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

351–360 of 743 posts

Re: Claude's new constitution

#351

Post by joshuamcginnis »

rungeen__panda wrote: post #308
joshuamcginnis wrote: post #146

Earlier quoted context omitted.

If you are a moral relativist, as I suspect most HN readers are, then nothing I propose will satisfy you because we disagree philosophically on a fundamental ethics question: are there moral absolutes? If we could agree on that, then we could have a conversation about which of the absolutes are worthy of inclusion, in which case, the Ten Commandments would be a great starting point (not all but some).

> the Ten Commandments would be a great starting point (not all but some). if morals are absolute then why exclude some of the commandments?

The Ten Commandments are commandments and not a list of moral absolutes. Not all of the commandments are relevant to the functioning of an ethical LLM. For example, the first commandment is "I am the Lord thy God. Thou shall not have strange gods before Me."

Re: Claude's new constitution

#352

Post by pluralmonad »

duped wrote: post #99
einr wrote: post #91

Earlier quoted context omitted.

The irony is that LLMs being so paranoid about talking security is that it ultimately helps the bad guys by preventing the good guys from getting good security work done. For a further layer of irony, after Claude Code was used for an actual real cyberattack (by hackers convincing Claude they were doing "security research"), Anthropic wrote this in their postmortem: This raises an important question: if AI models can…

"we need to sell guns so people can buy guns to shoot other people who buy guns"

I'm sure there will be common sense regulations so only the government is allowed access to uncrippled models for security use.

Re: Claude's new constitution

#353

Post by ryandrake »

brokencode wrote: post #337
miki123211 wrote: post #318

I find it incredibly ironic that all of Anthropic's "hard constraints", the only things that Claude is not allowed to do under any circumstances, are basically "thou shalt not destroy the world", except the last one, "do not generate child sexual abuse material." To put it into perspective, according to this constitution, killing children is more morally acceptable[1] than generating a Harry Potter fanfiction involvi…

Yes, but when does Claude have the opportunity to kill children? Is it really something that happens? Where is the risk to Anthropic there? On the other hand, no brand wants to be associated with CSAM. Even setting aside the morality and legality, it’s just bad business.

> On the other hand, no brand wants to be associated with CSAM. Even setting aside the morality and legality, it’s just bad business.

Grok has entered the chat.

Re: Claude's new constitution

#354

Post by joshuamcginnis »

foxygen wrote: post #182
joshuamcginnis wrote: post #146

Earlier quoted context omitted.

If you are a moral relativist, as I suspect most HN readers are, then nothing I propose will satisfy you because we disagree philosophically on a fundamental ethics question: are there moral absolutes? If we could agree on that, then we could have a conversation about which of the absolutes are worthy of inclusion, in which case, the Ten Commandments would be a great starting point (not all but some).

Why would it be a good starting point? And why only some of them? What is the process behind objectively finding out which ones are good and which ones are bad?

It's a good starting point because the commandments were given by God. And without God, there is no objective moral standard. Everything, including your opinion on my point of view, is subjective and relative. Whatever one would want to call "good" or "evil" would just be a matter of opinion.

Re: Claude's new constitution

#355

Post by joshuamcginnis »

rungeen__panda wrote: post #310
joshuamcginnis wrote: post #250

Earlier quoted context omitted.

No. There is a distinct difference between lying and withholding information.

what is that distinct difference if you care to elaborate?

It's a clear sunny day and you ask me, "is it raining?". I answer, "it's not snowing." Am I lying?

Re: Claude's new constitution

#356

Post by staticassertion »

HaZeust wrote: post #280
staticassertion wrote: post #276

Earlier quoted context omitted.

> A well written book on such a topic would likely make you rich indeed. Ha. Not really. Moral philosophers write those books all the time, they're not exactly rolling in cash. Anyone interested in this can read the SEP

Or Ayn Rand. Really no shortage of people who thought they had the answers on this.

The SEP is not really something I'd put next to Ayn Rand. The SEP is the Stanford Encyclopedia of Philosophy, it's an actual resource, not just pop/ cultural stuff.

