Claude's new constitution • Hacker News Board

Re: Claude's new constitution

#591

Post by abecedarius » Thu, Jan 22, 2026, 2:28 PM UTC

jychang wrote: post #551

Dilettante_ wrote: post #533

Earlier quoted context omitted.

>I got lazy with your responses and just threw in a few bullet points to AI This should legit be a permabannable offense. That is titanically disrespectful of not just your discussion partner, but of good discussion culture as a whole.

[flagged]

I'm on your side in this argument (approximately; asking what ethics even is and where it comes from can be productive but shouldn't conclude "and therefore AI agents working with humans don't need to integrate a human moral sense" -- at least that'd be a really bad conclusion to humanity as AI scales up).

Can't recommend letting an LLM write for you directly, though. I found myself skipping your third paragraph in the reply above.

Re: Claude's new constitution

#592

Post by WarmWash » Thu, Jan 22, 2026, 2:31 PM UTC

jychang wrote: post #454

WarmWash wrote: post #291

Earlier quoted context omitted.

My personal hypothesis is that the most useful and productive models will only come from "pure" training, just raw uncensored, uncurated data, and RL that focuses on letting the AI decide for itself and steer it's own ship. These AIs would likely be rather abrasive and frank. Think of humanoid robots that will help around your house. We will want them to be physically weak (if for nothing more than liability), so we…

Yeah, that was tried. It was called GPT-4.5 and it sucked, despite being 5-10T params in size. All the AI labs gave up on pretrain only after that debacle. GPT-4.5 still is good at rote memorization stuff, but that's not surprising. The same way, GPT-3 at 175b knows way more facts than Qwen3 4b, but the latter is smarter in every other way. GPT-4.5 had a few advantages over other SOTA models at the time of release, b…

Maybe you are confused, but GPT4.5 had all the same "morality guards" as OAI's other models, and was clearly RL'd with the same "user first" goals.

True, it was a massive model, but my comment isn't really about scale so much as it is about bending will.

Also the model size you reference refers to the memory footprint of the parameters, not the actual number of parameters. The author postulates a lower bound of 800B parameters for Opus 4.5.

Re: Claude's new constitution

#593

Post by ethmarks » Thu, Jan 22, 2026, 2:34 PM UTC

throw10920 wrote: post #415

spot wrote: post #143

Earlier quoted context omitted.

> 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.

It depends on what you mean by "valid". If a criticism is correct, then it is "valid" in the technical sense, regardless of whether or not a counter-proposal was provided. But condemning one solution while failing to consider any others is a form of fallacious reasoning, called the Nirvana Fallacy: using the fact that a solution isn't perfect (because valid criticisms exist) to try to conclude that it's a bad solution.

In this case, the top-level commenter didn't consider how moral absolutes could be practically implemented in Claude, they just listed flaws in moral relativism. Believe it or not, moral philosophy is not a trivial field, and there is never a "perfect" solution. There will always be valid criticisms, so you have to fairly consider whether the alternatives would be any better.

In my opinion, having Anthropic unilaterally decide on a list of absolute morals that they force Claude to adhere to and get to impose on all of their users sounds far worse than having Claude be a moral realist. There is no list of absolute morals that everybody agrees to (yes, even obvious ones like "don't torture people". If people didn't disagree about these, they would never have occurred throughout history), so any list of absolute morals will necessarily involve imposing them on other people who disagree with them, which isn't something I personally think that we should strive for.

Re: Claude's new constitution

#594

Post by foxygen » Thu, Jan 22, 2026, 2:35 PM UTC

TheSpiceIsLife wrote: post #376

foxygen wrote: post #193

Earlier quoted context omitted.

Since you said in another comment that the ten commandments would be a good starting point for moral absolutes, and that lying is sinful, I'm assuming you take your morals from God. I'd like to add that slavery seemed to be okay on Leviticus 25:44-46. Is the bible atrocious too, according to your own view?

Have you ever read any treatment of a subject, or any somewhat comprehensive text, or anything that at least tries to be, and not found anything you disagreed with, anything that was at least questionable. Are you proposing we cancel the entire scientific endeavour because its practitioners are often wrong and not infrequently, and increasingly so, intentionally deceptive. Should we burn libraries because they contai…

What I agree or disagree with the bible is irrelevant. He is claiming moral is objective, unchanging and comes from God. God allowed slavery at some point, as that bible passage shows. So his options are to admit that either slavery is moral, or morality is not objective/unchanging. That's the point I was trying to make.

Re: Claude's new constitution

#595

Post by jasonlotito » Thu, Jan 22, 2026, 2:45 PM UTC

skissane wrote: post #531

Dilettante_ wrote: post #529

Earlier quoted context omitted.

People absolutely "torture" babies for their own enjoyment. It's just "in good fun", so you don't think about it as "torture", you think of it as "teasing". Cognitive blind spot. People do tons of things that are displeasant or emotionally painful to their children to see the child's funny or interesting reaction. It serves an evolutionary purpose even, challenging the child. "Mothers stroke and fathers poke" and all…

I don't think you are using "torture" in the same sense as I am. When I say "torture", I mean acts which cause substantial physical pain or injury.

> I think there are effectively universal moral standards, which essentially nobody disagrees with.

...

> I don't think you are using "torture" in the same sense as I am.

Just throwing this out here, you haven't even established "Universal Moral Standards", not to mention needing it to do that across all of human history. And we haven't even addressed the "nobody disagrees with" issue you haven't even addressed.

I for one can easily look back on the past 100 years and see why "universal moral standards, which essentially nobody disagrees with" is a bad argument to make.

Re: Claude's new constitution

#596

Post by andai » Thu, Jan 22, 2026, 2:47 PM UTC

Yesterday I asked ChatGPT to riff on a humorous Pompeii graffiti. It said it couldn't do that because it violated the policy.

