LessWrong 2.0 Reader

I think you are very confused about how to interpret disagreements around which mental processes ground consciousness. These disagreements do not entail a fundamental disagreement about what consciousness is as a phenomenon to be explained. 

Regardless of that though, I just want to focus on one of your "referents of consciousness" here, because I also think the reasoning you provide for your particular claims is extremely weak. You write the following

#9: Symbol grounding.  Even within a single interaction, an LLM can learn to associate a new symbol to a particular meaning, report on what the symbol means, and report that it knows what the symbol means.

The behavioural capacity you describe does not suffice for symbol grounding. Indeed, the phrase "associate a new symbol to a particular meaning" begs the question, because the symbol grounding problem asks how it is that symbolic representations in computing systems can acquire meaning in the first place. 

The most famous proposal for what it would take to ground symbols was proposed by Harnad in his classic 1990 paper. Harnad thought grounding was sensorimotor in nature and required both iconic and categorical representations, where iconic representations are formed via "internal analog transforms of the projections of distal objects on our sensory surfaces" and categorical representations are "those 'invariant features' of the sensory projection that will reliably distinguish a member of a category from any nonmembers" (Harnad though connectionist networks were good candidates for forming such representations and time has shown him to be right). Now, it seems to me highly unlikely that LLMs exhibit their behavioural capacities in virtue of iconic representations of the relevant sort, since they do not have "sensory surfaces" in anything like the right kind of way. Perhaps you disagree, but merely describing the behavioural capacities is not evidence.

Notably, Harnad's proposal is actually one of the more minimal answers in the literature to the symbol grounding problem. Indeed, he received significant criticism for putting the bar so low. More demanding theorists have posited the need for multimodal integration (including cognitive and sensory modalities), embodiment (including external and internal bodily processes), normative functions, a social environment and more besides. See Barsalou for a nice recent discussion and Mollo and Milliere for an interesting take on LLMs in particular.

In case anyone’s wondering, if there’s a 1/n chance of something happening each time (iid), and you try n times (for large n), then it will happen m times with probability $(1/n!)/e$. So 0,1,2,3… hits would be 36.8%, 36.8%, 18.4%, 6.1%, 1.5%, 0.3%, … Nice how it sums to one.

Sing along! https://suno.com/song/35d62e76-eac7-4733-864d-d62104f4bfd0

That said, while the methodology isn't sound, I wouldn't be surprised if there was in fact a real conflationary alliance around the term, since the term is used in a context where deciding if someone is conscious or not (like uploads) have pretty big moral and political ramifications too, so there are pressures for the word to be politicized and not truth-tracking.

I enjoyed the hell out of LessOnline [LW · GW] and would love to go to this too. I'm not sure yet if I can make the budget work; is anyone I met at LO looking for roommates?

Every year I have run the Rationalist Megameetup [...], we’ve run out of space and I’ve had people ask if they can come anyway. We could limit the size by taking applications and turning people away.

I thought about this after LO -- overcrowding is an attractor state for conventions -- and wondered if overcrowding could be managed by dynamic pricing. If you know the size of the space, it feels like you could fill it nearly exactly by making the price some function of (time-before-event, number-of-remaining-slots). This is one of the few crowds where that sort of mathematical jiggery might not alienate people.

(on the other hand, I expect it would make budgeting the event much harder, so I dunno).

The density of butter is reasonably close to 1 avoirdupois ounce per 1 fluid ounce, but is definitely not exactly equal:

https://kg-m3.com/material/butter gives the density as 0.95033293516 oz./fl. oz., or 0.911 kg/m^3.

(The link you provide doesn’t give a source; the data at the above link is sourced from the International Network of Food Data Systems (INFOODS).)

Further commentary:

The density of water (at refrigerator temperatures) is ~1 g/cm^3. 1 oz. = ~28.35 g; 1 fl. oz. = ~ 29.57 cm^3; thus the density of water is (1/28.35) / (1/29.57) = ~1.043 = oz./fl. oz. (This is, of course, equal to 0.95033293516 / 0.911, allowing for rounding and floating point errors.)

Note that the composition of butter varies. In particular, it varies by the ratio of butterfat to water (there are also butter solids, i.e. protein, but those are a very small part of the total mass). American supermarket butter has approx. 80% butterfat; Amish butter, European butters (e.g. Kerrygold), or premium American butters (e.g. Vital Farms brand) have more butterfat (up to 85%). Butterfat is less dense than water (thus the more butterfat is present, the lower the average density of the stick of butter as a whole—although this doesn’t make a very big difference, given the range of variation).

Given the numbers in the paper at the last link, we can calculate the average density (specific gravity) of butter (assuming butterfat content of a cheap American supermarket brand) as 0.8 * 0.9 + 0.2 * 1.0 = 0.92. This approximately matches our 0.911 kg/m^3 number above.

Fwiw I was too much of a coward/too conflict averse to say anything myself but I agree with this critique. (As I've said in my post [LW · GW] I think half of all people are talking about mostly the same thing when they say 'consciousness', which imo is fully compatible with the set of responses Andrew listed in his post given how they were collected.)

In related puzzles I did hear something a while ago now, Bostrom perhaps.  You have say 6 challenging events to achieve to get from no life to us. They are random and some of those steps are MUCH harder than the others, but if you look at the successful runs, you cant in hindsight see what they are. For life its say no life to life, simple single cell to complex cell and perhaps 4 other events that aren't so rare.

A run is a sequence of 100 steps where you either don't achieve the end state (all 6 challenging events achieved in order, or you do)

There is a 1 in a million chance that a run is successful.

Now if you look at the successful runs, you cant then in hindsight see what events were really hard and which weren't.  The event with 1/10,000 chance at each step may have taken just 5 steps in the successful run, it couldn't take 10,000 steps because only 100 are allowed etc.

I don't think so. Compare the following two requests:

(1) Describe a refrigerator without using the word refrigerator or near-synonyms. 

(2) Describe the structure of a refrigerator in terms of moving parts and/or subprocesses.

The first request demands the tabooing of words; the second request demands an answer of a particular (theory-laden) form. I think the OPs request is like request 2. What's more, I expect submitting request 2 to a random sample of people would license the same erroneous conclusion about "refrigerator" as it did about "consciousness".

This is not to say there are no special challenges associated with "consciousness" that do not hold for "refrigerator". Indeed, I believe there are. However, the basic point that people can be referring to a single phenomenon even if they have different beliefs about the phenomenon's underlying structure seems to me fairly straightforward. 

Edit: I see sunwillrise gave a much more detailed response already. That response seems pretty much on the money to me. 

I will also point people to this paper if they are interested in reading an attempt by a prominent philosopher of consciousness at defining it in minimally objectionable terms. 

Hmmm, my long term strategy is to build wealth and then do it myself, but I suppose that would require me to leave academia eventually :)

I wonder if MIRI would fund it? Doesn't seem likely.