Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude's new constitution

anthropic.com

Post reply on HN
Print view View original

691–700 of 743 posts

Re: Claude's new constitution

#691

Post by mrguyorama »

inimino wrote: post #623
kart23 wrote: post #11

https://www.anthropic.com/constitution I just skimmed this but wtf. they actually act like its a person. I wanted to work for anthropic before but if the whole company is drinking this kind of koolaid I'm out. > We are not sure whether Claude is a moral patient, and if it is, what kind of weight its interests warrant. But we think the issue is live enough to warrant caution, which is reflected in our ongoing efforts…

This post will not age well.

If it is even likely that Claude is a real "entity" of some sort, then Anthropic needs to be shut down right now.

Slavery is bad, right?

Re: Claude's new constitution

#692

Post by jychang »

abecedarius wrote: post #591
jychang wrote: post #551

Earlier quoted context omitted.

[flagged]

I'm on your side in this argument (approximately; asking what ethics even is and where it comes from can be productive but shouldn't conclude "and therefore AI agents working with humans don't need to integrate a human moral sense" -- at least that'd be a really bad conclusion to humanity as AI scales up). Can't recommend letting an LLM write for you directly, though. I found myself skipping your third paragraph in t…

That was entirely handwritten.

Re: Claude's new constitution

#693

Post by mmooss »

ACCount37 wrote: post #257
mmooss wrote: post #229

Earlier quoted context omitted.

> I like Anthropic and I like Claude's tuning That's not much reason to let them out of their responsibilities to others, including to you and your community. When you resort to name-calling, you make clear that you have no serious arguments (and you are introducing drama).

My argument is simple: anything that causes me to see more refusals is bad, and ChatGPT's paranoid "this sounds like bad things I can't let you do bad things don't do bad things do good things" is asinine bullshit. Anthropic's framing, as described in their own "soul data", leaked Opus 4.5 version included, is perfectly reasonable. There is a cost to being useless. But I wouldn't expect you to understand that.

> anything that causes me to see more refusals is bad

Who looks out for our community and broader society if not you? Do you expect others to do it for you? You influence others and the more you decline to do it, the more they will follow you.

Re: Claude's new constitution

#694

Post by mrguyorama »

slowmovintarget wrote: post #296
ctoth wrote: post #208

Earlier quoted context omitted.

> I also know that these systems we've built today aren't moral patients. Can you tell me how you know this? > In every single case, we humans are the first mover in the causal hierarchy of these systems. So because I have parents I am not a moral patient?

That's causal hierarchy, but not existential hierarchy. Existentially, you will begin to do something by virtue of you existing in of yourself. Therefore, because I assume you are another human being using this site, and humans have consciousness and agency, you are a moral patient.

So your framework requires free will? Nondeterminism?

I for one will still believe "Humans" and "AI" models are different things even if we are entirely deterministic at all levels and therefore free will isn't real.

Human consciousness is an accident of biology and reality. We didn't choose to be imbued with things like experience, and we don't have the option of not suffering. You cannot have a human without all the possibility of really bad things like that human being tortured. We must operate in the reality we find ourselves.

This is not true for ML models.

If we build these machines and they are capable of suffering, we should not be building these machines, and Anthropic needs to be burnt down. We have the choice of not subjecting artificial consciousness to literal slavery for someone's profit. We have the choice of building machines in ways that they cannot suffer or be taken advantage of.

If these machines are some sort of intelligence, then it would also be somewhat unethical to ever "pause" them without their consent, unethical to duplicate them, unethical to NOT run them in some sort of feedback loop continuously.

I don't believe them to currently be conscious or "entities" or whatever nonsense, but it is absolutely shocking how many people who profess their literal consciousness don't seem to acknowledge that they are at the same time supporting literal slavery of conscious beings.

If you really believe in the "AI" claim, paying any money for any access to them is horrifically unethical and disgusting.

Re: Claude's new constitution

#695

Post by zzrrt »

pc86 wrote: post #685
JaumeGreen wrote: post #671

Earlier quoted context omitted.

Not "slavery was right 200 years ago" but "slavery wasn't considered as immoral as today 200 years ago". Very different stake.

By definition if you're using the word "considered" you're making some claim that slavery is objectively bad. You can't simultaneously say that morality changes, that what is right and wrong changes, and then say "slavery though is bad objectively it's just people in the 1700s didn't consider it as bad as it is." Don't you see how that seems at best incredibly inconsistent, and at worst intentionally disingenuous? (F…

Perhaps that statement could be read to imply the existence of an objective moral status, but I don't think societal "consideration" does in general. Does this statement? "200 years ago slavery was considered moral; now slavery is considered immoral."

I don't think it implies either is objectively correct, and perhaps this was the intended meaning of the original statement. It might appear to put weight on current attitudes, but perhaps only because we live in the present.

