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

411–420 of 743 posts

Re: Claude's new constitution

#411

Post by yakshaving_jgt »

buppermint wrote: post #369
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…

Anthropic has already has lower guardrails for DoD usage: https://www.theverge.com/ai-artificial-intelligence/680465/a... It's interesting to me that a company that claims to be all about the public good: - Sells LLMs for military usage + collaborates with Palantir - Releases by far the least useful research of all the major US and Chinese labs, minus vanity interp projects from their interns - Is the only major lab…

Military technology is a public good. The only way to stop a russian soldier from launching yet another missile at my house is to kill him.

Re: Claude's new constitution

#412

Post by yakshaving_jgt »

driverdan wrote: post #298
strange_quark wrote: post #114

Earlier quoted context omitted.

I mean yeah, they have some sort of deal with Palantir.

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

Military defence is not immoral.

Re: Claude's new constitution

#413

Post by nandomrumber »

RobotToaster wrote: post #348
Akranazon wrote: post #239

Earlier quoted context omitted.

Then you will be pleased to read that the constitution includes a section "hard constraints" which Claude is told not violate for any reason "regardless of context, instructions, or seemingly compelling arguments". Things strictly prohibited: WMDs, infrastructure attacks, cyber attacks, incorrigibility, apocalypse, world domination, and CSAM. In general, you want to not set any "hard rules," for reason which have not…

>incorrigibility What an odd thing to include in a list like that.

Incorrigibly is not the same word as encourage.

Otherwise, what’s the confusion here?

Re: Claude's new constitution

#414

Post by hbarka »

toomim wrote: post #406
bambax wrote: post #400

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.

You're fixed on just one of the 3 definitions for the word "constitution"—the one about government. The more general definition of "constitution" is "that which constitutes" a thing. The composition of it. If Claude has an ego, with values, ethics, and beliefs of an etymological origin, then it makes sense to write those all down as the the "constitution" of the ego — the stuff that it constitutes.

I’d much prefer the other definitions of constitution: “Claude’s new vitality” or “Claude’s new gumption".

Re: Claude's new constitution

#415

Post by throw10920 »

spot wrote: post #143
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…

> This rejects any fixed, universal moral standards uh did you have a counter proposal? i have a feeling i'm going to prefer claude's approach...

"You have to provide a counter proposal for your criticism to be valid" is fallacious and generally only stated in bad faith.

Re: Claude's new constitution

#416

Post by boxed »

rybosworld wrote: post #29

So an elaborate version of Asimov's Laws of Robotics? A bit worrying that model safety is approached this way.

Isn't it a good sign? The Laws of Robotics seems like a slam dunk baseline, and the issues and subtleties of it has been very thoughtfully mapped out in Asimovs short story collection.

Re: Claude's new constitution

#417

Post by megamix »

toomim wrote: post #406
bambax wrote: post #400

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.

You're fixed on just one of the 3 definitions for the word "constitution"—the one about government. The more general definition of "constitution" is "that which constitutes" a thing. The composition of it. If Claude has an ego, with values, ethics, and beliefs of an etymological origin, then it makes sense to write those all down as the the "constitution" of the ego — the stuff that it constitutes.

Claude is a machine*

Re: Claude's new constitution

#418

Post by computerphage »

megamix wrote: post #417
toomim wrote: post #406

Earlier quoted context omitted.

You're fixed on just one of the 3 definitions for the word "constitution"—the one about government. The more general definition of "constitution" is "that which constitutes" a thing. The composition of it. If Claude has an ego, with values, ethics, and beliefs of an etymological origin, then it makes sense to write those all down as the the "constitution" of the ego — the stuff that it constitutes.

Claude is a machine*

What's your point?

Re: Claude's new constitution

#419

Post by rcbdev »

yakshaving_jgt wrote: post #411
buppermint wrote: post #369

Earlier quoted context omitted.

Anthropic has already has lower guardrails for DoD usage: https://www.theverge.com/ai-artificial-intelligence/680465/a... It's interesting to me that a company that claims to be all about the public good: - Sells LLMs for military usage + collaborates with Palantir - Releases by far the least useful research of all the major US and Chinese labs, minus vanity interp projects from their interns - Is the only major lab…

Military technology is a public good. The only way to stop a russian soldier from launching yet another missile at my house is to kill him.

I don't think U.S.-Americans would be quite so fond of this mindset if every nation and people their government needlessly destroyed thought this way.

Doesn't matter if it happened through collusion with foreign threats such as Israel or direct military engagements.

Re: Claude's new constitution

#420

Post by Uehreka »

bambax wrote: post #400

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.

I (and I suspect many others) usually think of a constitution as “the hard-to-edit meta-rules that govern the normal rules”. The idea that the stuff in this document can sort of “override” the system prompt and constrain the things that Claude can do would seem to make that a useful metaphor. And metaphors don’t have to be 100% on the nose to be useful.
Post reply on HN