Dentosal

LESSWRONG
LW

Dentosal — LessWrong

Replying toI wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

I wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

Don't be sorry. While I didn't like it, it was worth it; no question about that. In the intro post on the 1st, I wrote:

The main goal is just to write more, and to lower my bar on what's writing- and publishing-worthy.

That was achieved. I ought to feel proud of myself, but right now I just feel numb.

My motivation was in a way a mix of all four categories, the division between them quite unclear. I don't think it was so much about writing, though, and more about expressing ideas. I want to be the kind of person who is known for having the kind of ideas I do have. And on... (read more)

I wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

Dentosal

3mo

It's done. I made it to the end. A Finnish proverb fits the situation perfectly:

Paska reissu mutta tulipahan tehtyä

Which translates to something like "A crappy journey but in any case it's over now". I forced myself to do this. It was not fun. I rarely enjoyed writing. Every day I kept looking at the word counter, hoping that it would be over already. Sometimes the text was not done when I reached 500 words, which meant I had to write more.

I did not manage to keep any buffer. Each text was written on the day when it needed to be ready, except for this one which I wrote five days in advance... (read 561 more words →)

Reflections on my woo-aversion

Dentosal

3mo

I wish I had a thought recorder for this. It's much easier to think while walking, not interrupted by note-taking.

Woo was discussed last night. It's hard to say what it means, exactly. The defining example is meditation, and anything related to it. I think the extreme case is psychedelic drugs. Many components won't work unless you already believe they do, but they do actually work, sometimes. I'm very woo-averse.

Just a second, something's happening

I just jumped into a train. Twilight and the pleasant, gusty freshness of late autumn turn into a cramped, unpleasant space full of people. Air feels heavy. But it's the lights that bother me the most. It's tempting to just... (read 368 more words →)

Some notes on supply, demand, cost and utility

Dentosal

3mo

What determines how much things cost? The textbook answer is, supply and demand. But that's just the Teacher's Password. An actually useful model could be used to answer some questions like "How much should I ask for this product?" or "Am I getting ripped off?".

Cost and utility

We typically think of cost as monetary, and for most purchases this is the only sensible way to think about them. When I eat pizza at the restaurant or take a train to another city, in the end the question of how much it cost is rather simple. You want something, and to get it, you'll have to fork over some money. If you want the... (read 667 more words →)

Incoherent rambling about preference utilitarism

Dentosal

3mo

The yesterday's post gathered a relatively large number of comments. Nice! And downvotes! Engagement!! Sadly it was not a ragebait, only my honest-yet-unsure take on a complex and hard-to-understand topic.

One of the comments, by Vladimir Nesov, did change how I was modelling the whole thing:

How is suffering centrally relevant to anything? If a person strives for shaping the world in some ways, it's about the shape of the world, the possibilities and choice among them, not particularly about someone's emotions, and not specifically suffering. Perhaps people, emotions, or suffering and among the considerations for how the world is being shaped, but that's hardly the first thing that should define the whole affair.
(Imagine

... (read 454 more words →)

Replying toShould we extend moral patienthood to LLMs?

Dentosal3mo

Should we extend moral patienthood to LLMs?

Does this match your viewpoint? "Suffering is possible without consciousness. The point of welfare is to reduce suffering."

-1

Replying toShould we extend moral patienthood to LLMs?

Dentosal3mo*

Should we extend moral patienthood to LLMs?

I have been associating the term "welfare" with suffering-minimization. (Suffering is, in the most general sense, the feelings that come from lacking something from the Maslow's hierarcy of needs.)

It indeed seems like I've misunderstood the whole caring-about-others thing. It's about value-fullfillment, letting them shape the world as they see fit? And reducing suffering is just the primary example of how biological agents wish the world to change.

That's way more elegant model than focusing on the suffering, at least. Sadly this seems to make the question "why should I care?" even harder to answer. At least suffering is aesthetically ugly, and there's some built-in impulse to avoid it.

EDIT: You're arguing for preference utilitarism here, right?

Should we extend moral patienthood to LLMs?