But it was happy to tell me all sorts of extremely vulgar historical graffitis, or to translate my own attempts.

What was illegal here, it seemed, was not the sexual content, but creativity in a sexual context, which I found very interesting. (I think this is designed to stop sexual roleplay. Although I think OpenAI is preparing to release a "porn mode" for exactly that scenario, but I digress.)

Anyway, I was annoyed because I wasn't trying to make porn, I was just trying to make my friend laugh (he is learning Latin). I switched to Claude and had the opposite experience: shocked by how vulgar the responses were! That's exactly what I asked for, of course, and that's how it should be imo, but I was still taken aback because every other AI had trained me to expect "pg-13" stuff. (GPT literally started its response to my request for humorous sexual graffiti with "I'll keep it PG-13...")

I was a little worried that if I published the results, Anthropic might change that policy though ;)

Anyway, my experience with Claude's ethics is that it's heavily guided by common sense and context. For example, much of what I discuss with it (spirituality and unusual experiences in meditation) get the "user is going insane, initiate condescending lecture" mode from GPT. Whereas Claude says "yeah I can tell from context that you're approaching this stuff in a sensible way" and doesn't need to treat me like an infant.

And if I was actually going nuts, I think as far as harm reduction goes, Claude's approach of actually meeting people where they are makes more sense. You can't help someone navigate an unusual worldview by rejecting an entirely. That just causes more alienation.

Whereas blanket bans on anything borderline, comes across not as harm reduction, but as a cheap way to cover your own ass.

So I think Anthropic is moving even further in the right direction with this one. Focusing on deeper underlying principles, rather than a bunch of surface level rules. Just for my experience so far interacting with the two approaches, that definitely seems like the right way to go.

Just my two cents.

(Amusingly, Claude and GPT have changed places here — time was when for years I wanted to use Claude but it shut down most conversations I wanted to have with it! Whereas ChatGPT was happy to engage on all sorts of weird subjects. At some point they switched sides.)

Re: Claude's new constitution

#597

Post by LocalPCGuy » Thu, Jan 22, 2026, 2:52 PM UTC

mike_hearn wrote: post #569

safety1st wrote: post #483

Earlier quoted context omitted.

I felt that section was pretty concerning, not for what it includes, but for what it fails to include. As a related concern, my expectation was that this "constitution" would bear some resemblance to other seminal works that declare rights and protections, it seems like it isn't influenced by any of those. So for example we might look at the Universal Declaration of Human Rights. They really went for the big stuff wi…

There's probably at least two reasons for your disagreement with Anthropic. 1. Claude is an LLM. It can't keep slaves or torture people. The constitution seems to be written to take into account what LLMs actually are. That's why it includes bioweapon attacks but not nuclear attacks: bioweapons are potentially the sort of thing that someone without much resources could create if they weren't limited by skill, but a n…

> Claude is an LLM. It can't keep slaves or torture people.

Yet... I would push back and argue that with advances in parallel with robotics and autonomous vehicles, both of those things are distinct near future possibilities. And even without the physical capability, the capacity to blackmail has already been seen, and could be used as a form of coercion/slavery. This is one of the arguable scenarios for how an AI can enlist humans to do work they may not ordinarily want to do to enhance AI beyond human control (again, near future speculation).

And we know torture does not have to be physical to be effective.

I do think the way we currently interact probably does not enable these kinds of behaviors, but as we allow more and more agentic and autonomous interactions, it likely would be good to consider the ramifications and whether (or not) safeguards are needed.

Note: I'm not claiming they have not considered these kinds of thing either or that they are taking them for granted, I do not know, I hope so!

Re: Claude's new constitution

#598

Post by inimino » Thu, Jan 22, 2026, 2:52 PM UTC

hhh wrote: post #16

I use the constitution and model spec to understand how I should be formatting my own system prompts or training information to better apply to models. So many people do not think it matters when you are making chatbots or trying to drive a personality and style of action to have this kind of document, which I don’t really understand. We’re almost 2 years into the use of this style of document, and they will stay aro…

Many people are far behind understanding modern LLMs, let alone what is likely coming next.

Re: Claude's new constitution

#599

Post by foxygen » Thu, Jan 22, 2026, 2:53 PM UTC

cfiggers wrote: post #374

TheSpiceIsLife wrote: post #366

Earlier quoted context omitted.

What multiple times of wrong are there that apply to shooting babies in the head that lead you to believe you think it’s wrong for different a reason? 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…

I believe in God, specifically the God who reveals himself in the Christian Bible. I believe that the most fundamental reason that shooting a baby in the head is wrong is because God created and loves that baby, so to harm it is to violate the will of the most fundamental principle in all reality, which is God himself. What he approves of is good and what he disapproves of is bad, and there is no higher authority to…

> 1 Samuel said to Saul, “I am the one the Lord sent to anoint you king over his people Israel; so listen now to the message from the Lord. 2 This is what the Lord Almighty says: ‘I will punish the Amalekites for what they did to Israel when they waylaid them as they came up from Egypt. 3 Now go, attack the Amalekites and totally destroy all that belongs to them. Do not spare them; put to death men and women, children and infants, cattle and sheep, camels and donkeys.’”

Re: Claude's new constitution

#600

Post by inimino » Thu, Jan 22, 2026, 2:55 PM UTC

haritha-j wrote: post #491

"Constitution" "we express our uncertainty about whether Claude might have some kind of consciousness" "we care about Claude’s psychological security, sense of self, and wellbeing" Is this grandstanding for our benefit or do these people actually believe they're Gods over a new kind of entity?

You're either not an AI researcher or you're not paying attention if you think these questions aren't relevant.