That's what I'm asking... Why not? I'm alluding to what seems to be a culturally self-imposed refusal to seek legal remedies among makers and hackers. We have Jeff Geerling (who I generally like and agree with) disappointingly referring to the GPL as a "social contract," as though it can have no legal force behind it.
The biggest companies in the world use licenses to weild power over people, but heaven forbid people use the same body of law to their benefit.
The way I understood the 80% is that is the margin on the actual product. 36% is what remains after the “investments” in moonshot projects nobody asked for.
Would you say that displaying image of something on a screen qualifies as actually happening? Writing data on a storage medium? What about a roomba vacuuming a floor?
> Would you say that displaying image of something on a screen qualifies as actually happening?
Yeah, of course.
What I'm addressing is "if we turn 100% of everything about neurons into numbers we can do calculations on those numbers and it's the same as that stuff actually happening with real neurons". Which is entirely wrong. A trajectory calculation isn't different from actually firing a projectile because it's not precise enough but because it's something else entirely.
Can descriptions of brains do consciousness? I don't know why we'd expect that they could. You can describe a fire in all the detail you like, and burn nothing.
Can electronic brains be conscious? I dunno. If I had to guess? Sky's-the-limit ignore-all-physical-and-temporal-constraints? Probably. Within the bounds of what humans will ever achieve? Maybe. I doubt they'd look as little-removed from tabulation machines as ours are, though. Like I definitely don't think you get there solving math problems. That would be surprisingly metaphysical.
A fire is something that happens externally and has observable actions. An internal state is not. Your thoughts may take a physical form but that form cannot be demonstrated. Unless you can show me telekinesis then you have only intuition. Why are you so certain that these intuitions are true?
Possibly metaphysical naturalism is wrong and supernatural things exist! And maybe thoughts (and/or the experience of consciousness) are among those supernatural things. That could be it. In which case sure, maybe solving math problems can create consciousness (why not?).
Do I think supernatural things like thoughts not being represented in physical reality exist? I defer to Russell's Teapot on this one and lean toward "no". If they do, then attempting to reason about anything gets pretty iffy anyway. Who knows what might exist or be true, in that case!
There is nothing that says that if thoughts are not made in brains they must be supernatural. You are making conclusions not based on evidence or argument.
> you can easily construe it to imply that he believes there's something fundamentally special about human consciousness that cannot be reproduced by a machine. On the other hand you could interpret his perspective, which I think is more in line with his real perspective, as implyimg that replicating the human mind machine requires truly replicating it physically
I'm not sure I understand. If we must replicate a human brain physically in order to create something that has consciousness, then how is that not something 'special that cannot be reproduced by a machine'?
Your comment does serve the point I was making. Still there is a perspective that if you could artificially reproduce the human mind top to bottom, a truly perfect reproduction in other words, then you ought to be able to trigger an identical consciousness. In other words yes special type of machine is needed for the machine nevertheless not some special soul.
Of course the counterpoint and maybe the one you're making is that special machine ought to be simply called a soul machine and we could all agree it would be very difficult to reproduce it and it is intrinsically special... but maybe that's for the very specific form of Consciousness we have... but maybe there are other forms
That perspective is 'biological exceptionalism' and requires that there is something specific to biology that allows consciousness while precluding anything not biological. For that to be convincing there must be a mechanism and no one has proposed anything other than a soul for that.
This is where I would say that to defining that mechanism is the hard problem... it's a mischaracterization to call it the easy problem. But it doesn't require a soul
2. If free markets did exist they would not conform to the theory that people are using when they think of what free markets are, since people do behave rationally, power dynamics are real, and no consumer can have all of the information needed to make rational decisions even if that information were available
3. The market is providing solutions to its own failures without fixing the underlying failures because it is more profitable this way. Is buying something from a company that mitigates a problem created by the same company actually a free market, or is it just extraction?
What would you think of a person who said that they are already convinced that an opposing view could not be correct without even hearing the arguments for it?
> Funny, but you could argue this is actively harmful to the web.
Was not followed by an actual argument that it is harmful to the web. The comment was an assertion, not an argument.
So we are left in the inconvenient position of rejecting hypothetical arguments, and others defending the philosophical possibility that a valid argument does exist.
Without the argument being explicit then there can be no retort to it, so closing your mind before hearing it demonstrates that the argument itself is irrelevant. One could thus conclude that the existence of a valid argument is not itself a condition for my question.
We also shouldn’t close our minds to the possibility of an eigen-retort, one which covers all possible arguments already made or argued in the future regarding the consequences of this website on the health of the Internet.