Dentosal

3mo

I hear more and more people talk about AI welfare. I'm confused.

Computer programs do not suffer any more than rocks do. If I paint a face on a rock and smash it, some part of my brain would feel like someone got hurt. But it would be ridiculous to say that it suffered. The same should logically extend to all mechanical systems, surely a calculator doesn't suffer either, even when I divide by zero or when the battery goes out. Anthropomorphization is buried deep into the human brain, but surely we can recognize it as a bias.

The logic gets harder once we enter the world of biology. Can a single cell suffer?... (read 453 more words →)

-3

EA ITT: An attempt

Dentosal

3mo

Every now and then, I hang out with people who tell me they're doing Effective Altruism. I won't claim to have read even the standard introductory texts, and Ord's The Precipice gifted to me still gathers dust on the shelf, while the ever-practical collection of Nietzsche's works still feels worth revisiting every now and then. That by itself should tell you enough about me as a person. Regardless, for a long time I thought I knew what it was about, namely Purchasing Fuzzies and Utilons Separately, along with some notion of utility meanng something more than just the fuzzies. I already subscribed to fully to the idea of effectiveness in general. Altruism,... (read 1169 more words →)

On morality, defection-robustness, and legibility incentives

Dentosal

3mo

One of the tests for noticing a broken system is asking "What would happen if everyone did that?" about breaking some rule. This is especially useful when you're considering breaking it yourself for short-term gain. If the answer is "the system would need to change in a way that's better for me", then it's often justified.

Another perspective is seeing how often the rules are broken by other people. In almost every system, rule-breakers are gaining unfair advantage due to insufficient enforcement. This should sometimes occur, because otherwise too many resources are getting spent on fighting it. But in a stag hunt it's stupidity, not altruism, to attempt teamwork when everyone else is... (read 744 more words →)

Emotions, Fabricated

Dentosal

3mo

Queries about my internal state tend to return fabricated answers. It doesn't much matter if it's me or someone else asking the questions. It's not like I know what's going on inside my head. Thoughts can be traced to an extent, but feelings are intangible. Typically I just don't try, and the most pressing issue is that I'm unable to differentiate anxiety and hunger. Not a huge problem, except for slight over-eating once in a while. I think the description of Alexithymia matches my experiences quite well, although naturally not all of the symptoms match.

The real issues arise from other people asking how I feel or what caused me to act in... (read 391 more words →)

My frustrations: AI doom

Dentosal

3mo

I've heard of this AI doom thingy. We're all going to die or something. It's going to happen soon, maybe in two to ten years. I find myself mostly unfazed by this. Is it because all previous claims of the end of the world have been fake? Or am I just depressed enough that death would come as a relief? Possibly it's just that nobody else seems to be panicking, so it's not like I'm going to start. That would mean other people would be questioning my sanity, and I do that enough myself. Maybe I could just not explain why I'm suddenly doing different things? In any case, I don't feel... (read 350 more words →)

Replying toComplaining about my inability to focus on uninteresting things

Dentosal3mo

Complaining about my inability to focus on uninteresting things

I have not. A reasonable person would have. I think obtaining it rather complicated (in Finland, that is), but possibly worth it. Possibly worth it doesn't mean worth it. I recognize that I'm probably not thinking clearly about this.

But what's the reason to be productive beyond my natural abilities? I fear I would just use it all to make even more money, which doesn't matter to my wellbeing at all. The admiration of others? That would be cheating. Self actualization? I don't think depression will go away by just doing more stuff, the problem isn't not doing enough, it's not enjoying the results. Fixable with other medication? Possibly. (Go to step one)

Complaining about my inability to focus on uninteresting things

Dentosal

3mo

Three weeks have passed since the starting this challenge. Writing doesn't feel any easier. The quality of my texts hasn't improved at all, or at least I'm not feeling it. I'm out of topics to write about, and speding so much time writing or stressing about it limits the interactions which could be used as source material. I had hoped to write more about my ideas and values instead of complaining and filler content, yet here I go again. Writing about writing is the boring kind of meta.

