361–370 of 743 posts
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…
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…
Deontological, spiritual/religious revelation, or some other form of objective morality? The incompatibility of essentialist and reductionist moral judgements is the first hurdle; I don't know of any moral realists who are grounded in a physical description of brains and bodies with a formal calculus for determining right and wrong. I could be convinced of objective morality given such a physically grounded formal sy…
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…
>specialized uses that don’t fully fit this constitution "unless the government wants to kill, imprison, enslave, entrap, coerce, spy, track or oppress you, then we don't have a constitution." basically all the things you would be concerned about AI doing to you, honk honk clown world. Their constitution should just be a middle finger lol. Edit: Downvotes? Why?
Earlier quoted context omitted.
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.
Earlier quoted context omitted.
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.
Earlier quoted context omitted.
>That's probably because we have yet to discover any universal moral standards. Really? We can't agree that shooting babies in the head with firearms using live ammunition is wrong?
That's not a standard, that's a case study. I believe it's wrong, but I bet I believe that for a different reason than you do.
Quentin Tarantino writes and produces fiction.
No one really believes needlessly shooting people in the head is an inconvenience only because of the mess it makes in the back seat.
Maybe you have a strong conviction that the baby deserved it. Some people genuinely are that intolerable that a headshot could be deemed warranted despite the mess it tends to make.
Earlier quoted context omitted.
No, I read your words the first time, I just don't understand. What would you have written differently, can you provide a concrete example?
I don’t how to explain it to you any different. I’m arguing for a different philosophy to be applied when constructing the llm guardrails. There may be a lot of overlap in how the rules are manifested in the short run.
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…
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 in the world that releases zero open weight models
- Actively lobbies to restrict Americans from access to open weight models
- Discloses zero information on safety training despite this supposedly being the whole reason for their existence
Earlier quoted context omitted.
> That's probably because we have yet to discover any universal moral standards. When is it OK to rape and murder a 1 year old child? Congratulations. You just observed a universal moral standard in motion. Any argument other than "never" would be atrocious.
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?
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 other and didn’t, at least momentarily, suffer any doubt, you’re arguably not human. Or have enough of a brain injury that you need special care.
Or
2. I kill everyone who has ever, and will ever, think they’re clever for proposing absurdly sterile and clear cut toy moral quandaries.
Maybe only true psychopaths.
And how to deal with them, individually and societally, especially when their actions don’t rise to the level of criminality that gets the attention of anyone who has the power to act and wants to, at least isn’t a toy theory.