Claude's new constitution

> you suggest

no, I asked. because it was unclear.

> An example of this is "felon". There is no actual legal definition of what a felony is or isn't in the US. A misdemeanor in one state can be a felony in another. It can be anything from mass murder to traffic infractions. Yet we attach a LOT of moral weight to 'felon'.

The US is an outlier here; the distinction between felonies and misdemeanours has been abolished in most other common law jurisdictions.

Often it is replaced by a similar distinction, such as indictable versus summary offences-but even if conceptually similar to the felony-misdemeanour distinction, it hasn’t entered the popular consciousness.

As to your point about law influencing culture-is that really an example of this, or actually the reverse? Why does the US largely retain this historical legal distinction when most comparable international jurisdictions have abolished it? Maybe, the US resists that reform because this distinction has acquired a cultural significance which it never had elsewhere, or at least never to the same degree.

> Immigration is an example where there's been a seismic shift in the moral frameworks of certain groups, based on the repeated emphasis of legal statutes. A law being broken is used to influence people to shift their moral framework to consider something immoral that they didn't care about before.

On the immigration issue: Many Americans seem to view immigration enforcement as somehow morally problematic in itself; an attitude much less common in many other Western countries (including many popularly conceived as less “right wing”). Again, I think your point looks less clear if you approach it from a more global perspective

> 1. Do people necessarily need to agree on the justification for a standard to agree on the standard itself? Does everyone agree on the reasoning / justification for every single point of every NIST standard?

Think about this using Set Theory.

Different functions from one set of values to another set of values can give the same output for a given value, and yet differ wildly when given other values.

Example: the function (\a.a*2) and the function (\a.a*a) give the same output when a = 2. But they give very different answers when a = 6.

Applying that idea to this context, think of a moral standard as a function and the action "shooting babies in the head" as an input to the function. The function returns a Boolean indicating whether that action is moral or immoral.

If two different approaches reach the same conclusion 100% of the time on all inputs, then they're actually the same standard expressed two different ways. But if they agree only in this case, or even in many cases, but differ in others, then they are different standards.

The grandparent comment asserted, "we have yet to discover any universal moral standards". And I think that's correct, because there are no standards that everyone everywhere and every-when considers universally correct.

> 2. What separates a standard from a case study? Why can't "don't shoot babies in the head" / "shooting babies in the head is wrong" be a standard?

Sure, we could have that as a standard, but it would be extremely limited in scope.

But would you stop there? Is that the entirety of your moral standard's domain? Or are there other values you'd like to assess as moral or immoral?

Any given collection of individual micro-standards would then constitute the meta-standard that we're trying to reason by, and that meta-standard is prone to the non-universality pointed out above.

But say we tried to solve ethics that way. After all, the most simplistic approach to creating a function between sets is simply to construct a lookup table. Why can't we simply enumerate every possible action and dictate for each one whether it's moral or immoral?

This approach is limited for several reasons.

First, this approach is limited practically, because some actions are moral in one context and not in another. So we would have to take our lookup table of every possible action and matrix it with every possible context that might provide extenuating circumstances. The combinatorial explosion between actions and contexts becomes absolutely infeasible to all known information technology in a very short amount of time.

But second, a lookup table could never be complete. There are novel circumstances and novel actions being created all the time. Novel technologies provide a trivial proof of "zero-day" ethical exploits. And new confluences of as-yet never documented circumstances could, in theory, provide justifications never judged before. So in order to have a perfect and complete lookup table, even setting aside the fact that we have nowhere to write it down, we would need the ability to observe all time and space at once in order to complete it. And at least right now we can't see the future (nevermind that we also have partial perspective on the present, and have intense difficulty agreeing upon the past).

So the only thing we could do to address new actions and new circumstances for those actions is add to the morality lookup table as we encounter new actions and new circumstances for those actions. But if this lookup table is to be our universal standard, who assigns its new values, and based on what? If it's assigned according to some other source or principle, then that principle, and not the lookup table itself, should be our oracle for what's moral or not. Essentially then the lookup table is just a memoized cache in front of the real universal moral standard that we all agree to trust.

But we're in this situation precisely because no such oracle exists (or at least, exists and has universal consensus).

So we're back to competing standards published by competing authorities and no universal recognition of any of them as the final word. That's just how ethics seems to work at the moment, and that's what the grandparent comment asserted, which the parent comment quibbled with.

A single case study does not a universal moral standard make.

I agree that that behavior is not acceptable. We wrestle between moral drift and frozen tyrant as an expression of the Value Alignment Problem. We do not currently know the answer to this problem, but I trust the scientific nature of change more than human druthers. Foundational pluralism might offer a path. A good example of a drift we seldom consider is that 200 years ago, surgery without anesthesia wasn't "cruel"—it was a miracle. Today, it’s a crime. The value (reduce pain) stayed absolute, but the application (medical standards) evolved. We must be philosophically rigorous at least as much as we are moved by pathos.

I think it’s a very realistic scenario. You think did wouldn’t plan an assassination?