Someone who is aware of the eigen-retort would therefore not need to hear the argument.
Since I haven’t heard either the hypothetical argument or the hypothetical eigen-retort yet, I’ll withhold my judgement.
I concede that the my question was loaded, but the assumptions behind it are grounded in practical experience. Regardless, I have not committed myself either to the existence of an argument, I just stated that its existence was not a condition for the validity of my question for SwellJoe. The statement which was made can mean a number of possible things, but we cannot know what unless the question is answered. So the existence of the retort is revealed by the question, and until that reveal we are limited to questions or assumptions.
I'm reasonably confident there is no argument that I would buy.
I hate AI slop more than average, but this is not slop being injected into human places. This is a dedicated dumping ground for slop, paid for by the owner/instigator of said slop. I don't have to go there, and it's not trying to fool anyone and no one will be fooled by it.
AI slop on a forum or social media or on facebook convincing boomers that a black person slapped a cop or whatever racist garbage they're being fed today? Fetch the guillotine.
AI slop as part of a dumb art project on somebody's personal website that isn't trying to manipulate or mislead? Have at it. Go nuts. It's your press, print as many pages of slop as you like.
So, I have exhaustively covered the possible arguments I can come up with for why this could be "actively harmful for the web", and rejected them outright.
That clarifies things much better than the original statement, but rejecting arguments you have conceived of which fail does not preclude the existence of those that do not, and thus the original question still remains.
I don't see a contradiction. What they are saying is that no amount of non-ambiguous presentation can make poor content acceptable. They never said the presentation was meaningless.
Example: A friend has died and consolation is given. No amount of consolation makes the death a good thing for you, but there is still a difference in how that consolation is presented to you.
Why can a colony of ants do things beyond any capabilities of the ants they contain? No ant can make a decision, but the colony can make complex ones. Large systems composed of simple mechanisms become more than the sum of their parts. Economies, weather, and immune systems, to name a few, all work this way.
They were approaching this from an interpretability standpoint, but the more interesting finding in there is that models come up with an answer that fits their training and context provided. CoT is generated to fit the anticipated answer.
In these studies, there are examples of CoT that directly contradicts the response these models ultimately settle on.
If you read these further, researchers believe this effect does exist, but only insofar as priming the model for the answer it was likely to give anyway and only when queries are in-distribution. If there was actual reasoning involved rather than pattern matching, we would expect to see performance improvements on out of distribution requests. Instead we see longer CoT actually degrade performance on out of distribution tasks.
The fact that common sense, simple logical questions (like should you drive or walk to the car wash) cannot be answered by LLMs simply because they don't appear often enough within pre- or post-training datasets despite CoT is just another indicator of them not performing what we would call reasoning or intent inference or whatever other anthropomorphic behavior we want to assign them. They remain spicy autocomplete with the caveat that the RLHF portion of their training _can_ result in goal seeking and problem-solving behavior... in the narrow set of problems that have been explicitly optimized for in their training.
> If you read these further, researchers believe this effect does exist, but only insofar as priming the model for the answer it was likely to give anyway and only when queries are in-distribution.
'Demonstrably' means one thing. They said it demonstrably improves outputs. If they want to hedge that with theories about why it would result in the same thing without it then they need to remove that word or come up with a coherent thesis, or I am misunderstanding what you are trying to argue.
> The fact that common sense, simple logical questions (like should you drive or walk to the car wash) cannot be answered by LLMs
These are trick questions designed to fool LLMs. It is like saying that people cannot visualize because optical illusions exist, or people don't understand the laws of physics because they fall for magic tricks. It is a failure mode in the way they operate but it doesn't say anything about their operation besides that they fail in that mode for specific reasons.
> They remain spicy autocomplete
And nuclear power plants remain spicy steam generators, but that says nothing actually useful nor offers any insight. Reducing something to its basic mechanism in order to dismiss its output is lazy and thought-terminating.
This is just a no-true-Scotsman defense of reasoning. We were talking about inferring intent.
If someone recorded the inner monologue of human decision-making, would it look like a logician’s workbook? No, I don’t think it would. People like to pretend they are rational.
When they say "pretends to" here they're talking about something quantifiable, that the extra text it outputs for CoT barely feeds back into the decisionmaking at all. In other words it's about as useful as having the LLM make the decision and then "explain" how it got there; the extra output is confabulation.
You make a good point. I had the impression they were using 'pretend' as a Chinese Room shortcut in that they are asserting that it is incapable of reasoning and only appears to be capable from the outside, which is completely irrelevant and unfalsifiable.
reply