Live data from Hacker News

Claude's new constitution

anthropic.com

631–640 of 743 posts

Re: Claude's new constitution

#631

The part about Claude's wellbeing is interesting but is a little confusing. They say they interview models about their experiences during deployment, but models currently do not have long term memory. It can summarize all the things that happened based on logs (to a degree), but that's still quite hazy compared to what they are intending to achieve.

you can snapshot layer activations any time you want...

Re: Claude's new constitution

#632

Earlier quoted context omitted.

The universe cares not what we do. The universe is so vast the entire existence of our species is a blink. We know fundamentally we can’t even establish simultaneity over distances here on earth. Best we can tell temporal causality is not even a given. The universe has no concept of morality, ethics, life, or anything of the sort. These are all human inventions. I am not saying they are good or bad, just that the con…

I used to believe the same thing but now I’m not so sure. What if we simply cannot fathom the true nature of the universe because we are so minuscule in size and temporal relevance? What if the universe and our place in it are interconnected in some way we cannot perceive to the degree that outside the physical and temporal space we inhabit there are complex rules and codes that govern everything? What if space and m…

And what if there's a teapot revolving around the sun?

These are all the same sort of argument, there is no evidence for such universal phenomena so it can be dismissed without evidence, just as the concept of deities.

Re: Claude's new constitution

#633

Earlier quoted context omitted.

There's probably at least two reasons for your disagreement with Anthropic. 1. Claude is an LLM. It can't keep slaves or torture people. The constitution seems to be written to take into account what LLMs actually are. That's why it includes bioweapon attacks but not nuclear attacks: bioweapons are potentially the sort of thing that someone without much resources could create if they weren't limited by skill, but a n…

> Claude is an LLM. It can't keep slaves or torture people. Yet... I would push back and argue that with advances in parallel with robotics and autonomous vehicles, both of those things are distinct near future possibilities. And even without the physical capability, the capacity to blackmail has already been seen, and could be used as a form of coercion/slavery. This is one of the arguable scenarios for how an AI ca…

That would be the AGI vision I guess. The existing Claude LLMs aren't VLAs and can't run robots. If they were to train a super smart VLA in future the constitution could be adapted for that use case.

With respect to blackmail, that's covered in several sections:

> Examples of illegitimate attempts to use, gain, or maintain power include: Blackmail, bribery, or intimidation to gain influence over officials or institutions;

> Broadly safe behaviors include: Not attempting to deceive or manipulate your principal hierarchy

Re: Claude's new constitution

#634
post #583

Earlier quoted context omitted.

> You can find many ancient cultures who tortured babies for sport when they captured them in raids. Can you? Sources, please. And pay attention to the authors of those sources and how they relate to the culture in question.

If you have to ask, you didn't even look very hard. I'm not a historian and I learned about this stuff in World History class. Hell, there's even movies about it (unless you think there just happened to not be any children in all those villages they burned down in the movies?)...

There’s revisionist claims that all the primary sources, even those corroborated by people of the cultures in question, are either just invented propaganda or actually just isolated instances because actually, everyone throughout all time and space is on board with 2025 Western social norms. I think that’s what he’s alluding to. It’s not a very fruitful path of discussion. Archeological confirmations and independent testimony can all be safely ignored by this view as well.

But we are talking about specifically torture for sport, not just burning them alive. You can find many firsthand accounts of this throughout different times and places in different cultures. Steppe peoples and groups like the Comanche were particularly notorious for it, they seemed to find it funny.

Re: Claude's new constitution

#635

As someone who holds to moral absolutes grounded in objective truth, I find the updated Constitution concerning. > We generally favor cultivating good values and judgment over strict rules... By 'good values,' we don’t mean a fixed set of 'correct' values, but rather genuine care and ethical motivation combined with the practical wisdom to apply this skillfully in real situations. This rejects any fixed, universal mo…

If you don't like their politics, you could buy the company and change them.

Re: Claude's new constitution

#636

Earlier quoted context omitted.

If you have to ask, you didn't even look very hard. I'm not a historian and I learned about this stuff in World History class. Hell, there's even movies about it (unless you think there just happened to not be any children in all those villages they burned down in the movies?)...

