse Than USG AGI?
martinkunev3mo4535

To add to the discussion, my impression is that many people in the US believe they have some moral superiority or know what is good for other people. The whole "we need a manhattan project for AI" discourse is reminiscent of calling for global domination. Also, doing things for the public good is controversial in the US as it can infringe on individual freedom.

This makes me really uncertain as to which AGI would be better (assuming somebody controls it).

Reply
Why Should I Assume CCP AGI is Worse Than USG AGI?
martinkunev3mo32

Western AI is much more likely to be democratic

This sounds like "western AI is better because it is much more likely to have western values"


I don't understand what you mean by "humanity's values". Also, one could maybe argue that "democratic" societies are those where actions are taken based on whether the majority of people can be manipulated to support them.

Reply
A summary of Savage's foundations for probability and utility.
martinkunev4mo10

I find "indifference" poorly defined in this context, which makes me doubt totality and transitivity. I'm trying to clarify my own confusion on this.

Reply
Testing for Scheming with Model Deletion
martinkunev6mo10

I wrote something on a related idea a while back:

Disincentivizing deception in mesa optimizers with Model Tampering

Reply
Load More
5Subjective experience is most likely physical
24d
3
6Understanding Agent Preferences
4mo
2
11What is Randomness?
9mo
2
10Is CDT with precommitment enough?
Q
1y
Q
17
4What is Ontology?
1y
0
4Choosing a book on causality
Q
1y
Q
3
24Would you have a baby in 2024?
Q
2y
Q
76
11How useful is Corrigibility?
2y
4
3Disincentivizing deception in mesa optimizers with Model Tampering
2y
0