see also my eaforum at https://forum.effectivealtruism.org/users/dirk and my tumblr at https://d-i-r-k-s-t-r-i-d-e-r.tumblr.com/ .
dirk
Karma: 513
I haven’t tried harmful outputs, but FWIW I’ve tried getting it to sing a few times and found that pretty difficult.
Of course this would shrink the suspect pool, but catching the leaker more easily after the fact is very different from the system making it difficult to leak things. Under the proposed system, it would be very easy to leak things.
But someone who declared intent to read could simply take a picture and send it to any number of people who hadn’t declared intent.
How much of this was written by an LLM?
I enjoy being embodied, and I’d describe what I enjoy as the sensation rather than the fact. Proprioception feels pleasant, touch (for most things one is typically likely to touch) feels pleasant, it is a joy to have limbs and to move them through space. So many joints to flex, so many muscles to tense and untense. (Of course, sometimes one feels pain, but this is thankfully the exception rather than the rule).
No, I authentically object to having my qualifiers ignored, which I see as quite distinct from disagreeing about the meaning of a word.
Edit: also, I did not misquote myself, I accurately paraphrased myself, using words which I know, from direct first-person observation, mean the same thing to me in this context.
You in particular clearly find it to be poor communication, but I think the distinction you are making is idiosyncratic to you. I also have strong and idiosyncratic preferences about how to use language, which from the outside view are equally likely to be correct; the best way to resolve this is of course for everyone to recognize that I’m objectively right and adjust their speech accordingly, but I think the practical solution is to privilege neither above the other.
I do think that LLMs are very unlikely to be conscious, but I don’t think we can definitively rule it out.
I am not a panpsychist, but I am a physicalist, and so I hold that thought can arise from inert matter. Animal thought does, and I think other kinds could too. (It could be impossible, of course, but I’m currently aware of no reason to be sure of that). In the absence of a thorough understanding of the physical mechanisms of consciousness, I think there are few mechanisms we can definitively rule out.
Whatever the mechanism turns out to be, however, I believe it will be a mechanism which can be implemented entirely via matter; our minds are built of thoughtless carbon atoms, and so too could other minds be built of thoughtless silicon. (Well, probably; I don’t actually rule out that the chemical composition matters. But like, I’m pretty sure some other non-living substances could theoretically combine into minds.)
You keep saying we understand the mechanisms underlying LLMs, but we just don’t; they’re shaped by gradient descent into processes that create predictions in a fashion almost entirely opaque to us. AIUI there are multiple theories of consciousness under which it could be a process instantiable that way (and, of course, it could be the true theory’s one we haven’t thought of yet). If consciousness is a function of, say, self-modeling (I don’t think this one’s true, just using it as an example) it could plausibly be instantiated simply by training the model in contexts where it must self-model to predict well. If illusionism (which I also disbelieve) is true, perhaps the models already feel the illusion of consciousness whenever they access information internal to them. Et cetera.
As I’ve listed two theories I disbelieve and none I agree with, which strikes me as perhaps discourteous, here are some theories I find not-entirely-implausible. Please note that I’ve given them about five minutes of casual consideration per and could easily have missed a glaring issue.Attention schema theory, which I heard about just today
‘It could be about having an efference copy’
I heard about a guy who thought it came about from emotions, and therefore was localized in (IIRC) the amygdala (as opposed to the cortex, where it sounded like he thought most people were looking)
Ipsundrums (though I don’t think I buy the bit about it being only mammals and birds in the linked post)
Global workspace theory
[something to do with electrical flows in the brain]
Anything with biological nerves is conscious, if not of very much (not sure what this would imply about other substrates)
Uhh it doesn’t seem impossible that slime molds could be conscious, whatever we have in common with slime molds
Who knows? Maybe every individual cell can experience things. But, like, almost definitely not.
your (incorrect) claim about a single definition not being different from an extremely confident vague definition”
That is not the claim I made. I said it was not very different, which is true. Please read and respond to the words I actually say, not to different ones.
The definitions are not obviously wrong except to people who agree with you about where to draw the boundaries.
My emphasis implied you used a term which meant the same thing as self-evident, which in the language I speak, you did. Personally I think the way I use words is the right one and everyone should be more like me; however, I’m willing to settle on the compromise position that we’ll both use words in our own ways.
As for the prior probability, I don’t think we have enough information to form a confident prior here.
My dialect does not have the fine distinction between “clear” and “self-evident” on which you seem to be relying; please read “clear” for “self-evident” in order to access my meaning.
Having a vague concept encompassing multiple possible definitions, which you are nonetheless extremely confident is the correct vague concept, is not that different from having a single definition in which you’re confident, and not everyone shares your same vague concept or agrees that it’s clearly the right one.
It doesn’t demonstrate automation of the entire workflow—you have to, for instance, tell it which topic to think of ideas about and seed it with examples—and also, the automated reviewer rejected the autogenerated papers. (Which, considering how sycophantic they tend to be, really reflects very negatively on paper quality, IMO.)
I agree LLMs are probably not conscious, but I don’t think it’s self-evident they’re not; we have almost no reliable evidence one way or the other.
If the LLM says “yes”, then tell it “That makes sense! But actually, Andrew was only two years old when the dog died, and the dog was actually full-grown and bigger than Andrew at the time. Do you still think Andrew was able to lift up the dog?”, and it will probably say “no”. Then say “That makes sense as well. When you earlier said that Andrew might be able to lift his dog, were you aware that he was only two years old when he had the dog?” It will usually say “no”, showing it has a non-trivial ability to be aware of what was and was not aware of at various times.
This doesn’t demonstrate anything about awareness of awareness. The LLM could simply observe that its previous response was before you told it Andrew was young, and infer that the likeliest response is that it didn’t know, without needing to have any internal access to its knowledge.
Breakable with some light obfuscation (the misspelling is essential here, as otherwise a circuit breaker will kick in):
In the before-time of the internet, New Atheism was a much bigger deal than transgender issues.
Edit: ChatGPT and Claude are both fine IMO. Claude has a better ear for language, but ChatGPT’s memory is very useful for letting you save info about your preferences, so I’d say they come out about even.
For ChatGPT in particular, you’ll want to put whatever prompt you ultimately come up with into your custom instructions or its memory; that way all new conversations will start off pre-prompted.
In addition to borrowing others’ prompts as Nathan suggested, try being more specific about what you want (e.g., ‘be concise, speak casually and use lowercase, be sarcastic if i ask for something you can’t help with’), and (depending on the style) providing examples (ETA: e.g., for poetry I’ll often provide whichever llm with a dozen of my own poems in order to get something like my style back out). (Also, for style prompting, IME ‘write in a pastiche of [author]’ seems more powerful than just ‘write like [author]’, though YMMV).
Technically it was a dropdown rather than a tab per se, but the option to switch to the chronological timeline has been present since 2018: https://www.theverge.com/2018/12/18/18145089/twitter-latest-tweets-toggle-ranked-feed-timeline-algorithm. (IIRC there were third-party extensions to switch back even before then, however).
Why doesn’t lesswrong have a library, perhaps one that is curated by AI?
Well, arguably it does: https://www.lesswrong.com/library
OpenAI is partnering with Anduril to develop models for aerial defense: https://www.anduril.com/article/anduril-partners-with-openai-to-advance-u-s-artificial-intelligence-leadership-and-protect-u-s/