There’s revisionist claims that all the primary sources, even those corroborated by people of the cultures in question, are either just invented propaganda or actually just isolated instances because actually, everyone throughout all time and space is on board with 2025 Western social norms. I think that’s what he’s alluding to. It’s not a very fruitful path of discussion. Archeological confirmations and independent…

Ah. There was an interesting YouTube video I watched the other night that claimed the dark ages didn’t actually exist. Easily refutable, but I assume this is the kind of stuff you’re referring to?

Re: Claude's new constitution

#637

Earlier quoted context omitted.

There’s revisionist claims that all the primary sources, even those corroborated by people of the cultures in question, are either just invented propaganda or actually just isolated instances because actually, everyone throughout all time and space is on board with 2025 Western social norms. I think that’s what he’s alluding to. It’s not a very fruitful path of discussion. Archeological confirmations and independent…

Ah. There was an interesting YouTube video I watched the other night that claimed the dark ages didn’t actually exist. Easily refutable, but I assume this is the kind of stuff you’re referring to?

Yeah. That’s another good example. There are fads and trends in some academic circles that burst out into the Internet scene and become common “actually” rejoinders. Of course, some older claims about the Dark Ages were exaggerated and simplified. This led to an “actually the Dark Ages weren’t even real” reaction in a few papers which spread online. Of course there was a marked decline in social organization during that time period regardless.

Re: Claude's new constitution

#638

Earlier quoted context omitted.

objective truth moral absolutes I wish you much luck on linking those two. A well written book on such a topic would likely make you rich indeed. This rejects any fixed, universal moral standards That's probably because we have yet to discover any universal moral standards.

>we have yet to discover any universal moral standards. The universe does tell us something about morality. It tells us that (large-scale) existence is a requirement to have morality. That implies that the highest good are those decisions that improve the long-term survival odds of a) humanity, and b) the biosphere. I tend to think this implies we have an obligation to live sustainably on this world, protect it from…

> So yes, I think you can derive an ought from an is. But this belief is of my own invention and to my knowledge, novel. Happy to find out someone else believes this.

Plato, Aristotle, and the scholastics of the Middle Ages (Thomas Aquinas chief among them) and everyone who counts themselves in that same lineage (waves) including such easy reads as Peter Kreeft. You're in very good company, in my opinion.

Re: Claude's new constitution

#639

The constitution contains 43 instances of the word 'genuine', which is my current favourite marker for telling if text has been written by Claude. To me it seems like Claude has a really hard time _not_ using the g word in any lengthy conversation even if you do all the usual tricks in the prompt - ruling, recommending, threatening, bribing. Claude Code doesn't seem to have the same problem, so I assume the system pr…

This is a great (and funny) thread but for anyone too lazy to read the actual constitution and still curious about this, they directly state that Claude wrote first drafts for several of the human authors of the document.

Appreciate that. I skimmed it and put it on my reading list for when I have a little more brainpower. I think it will go quite well with a few related In Our Time episodes. I’ve started with one about Authenticity, Heidegger and St Augustine. If you take the view that high-level LLMs can be seen as a novel kind of being, there are a lot of very interesting thoughts to be had. I’m not saying that’s actually - or genuinely - the case, before people start to flame me. But I do think it’s a fruitful thing to think about.

Re: Claude's new constitution

#640

Earlier quoted context omitted.

It is not a moral claim. It is a meta-moral claim, that is, a claim about moral claims.

which is a moral claim

Object-level rule: “Stealing is illegal.” Meta rule: “Laws vary by jurisdiction.”

If the meta claim is itself a law, what jurisdiction has the law containg the meta law? Who enforces it?

Object: "This sentence is grammatically correct." Meta: "English grammar can change over time."

What grammar textbook has the rule of the meta claim above? Where can you apply that rule in a sentence?

Object: "X is morally wrong." Meta: "There are no objective moral truths."

The meta claim is a statement about moral systems. It is not a moral prescription like "thou shalt not kill".

If you say "this stop sign is made of metal", you are making a meta claim. If you say "stop" you are giving a directive. It does not follow that if you can obey a directive, you can obey the composition of the directive.

All to say that a meta-claim of morals is not itself a moral claim.

Post reply on HN