For the first time in my life I've been able to do day's work before any fun activities, the way traditional work ethic is taught.... (read 354 more words →)

Replying toParsing Validation

Dentosal3mo

Parsing Validation

An astute reader pointed out that the Clueless designation might make more sense, if we consider ChatGPT inferior instead. I hadn't consider that option, and it makes much more sense.

Replying toNotes on Claude 4 System Card

Dentosal9mo

Notes on Claude 4 System Card

I'm drawing parallels between conventional system auditing and AI alignment assessment. I'm admittedly not sure if my intuitions transfer over correctly. I'm certainly not expecting the same processes to be followed here, but many of the principles should still hold.

We believe that these findings are largely but not entirely driven by the fact that this early snapshot had severe issues with deference to harmful system-prompt instructions. [..] This issue had not yet been mitigated as of the snapshot that they tested.

In my experience, if an audit finds lots of issues, it means nobody has time to look for the hard-to-find issues. I get the same feeling from this section; Apollo easily found... (read more)

Replying toFertility Will Never Recover

Dentosal1y

Fertility Will Never Recover

You cannot incentivize people to make that sacrifice at anything close to the proper scale because people don’t want money that badly. How many hands would you amputate for $100,000?

There's just no political will to do it, since the solutions would be harsh or expensive enough that nobody could impose them upon society. A god-emperor, who really wished to increase fertility numbers and could set laws freely without the society revolting, could use some combination of these methods:

If you're childless, or perhaps just unmarried, you pay additional taxes. The amount can be adjusted to be as high as necessary. Alternatively, just raise the general tax rate and give reduction based on the

... (read more)

-1

-2

Dentosal1y

Communication is indeed hard, and it's certainly possible that this isn't intentional. On the other hand, making mistakes is quite suspicious when they're also useful for your agenda. But I agree that we probably shouldn't read too much into it. The system card doesn't even mention the possibility of the model acting maliciously, so maybe that's simply not in scope for it?

Dentosal1yQuick Take

While reading OpenAI Operator System Card, the following paragraph on page 5 seemed a bit weird:

We found it fruitful to think in terms of misaligned actors, where:

the user might be misaligned (the user asks for a harmful task),

the model might be misaligned (the model makes a harmful mistake), or

the website might be misaligned (the website is adversarial in some way).

Interesting use of language here. I can understand calling the user or website misaligned, as understood as alignment relative to laws or OpenAI's goals. But why call a model misaligned when it makes a mistake? To me, misalignment would mean doing that on purpose.

Later, the same phenomenon is described like this:

The second category of harm is if the model mistakenly takes some action misaligned with the user’s intent, and that action causes some harm to the user or others.

Is this yet another attempt to erode the meaning of "alignment"?

Dentosal1yQuick Take

Billionaire Larry Ellison says a vast AI-fueled surveillance system can ensure 'citizens will be on their best behavior'

Ellison is the CTO of Oracle, one of the three companies running the Stargate Project. Even if aligning AI systems to some values can be solved, selecting those values badly can still be approximately as bad as the AI just killing everyone. Moral philosophy continues to be an open problem.

LESSWRONG
LW

LESSWRONG
LW

I wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

The Aura of a Dark Lord

Omniscience one bit at a time: Chapter 1

Me consuming five different forms of media at once to minimize the chance of a thought occurring

Dentosal

I wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

Reflections on my woo-aversion

Some notes on supply, demand, cost and utility

Incoherent rambling about preference utilitarism

Should we extend moral patienthood to LLMs?

EA ITT: An attempt

On morality, defection-robustness, and legibility incentives

Dentosal

I wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

The Aura of a Dark Lord

Omniscience one bit at a time: Chapter 1

Me consuming five different forms of media at once to minimize the chance of a thought occurring

Dentosal

I wrote a blog post every day for a month, and all I got was this lousy collection of incoherent ramblings

Reflections on my woo-aversion

Some notes on supply, demand, cost and utility

Incoherent rambling about preference utilitarism

Should we extend moral patienthood to LLMs?

EA ITT: An attempt

On morality, defection-robustness, and legibility incentives

Cost and utility