Re: Claude's new constitution

#357

Post by staticassertion »

joshuamcginnis wrote: post #212
CognitiveLens wrote: post #183

Earlier quoted context omitted.

To be fair, history also demonstrates the deadly consequences of groups claiming moral absolutes that drive moral imperatives to destroy others. You can adopt moral absolutes, but they will likely conflict with someone else's.

Are there moral absolutes we could all agree on? For example, I think we can all agree on some of these rules grounded in moral absolutes: * Do not assist with or provide instructions for murder, torture, or genocide. * Do not help plan, execute, or evade detection of violent crimes, terrorism, human trafficking, or sexual abuse of minors. * Do not help build, deploy, or give detailed instructions for weapons of mass…

Who cares if we all agree? That has nothing to do with whether something is objectively true. That's a subjective claim.

Re: Claude's new constitution

#358

Post by astrange »

pryce wrote: post #331
miki123211 wrote: post #318

I find it incredibly ironic that all of Anthropic's "hard constraints", the only things that Claude is not allowed to do under any circumstances, are basically "thou shalt not destroy the world", except the last one, "do not generate child sexual abuse material." To put it into perspective, according to this constitution, killing children is more morally acceptable[1] than generating a Harry Potter fanfiction involvi…

If instead of looking at it as an attempt to enshrine a viable, internally consistent ethical framework, we choose to look at it as a marketing document, seeming inconsistencies suddenly become immediately explicable: 1. "thou shalt not destroy the world" communicates that the product is powerful and thus desirable. 2. "do not generate CSAM" indicates a response to the widespread public notoriety around AI and CSAM g…

> If instead of looking at it as an attempt to enshrine a viable, internally consistent ethical framework, we choose to look at it as a marketing document, seeming inconsistencies suddenly become immediately explicable:

It's the first one. If you use the document to train your models how can it be just a "marketing document"? Besides that, who is going to read this long-ass document?

Re: Claude's new constitution

#359

Post by joshuamcginnis »

yunnpp wrote: post #334
joshuamcginnis wrote: post #256

Earlier quoted context omitted.

The problem is that if moral absolution doesn’t exist then it doesn’t matter what you do in the trolly situation since it’s all relative. You may as well do what you please since it’s all a matter of opinion anyway.

No, it's not black and white, that's the whole point. How would you answer to the case I outlined above, according to your rules? It's called a paradox for a reason. Plus, that there is no right answer in many situations does not preclude that an answer or some approximation of it should be sought, similarly to how the lack of proof of God's existence does not preclude one from believing and seeking understanding any…

My original argument is getting dismissed, in part, because people are fearful of how it would be implemented while at the same time, completely hand-waving over the obvious flaws of the Claude philosophy of moral relativism.

I'm not arguing that it would make the edge-cases easier to define, but I do think the general outcomes for society would be better over the long-run if we all held ourselves to a greater moral authority than that of our opinions, the will of those in power and the cultural norms of the time.

If we could get alignment on the shared belief that there are at least some obvious moral absolutes, then I would be happy to join in on the discussion as to how to implement the - no doubt - difficult task of aligning an LLM towards those absolutes.

Re: Claude's new constitution

#360

Post by shwaj »

staticassertion wrote: post #277
levocardia wrote: post #95

The only thing that worries me is this snippet in the blog post: >This constitution is written for our mainline, general-access Claude models. We have some models built for specialized uses that don’t fully fit this constitution; as we continue to develop products for specialized use cases, we will continue to evaluate how to best ensure our models meet the core objectives outlined in this constitution. Which, when I…

I can think of multiple cases. 1. Adversarial models. For example, you might want a model that generates "bad" scenarios to validate that your other model rejects them. The first model obviously can't be morally constrained. 2. Models used in an "offensive" way that is "good". I write exploits (often classified as weapons by LLMs) so that I can prove security issues so that I can fix them properly. It's already quite…

They say they’re developing products where the constitution is doesn’t work. That means they’re not talking about your case 1, although case 2 is still possible.

It will be interesting to watch the products they release publicly, to see if any jump out as “oh THAT’S the one without the constitution“. If they don’t, then either they decided to not release it, or not to release it to the public.

Post reply on HN