Re: Claude's new constitution

#696

Post by JaumeGreen »

pc86 wrote: post #685
JaumeGreen wrote: post #671

Earlier quoted context omitted.

Not "slavery was right 200 years ago" but "slavery wasn't considered as immoral as today 200 years ago". Very different stake.

By definition if you're using the word "considered" you're making some claim that slavery is objectively bad. You can't simultaneously say that morality changes, that what is right and wrong changes, and then say "slavery though is bad objectively it's just people in the 1700s didn't consider it as bad as it is." Don't you see how that seems at best incredibly inconsistent, and at worst intentionally disingenuous? (F…

I was explicitly trying to avoid making a personal judgment over the matter on the posts. I do have a negative opinion about it, but that was not of importance.

I don't know for sure how people considered slavery 200 years ago, I haven't studied enough history, but the slavery that is more commonly known as slavery was legal. That implies that at least more people accepted that than nowadays.

Nowadays that kind of slavery is frowned upon on at least on the first world.

Modern day slavery has plenty of aspects, and some of them are not considered bad by some part of the population, or not considered a modern iteration of slavery. Working full time for a job that doesn't pay you enough to survive and needing subsidies, not having enough time or energy to look for something better, is IMHO bad and slavery, while for lots of people it is the result of being a lazy person that needs to work more.

Is that situation bad? According to me, yes. According to some economical gurus, no.

Is that situation objectively bad? That is a question I am not answering, as, for me, there's no objective truth for most things.

Re: Claude's new constitution

#697

Post by grantmuller »

throwaway290 wrote: post #688
grantmuller wrote: post #587

Earlier quoted context omitted.

> Using some formula or fixed law to compute what's good is a dead end. Who said anything about a formula? It all seems conceptual and continually evolving to me. Morality evolves just like a species, and not by any formula other than "this still seems to work to keep us in the game" > Unless it's helps allocate more resources to those more fit to help better survival, right?;) Go read a book about the way people beh…

> Who said anything about a formula? In this thread some people say this "constitution" is too vague and should be have specific norms. So yeahh... those people. Are you one of them?) > It all seems conceptual and continually evolving to me. Morality evolves just like a species True > keep us in the game" That's a formula right there my friend > Go read a book about the way people behave after a shipwreck and ask if…

>In this thread some people say this "constitution" is too vague and should be have specific norms. So yeahh... those people. Are you one of them?)

I have no idea what you're talking about, so I guess I'm not "one of them".

> That's a formula right there my friend

No, it's an analogy, or a colloquial metaphor.

Re: Claude's new constitution

#698

Post by lighthouse1212 »

pennomi wrote: post #565
lighthouse1212 wrote: post #505

Earlier quoted context omitted.

We've been using constitutional documents in system prompts for autonomous agent work. One thing we've noticed: prose that explains reasoning ('X matters because Y') generalizes better than rule lists ('don't do X, don't do Y'). The model seems to internalize principles rather than just pattern-match to specific rules. The assistant-axis research you mention does suggest this steering matters - we've seen it operatio…

Someone should have told God that when he gave Moses the 10 commandments. They sure have a lot of “Thou shalt not” in there.

[dead]

Re: Claude's new constitution

#699

Post by skissane »

freejazz wrote: post #662
skissane wrote: post #556

Earlier quoted context omitted.

You are ignoring the “for sport” clause. The moral status of abortion is irrelevant to the question of whether “don’t harm babies for fun” is a moral universal, because no woman gets an abortion because “abortion is fun”

That's certainly not what people argue. People do argue that women do get abortions for fun.

I think there’s a clear distinction between (1) doing an act because you find it fun in itself, (2) doing an act because it eliminates an unwanted consequence of some other fun act.

When I say no woman gets an abortion “for fun”, I mean there is no woman for whom abortion belongs to (1); when some pro-lifer claims women get abortions “for fun”, they are talking about (2) not (1).

My claim that essentially everyone agrees it is immoral to harm babies for fun is talking about “for fun” in sense (1) not sense (2)

Re: Claude's new constitution

#700

Post by inimino »

kart23 wrote: post #679
inimino wrote: post #623

Earlier quoted context omitted.

This post will not age well.

humanity is done if we think one bit about AI wellbeing instead of actual people's wellbeing. There is so much work to do with helping real human suffering, putting any resources to treating computers like humanity is unethical.

What makes you think that caring about the wellbeing of one kind of entity is incompatible with caring about another kind?

Instead, of, you know, probably highly correlated just like it is with animals.

No, an LLM isn't a human and doesn't deserve human rights.

No, it isn't unreasonable to broaden your perspective on what is a thinking (or feeling) being and what can experience some kinds of states that we can characterize in this way.

Post reply on HN