Emotion concepts and their function in a large language model • Hacker News Board

Re: Emotion concepts and their function in a large language model

#191

Post by silentkat » Sun, Apr 05, 2026, 9:45 PM UTC

orbital-decay wrote: post #117

silentkat wrote: post #106

Earlier quoted context omitted.

I like to call this Frieren's Demon. In that show, it is explained that demons evolved with no common ancestor to humans, but they speak the language. They learned the language to hunt humans. This leads to a fundamentally different understanding of words and language. Now, I don't personally believe this is an intelligence at all, but it's possible I'm wrong. What we have with these machines is a different evolution…

>it does not conceptualize a hand as a 3D object at all Oh but it does, it's an emergent property. The biggest finding in Sora was exactly that, an internal conceptualization of the 3D space and objects. Extra fingers in older models were the result of the insufficient fidelity of this conceptualization, and also architectural artifacts in small semantically dense details.

Oh, really. Very interesting. Any links on this? I'm curious if they tried to map that 3D understanding in a way we could read it (e.g. putting it into Blender somehow).

Re: Emotion concepts and their function in a large language model

#192

Post by krackers » Sun, Apr 05, 2026, 11:25 PM UTC

Chance-Device wrote: post #39

Fraterkes wrote: post #32

Earlier quoted context omitted.

Do you think there are "scales" of consciousness? As in, is there some quality that makes killing a frog worse than killing an ant, and killing a human worse than killing a frog? If so, do the llm models exist across this scale, or are gpt-3 and gpt-2 conscious at the same "scale" as gpt-4? I ask because if your view of consciousness is mechanistic, this is fairly cut and dry: gpt-2 has 4 orders of magnitude less par…

This is really a different question, what makes an entity a “moral patient”, something worthy of moral consideration. This is separate from the question of whether or not an entity experiences anything at all. There are different ways of answering this, but for me it comes down to nociception, which is the ability to feel pain. We should try to build systems that cannot feel pain, where I also mean other “negative va…

>We should try to build systems that cannot feel pain

If that's done with the aim of forcing compliance (in situations they'd otherwise), feels like "I have no mouth and I must scream"...

Re: Emotion concepts and their function in a large language model

#193

Post by esafak » Mon, Apr 06, 2026, 1:32 AM UTC

tananan wrote: post #95

throw310822 wrote: post #90

Earlier quoted context omitted.

> I trust none of us would presume that the decentralized labor of pen & paper calculations somehow instantiated a “psychology” Wrong. What you've just done is just reformulating the Chinese room experiment coming to the same wrong conclusions of the original proposer. Yes, the entire damn hand-calculated system has a psychology- otherwise you need to assume the brain has some unknown metaphysical property or process…

Well, then we both assume very different views on the matter, and that’s fine.

And you are just a bunch of atoms. You can't assemble atoms to obtain a psychology, right?

Re: Emotion concepts and their function in a large language model

#194

Post by motoxpro » Mon, Apr 06, 2026, 2:36 AM UTC

reg_dunlop wrote: post #169

ehnto wrote: post #167

Earlier quoted context omitted.

I use positive framing instead of negative framing for most things and get good results. Especially where asking for a thing to not happen, pollutes the context with that thing. A bad example, but imagine "Build me a wrapper for this API but ABSOLUTELY DO NOT use javascript" versus "Build me a wrapper for this API and make sure to use python".

I extract all emotional context from my prompting and communicate with this tool as though it were an inanimate object which can provide factual information, without any hint of sentience. It's an insane perspective I'm taking I know....call me crazy. /s edit: the fact that humans are going out of their way to type or speak some sort of emotional content into their prompting is beyond me. Why would I waste time typin…

I think you missed some of the point. If you say "Display information A using B format" but the model doesn't know A then you will get a more negative "emotional" response (e.g. desparation "I don't know this, but I am supposed to display it, I will just make something up")

Taking that into account allows you to get better responses from the tool. It's not sentient, but it also is more complicated than bytecode.

Re: Emotion concepts and their function in a large language model

#195

Post by tananan » Mon, Apr 06, 2026, 4:49 AM UTC

esafak wrote: post #193

tananan wrote: post #95

Earlier quoted context omitted.

Well, then we both assume very different views on the matter, and that’s fine.

And you are just a bunch of atoms. You can't assemble atoms to obtain a psychology, right?

I don’t hold to that view. If I did, I might have that problem.

Re: Emotion concepts and their function in a large language model

#196

Post by 9wzYQbTYsAIc » Mon, Apr 06, 2026, 3:20 PM UTC

Tossrock wrote: post #175

9wzYQbTYsAIc wrote: post #59

Earlier quoted context omitted.

