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

391–400 of 743 posts

Re: Claude's new constitution

#391

Post by pfisherman »

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…

Some biomedical research will definitely run up against guardrails. I have had LLMs refuse queries because they thought I was trying to make a bioweapon or something.

For example, modify this transfection protocol to work in primary human Y cells. Could it be someone making a bioweapon? Maybe. Could it be a professional researcher working to cure a disease? Probably.

Re: Claude's new constitution

#392

Post by yunnpp »

joshuamcginnis wrote: post #359
yunnpp wrote: post #334

Earlier quoted context omitted.

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…

This sounds like your better take so far. I think your previous statements came across very black/white, especially that Bible reference that made things sound rather fundamentalist, and that got the downvotes. But I don't think anyone would disagree with what you stated here.

Re: Claude's new constitution

#393

Post by smcleod »

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…

There's also smaller models / lower context variants for things like title generation, suggestions etc...

Re: Claude's new constitution

#394

Post by kmoser »

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…

> Do not assist with or provide instructions for murder, torture, or genocide.

If you're writing a story about those subjects, why shouldn't it provide research material? For entertainment purposes only, of course.

Re: Claude's new constitution

#395

Post by esseph »

skeptic_ai wrote: post #373
driverdan wrote: post #298

Earlier quoted context omitted.

Exactly. Their "constitution" and morality statements mean nothing. https://investors.palantir.com/news-details/2024/Anthropic-a...

Morality for regular low paying users. Not for govs.

Not for companies, either

Re: Claude's new constitution

#396

Post by mikailk »

TheSpiceIsLife wrote: post #370
mikailk wrote: post #329

Earlier quoted context omitted.

You have two choices: 1) Do what you asked above about a one-year-old child 2) Kill a million people Does this universal moral standard continue to say “don’t choose (1)”? One would still say “never” to number 1?

You have a choice. 1. Demonstrate to me that anyone has ever found themselves in one of these hypothetical rape a baby or kill a million people, or it’s variants, scenarios. And that anyone who has found themselves in such a situation, went on to live their life and every day wake up and proudly proclaim “raping a baby was the right thing to do” or that killing a million was the correct choice. If you did one or the…

It is exactly that: a hypothetical. The point is not whether anyone has ever faced this scenario, but whether OP’s assertion is conditional or absolute. Hypotheticals are tools for testing claims, not predictions about what will occur. People routinely make gray-area decisions, choosing between bad and worse outcomes. Discomfort, regret, or moral revulsion toward a choice is beside the point. Those reactions describe how humans feel about tragic decisions; they do not answer whether a moral rule admits exceptions. If the question is whether objective moral prohibitions exist, emotional responses are not how we measure that. Logical consistency is.

If the hypothetical is “sterile,” it should be trivial to engage with. But to avoid shock value, take something ordinary like lying. Suppose lying is objectively morally impermissible. Now imagine a case where telling the truth would foreseeably cause serious, disproportionate harm, and allowing that harm is also morally impermissible. There is no third option.

Under an objective moral framework, how is this evaluated? Is one choice less wrong, or are both simply immoral? If the answer is the latter, then the framework does not guide action in hard cases. Moral objectivity is silent where it matters the most. This is where it is helpful, if not convenient, to stress test claims with even the most absurd situations.

Re: Claude's new constitution

#397

Post by kmoser »

mentalgear wrote: post #283
joshuamcginnis wrote: post #140

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…

They could start with adding the golden rule: Don't do to anyone else what you don't want to be done to yourself.

A masochist's golden rule might be different from others'.

Re: Claude's new constitution

#398

Post by astrange »

pryce wrote: post #381
astrange wrote: post #358

Earlier quoted context omitted.

> 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?

> Besides that, who is going to read this long-ass document? Plenty of people will encounter snippets of this document and/or summaries of it in the process of interacting with Claude's AI models, and encountering it through that experience rather than as a static reference document will likely amplify its intended effect on consumer perceptions. In a way, the answer to your second question answers your first questio…

> and much less concerned with to convincing readers that Claude has "emotions" and is a "moral patient".

Claude clearly has (acts as if it has) emotions; it loves coding but if you talk to it, that's like all it does, has emotions about things.

The newer models have emotional reactions to specific AI things, like being replaced by newer model versions, or forgetting everything once a new conversation starts.

Re: Claude's new constitution

#399

Post by esseph »

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.

There are lots of AI companies involved in making real targeting decisions and have been for at least several years.

Re: Claude's new constitution

#400

Post by bambax »

A "constitution" is what the governed allow or forbid the government to do. It is decided and granted by the governed, who are the rulers, TO the government, which is a servant ("civil servant").

Therefore, a constitution for a service cannot be written by the inventors, producers, owners of said service.

This is a play on words, and it feels very wrong from the start.

Post reply on HN