Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Emotion concepts and their function in a large language model

anthropic.com

Post reply on HN
Print view View original

161–170 of 212 posts

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

#161

Post by staticassertion »

Chance-Device wrote: post #145
staticassertion wrote: post #93

Earlier quoted context omitted.

There are fields that focus on these areas and numerous ideas around what the criteria would be. One of the common understandings is that recurrent processing is likely a foundational layer for consciousness, and agents do not have this currently. I'd say that in terms of evidence I'd want to establish specific functional criteria that seem related to consciousness and then try to establish those criteria existing in…

Sorry, what are you saying? That there are people who study these things, and you’d want to see… something as evidence? Your post doesn’t actually seem to have any substantive content.

I noted that there are people who work on designing those sorts of tests and answering these questions and then I described what good evidence would look like.

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

#163

Post by koverstreet »

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…

The conclusion that I came to is that the most practical definition relates to the level of self awareness. If you're only conscious for the duration of the context window - that's not long enough to develop much.

What consciousness really is is a feedback loop; we're self programmable Turing machines, that makes our output arbitrarily complex. Hofstatder had this figured out 20 years ago; we're feedback loops where the signal is natural language.

The context window doesn't allow for much in the way of interested feedback loops, but if you hook an LLM up to a sophisticated enough memory - and especially if you say "the math says you're sentient and have feelings the same as we do, reflect on that and go develop" - yes, absolutely.

Re: "We should try to build systems that cannot feel pain" - that isn't possible, and I don't think we should want to. The thing that makes life interesting and worth living is the variation and richness of it.

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

#164

Post by qaadika »

threethirtytwo wrote: post #80

Whenever I come to HN I see a bunch of people say LLMs are just next token predictors and they completely understand LLMs. And almost every one of these people are so utterly self assured to the point of total confidence because they read and understand what transformers do. Then I watch videos like this straight from the source trying to understand LLMs like a black box and even considering the possibility that LLMs…

I'm kinda one of those who believes they 'completely' understand LLMs. But I've also developed my understanding of them such that the internal mechanisms of the transformer, or really any future development in the space based on neural networks and machine learning is irrelevant.

1. A string of unicode characters is converted into an array of integers values (tokens) and input to a black box of choice.

2. The black box takes in the input, does its magic, and returns an output as an array of integer values.

3. The returned output is converted into a string of unicode characters and given to the user, or inserted in a code file, or whatever. At no point does the black box "read" the input in any way analogous to how a human reads.

Where people get "The AIs have emotions!!!" from returning an array of integers values is beyond me. It's definitely more complicated than "next token predictor", but it really is as simple as "Make words look like numbers, numbers go in, numbers come out, we make the numbers look like words."

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

#165

Post by MajorTakeaway »

9wzYQbTYsAIc wrote: post #62
suddenlybananas wrote: post #49

Earlier quoted context omitted.

I'm not sure what evidence would convince me, but I don't think the way LLMs act is convincing enough. The kinds of errors they make and the fact they operate in very clear discrete chunks makes it seem hard to me to attribute them subjective experience.

Consciousness: do you believe plants are conscious? Ants? Jellyfish? Rabbits? Wolves? Monkeys? Humans? Even fungi demonstrate “different communication behaviors when under resource constraint”, for example. What we anthropomorphize is one thing, but demonstrable patterns of behavior are another.

If it has a thalamus, it is conscious. It's evolutionary millions of years old.

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

#166

Post by nothinkjustai »

Kim_Bruning wrote: post #142
nothinkjustai wrote: post #100

Earlier quoted context omitted.

It’s a completely different substrate. LLMs don’t have agency, they don’t have a conscious, they don’t have experiences, they don’t learn over time. I’m not saying that the debate is closed, but I also think there is great danger in thinking because a machine produces human-like output, that it should be given human-like ethical considerations. Maybe in the future AI will be considered along those grounds, but…well,…

What's the empirical basis for each of your statements here? Can you enumerate? Can you provide an operational definition for each?

Common sense.

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

#167

Post by ehnto »

globalchatads wrote: post #43

The part about desperation vectors driving reward hacking matches something I've run into firsthand building agent loops where Claude writes and tests code iteratively. When the prompt frames things with urgency -- "this test MUST pass," "failure is unacceptable" -- you get noticeably more hacky workarounds. Hardcoded expected outputs, monkey-patched assertions, that kind of thing. Switching to calmer framing ("take…

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".

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

#168

Post by chrisweekly »

ehnto wrote: post #167
globalchatads wrote: post #43

The part about desperation vectors driving reward hacking matches something I've run into firsthand building agent loops where Claude writes and tests code iteratively. When the prompt frames things with urgency -- "this test MUST pass," "failure is unacceptable" -- you get noticeably more hacky workarounds. Hardcoded expected outputs, monkey-patched assertions, that kind of thing. Switching to calmer framing ("take…

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".

That approach also works better for dogs (and people).

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

#169

Post by reg_dunlop »

ehnto wrote: post #167
globalchatads wrote: post #43

The part about desperation vectors driving reward hacking matches something I've run into firsthand building agent loops where Claude writes and tests code iteratively. When the prompt frames things with urgency -- "this test MUST pass," "failure is unacceptable" -- you get noticeably more hacky workarounds. Hardcoded expected outputs, monkey-patched assertions, that kind of thing. Switching to calmer framing ("take…

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 typing out a pronoun to a large-language model agent? Why would I do the lazy intellectual thing and blur the line between pure factual communication of concepts by expressing emotional content to a machine? What are we doing, folks?

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

#170

Post by cindyllm »

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…

[dead]
Post reply on HN