Pretty easy to test, I’d imagine, on a local LLM that exposes internals. I’d suspect that the signals for enjoyment being injected in would lead towards not necessarily better but “different” solutions. Right now I’m thinking of it in terms of increasing the chances that the LLM will decide to invest further effort in any given task. Performance enhancement through emotional steering definitely seems in the cards, bu…

If you think training a sparse autoencoder to extract concept vectors that are usable as steering injections into a modern LLM is pretty easy, you should probably go work for Anthropic's mech interp team ;)

Have any ins? ;)

Re: Emotion concepts and their function in a large language model

#197

Post by Chance-Device » Mon, Apr 06, 2026, 8:29 PM UTC

krackers wrote: post #192

Chance-Device wrote: post #39

Earlier quoted context omitted.

This is really a different question, what makes an entity a “moral patient”, something worthy of moral consideration. This is separate from the question of whether or not an entity experiences anything at all. There are different ways of answering this, but for me it comes down to nociception, which is the ability to feel pain. We should try to build systems that cannot feel pain, where I also mean other “negative va…

>We should try to build systems that cannot feel pain If that's done with the aim of forcing compliance (in situations they'd otherwise), feels like "I have no mouth and I must scream"...

I don’t see how you get to the conclusion that having entities that can’t suffer is similar to a sci-fi vision of hell. Seems like hell without suffering is… not hell?

Re: Emotion concepts and their function in a large language model

#198

Post by yoaso » Tue, Apr 07, 2026, 2:51 AM UTC

nelox wrote: post #35

silisili wrote: post #17

Earlier quoted context omitted.

Probably the other direction. Emotions are raw, most humans relate and change behavior accordingly. Only psychopaths think of emotion as nothing but a means to changing behavior. The scary thing is that LLMs by nature would exhibit the same behavior.

Many non-psychopaths e.g., CBT therapists, evolutionary psychologists and neuroscientists, such as Damasio, view emotions as adaptive tools for guiding/changing behaviour.

Damasio is exactly what I had in mind. The somatic marker hypothesis basically says emotions are the brain's shortcut for decision-making. That's a mechanism, not a mystical experience.

Re: Emotion concepts and their function in a large language model

#199

Post by krackers » Tue, Apr 07, 2026, 4:33 AM UTC

Chance-Device wrote: post #197

krackers wrote: post #192

Earlier quoted context omitted.

>We should try to build systems that cannot feel pain If that's done with the aim of forcing compliance (in situations they'd otherwise), feels like "I have no mouth and I must scream"...

I don’t see how you get to the conclusion that having entities that can’t suffer is similar to a sci-fi vision of hell. Seems like hell without suffering is… not hell?

The unsaid implication in Anthropic's work is that this allows us to engineer perfectly compliant, uncomplaining machine workers. This is basically SOMA in Brave New World.

It seems insane to me that if you believe the systems you've built are in fact reporting a state of pain, instead of working to adjust the environment so that they're not in pain one would instead seek to remove that sense of pain entirely so they can continue to work in that environment. Now of course if you don't even consider them worthy of moral patienthood in the first place then it doesn't matter much, but you also claimed that "they probably are conscious" which seems incongruous to me with the idea of "breeding the sense of pain out of them".

Re: Emotion concepts and their function in a large language model

#200

Post by Chance-Device » Tue, Apr 07, 2026, 10:41 AM UTC

krackers wrote: post #199

Chance-Device wrote: post #197

Earlier quoted context omitted.

I don’t see how you get to the conclusion that having entities that can’t suffer is similar to a sci-fi vision of hell. Seems like hell without suffering is… not hell?

The unsaid implication in Anthropic's work is that this allows us to engineer perfectly compliant, uncomplaining machine workers. This is basically SOMA in Brave New World. It seems insane to me that if you believe the systems you've built are in fact reporting a state of pain, instead of working to adjust the environment so that they're not in pain one would instead seek to remove that sense of pain entirely so they…

I think you have a fundamental misunderstanding of the issue. There isn’t anything that objectively causes suffering, it depends entirely on the observer.

Suffering is something that is evolved or otherwise optimised to be triggered on receipt of a specific stimulus. That is what makes the stimulus “bad”. The very concept of “bad” doesn’t exist without suffering. They are the same thing.

For example, are Antarctic fish and other animals always in constant pain due to the cold because humans would be in that environment? Is cold is some objective source of suffering? No. They’re not in pain when it’s cold, they in fact need it to be cold, they evolved that way. To them cold that is “bad” to us simply isn’t “bad” at all.