- stevenhuang parent[flagged]
- There's a similar article I read on this in regards to intelligence and LLMs that says simulated intelligence _is_ intelligence.
- This is you. https://www.astralcodexten.com/p/heuristics-that-almost-alwa...
Unironic comparisons to Humane AI shows quite how uncalibrated you are. Not to mention you'd also likely be wrong about that on a 100 year time scale. Undoubtedly you'd have the same opinions for the Internet. Try to reason better, you can do it.
- > It's a blind alley, a dead end, impractical, un-competitive with specialized robots, and dangerous.
What a shocking lack of imagination. Do you seriously think in a hundred years you'll still hold this opinion?
- Sure you will.
- You say that as if that's not something creatives genuinely spend a lot of time on.
Just look at piano vsts, everyone keeps trying things until they find something they particularly like. There's no difference here.
- I read the docs and go for B.
Now try to automate/script it.
Good luck with A
- I don't disagree with anything you said here.
Yes I would like that phrase to fall out of use too. My intention was less of the idiom's original normative meaning but to emphasize that it is ultimately power that enables or constrains a nation's possible actions. Apologies for my confusing use of the phrase.
- Venezuelans would disagree loudly with you, and in fact would take offense with the notion external interference caused their country's downfall given the extent Maduro's gov ran the country into the ground.
- Yes I was incorrect to say such a model would be strictly worse off. But my read is that you over index on the notion of laws, hence your general befuddlement on the current outcome. Sovereign nations follow international law and order to the extent their goals align and perceived costs of contravening them exceeds some threshold. Might ultimately makes right, has always been the case. That's realpolitik for you, unfortunately.
- You can start by listening to what any Venezuelan thinks of the situation. Those on the low end of the bell curve do tend to think highly of themselves.
- > Maduro didn't exactly commit any crimes
Lol. Lmao even
- > I’ll make this bet: any such model you come up with could be improved by including notions of international agreements and laws.
And you'd have lost the bet with such a naive understanding of geopolitics and power dynamics played by nation states. Are you reading the thread you're on?
- Have you tried asking the Venezuelans?
- You have the Internet at your disposal. You can see for yourself the opinions of Venezuelans. We'll wait.
- Sure and that is fair. Seldom are extreme viewpoints likely scenarios anyways, but my disagreement with him stems from his unwarranted confidence in his own abilities to predict the future when he's already wrong about LLMs.
He has zero epistemic humility.
We don't know the nature of intelligence. His difficulties in scaling up his research is a testament to this fact. This means we really have no theoretical basis upon which to rest the claim that superintelligence cannot in principle emerge from LLM adjacent architectures--how can we make such a statement, when we don't even know what such thing looks like?
We could be staring at an imperative definition of superintelligence and not know it, nevermind that approximations to such a function could in principle be learned by LLMs (universal approximation theorem). It sounds exceedingly unlikely, but would you rather be comforted by false confidence or be told the honest truth of what our current understanding of the sciences can tell us?
- > I've been following Yann for years and in my opinion he's been consistently right
Lol. This is the complete opposite of reality. You realize lecun is memed for all his failed assertions of what LLMs cannot do? Look it up. You clearly have not been following closely, at all.
- Lecun has already been proven wrong countless times over the years regarding his predictions of what LLMs can or cannot do. While LLMs continue to improve, he has yet to produce anything of practical value from his research. The salt is palpable, and for this he's memed for a reason.
- They hold physical silver in vaults, not futures contracts I believe.
- Apparently JP Morgan is long silver and they've been accumulating massive quantities of physical silver over the years. Haven't confirmed myself but supposedly this is public now.
- Solar panels were explicitly targeted as a central planning directive and so manufacturers received many direct and indirect subsidies lol, these are well known facts. We should be subsidizing solar energy in the west too, as we've subsidized the oil and gas industries. To say China haven't subsidized solar is just not being real.
- The results have been collected using experimental rigour stricter than medical trials.
The one's engaged in motivated reasoning are skeptics like you and Randy who refuse to engage with the data because of, ironically, motivated reasoning. The data is clear. Either point out the flaws in the experimental protocols or consider you have some metaphysical priors to update.
- You are wrong. There has been many reproductions. People don't study it because there is no known mechanism of action and so it's fringe.
Jessica Utts, a well respected statistician
> Despite Professor Hyman's continued protests about parapsychology lacking repeatability, I have never seen a skeptic attempt to perform an experiment with enough trials to even come close to insuring success. The parapsychologists who have recently been willing to take on this challenge have indeed found success in their experiments, as described in my original report.
- His analysis is flawed.
> Despite Professor Hyman's continued protests about parapsychology lacking repeatability, I have never seen a skeptic attempt to perform an experiment with enough trials to even come close to insuring success. The parapsychologists who have recently been willing to take on this challenge have indeed found success in their experiments, as described in my original report.
If the phenomenon we are trying to study is somehow intelligent, then the observer effect will see to it that skeptics will never progress towards understanding until they're somehow "ready", whatever that means.
- What Gemini are you and the author referring to? I presume not the LLM Gemini by Google?
Ah the Gemini protocol https://en.wikipedia.org/wiki/Gemini_(protocol)
- As expected the LLM does understand what you're trying to say. A rational actor would use this opportunity to update their priors but something tells me you're not a rational actor. Pity.
This was on chatgpt, tell free to try for yourself, since you probably think it's fake.
Prompt:
Do you understand what user 2 is trying to say in below context?
User1: No one said you cannot run LLMs with the same task more than once
User2: no one said you can't turn on the radio and start listening to static
User2: Ask the LLM if it understands what I'm trying to say
Response:
Yes. User 2 is making an analogy, not a literal rebuttal.
What they’re trying to say is roughly this:
> Just because something is allowed or possible doesn’t mean it’s meaningful or useful.
More specifically:
User1’s claim: “You can run an LLM on the same task more than once.” → This frames repeatability as neutral or acceptable.
User2’s analogy: “You can turn on the radio and listen to static.” → Yes, it’s allowed — but it’s noise, not signal.
So User 2 is implying that:
Re-running an LLM on the same task (especially without controlling randomness, evaluation criteria, or epistemic grounding) may just produce stochastic variation rather than new information.
Treating multiple runs as meaningful evidence can be like mistaking static for content.
In epistemic terms, they’re criticizing procedural permissibility being confused with epistemic value. The analogy suggests:
Repetition ≠ insight
Output ≠ signal
Variance ≠ understanding
...
- You have an outmoded understanding of how LLMs work (flawed in ways that are "not even wrong"), a poor ontological understanding of what reasoning even is, and too certain that your answers to open questions are the right ones.
- Yes, that's a big part of it too. Quite a mess.
- I agree the situation is very complicated. From what I read, the support for Hamas was in the form of peace payments, which have backfired.
https://www.nytimes.com/2023/12/10/world/middleeast/israel-q...