We are in an economic mania right now. Governments, corporations, startups, you name it, are all afraid of being left behind. They are buying up memory, disks, computing capacity because, well, if they don't, someone else--one of their competitors--will.

Supply will be expanded and built out while demand remains high.

How long will this take? That's the trillion dollar question. It could be months or it could be years, but at some point, demand and supply will come back into closer to equilibrium. Whether that's because demand crashes or because supply builds up to meet demand is another open question. This has to be one of the greatest repositioning of capital in recent memory.

Hah, agreement on something!

But, how do you know that humans aren't deterministic? Maybe my exact brain and body, when given the exact same external stimuli over the past however many years, would produce the exact same results? Can't prove it either way, so are you operating on faith and belief about human intelligence?

LLMs are generally considered a combination of stochastic and deterministic (training, specifically). Critics often use the term "stochastic parrots," for example. Since LLMs rely on randomness, if you have a truly random number source, does that make them non-deterministic?

Probably better to not go down this road.

It's too bad, because Dawkins has written some interesting things, and hey, being the inventor of the word "meme" and memetics is a pretty big deal.

His reaction here is just astoundingly ignorant. Reading the dialog where he makes a Trump joke and the LLM responds (predictably) sycophanticly is, to use the modern parlance, just cringe. I would have hoped for a more informed take.

Hah, you're losing your touch! I've seen you troll far better than this.

Ok, then point me to a post on Slashdot where someone says (roughly, even) "it is all just known" when it comes to human intelligence or the brain."

Are you confused or talking to the wrong person? I have said many times that my position is that the existence of a brain that produces intelligence is evidence that human-type intelligence can be built or simulated. If it exists, it can be built. Disagreeing, Gweiher, literally in the post before mine, brought up the concept of "Physicalism." Physicalism is, definitionally, a metaphysical belief. The opposite of physicalism is another metaphysical belief, idealism, that more or less centers around the belief that reality is formed in the mind and spirit.

So, no, I did not bring up metaphysics or spiritualism.

Unbelievable...

That's pretty myopic thinking.

First of all, you're wrong. An attacker does not need "console" access but rather does need some kind of shell or execution ability. Given how sophisticated attacks today are often chains of vulnerabilities, I would not at all be surprised to see cPanel or other web vulnerabilities chained with this. Furthermore, if someone who doesn't work for you already has that level of access (meaning ability to execute a program on a computer), you already screwed up? Ok, and what if a trusted user account is compromised?

I don't understand the reaction.

For small values of "interesting" perhaps!

Point taken.

I think that's a fair statement. I'm personally not terribly interested in metaphysics. It's one of those topics that strikes me as like Christians arguments on the nature of Christ--is Christ purely divine? Is he both man and divine? Is he just a human? I feel like no matter how much energy I (or anyone!) expends on the metaphysical stuff, there's no answer, and not even a way of proving who is right or wrong. And, if I'm wrong? So what? A bit too ethereal for me!

In general, in the absence of decisive evidence either way, I would lean towards "it's possible" as opposed to "it's impossible."

I have never seen anyone on slashdot claim that "it is all just known" when it comes to human intelligence or the brain. Literally, never. It is also absolutely incorrect to say that we have no clue how the human--we have many clues. I have said repeatedly that we don't know it all. What we do know is that humans exist, and humans have human intelligence.

I posited earlier that if it exists, it can be built.

If you want to change the conversation to a metaphysical conversation about the nature of reality and your spiritual beliefs, then who even cares about your complaints about LLM technology? If you insist that human-type intelligence can never be built or simulated, prove that it can never happen. That's just like, your opinion, man.

I had an interesting exchange with Gweihir recently. I don't want to put words in his mouth, but he seems to be of the opinion that it is not proven that the human brain is responsible for human intelligence, that there is something special about human intelligence (that he also believes cannot be simulated or reproduced), and that understanding human intelligence is potentially impossible.

He says "Ah, yes, the deranged claim that we know how the human mind works and it is purely mechanistic. You just excluded yourself from rational discussion by pushing a quasi-religious dogma with no supporting scientifically sound evidence." (Gweihir also often capitalizes "Science".)

I don't know what he believes, but it kind of seems like he believes there is something ineffably unique and special about human intelligence, and he's offended that people ascribe similar "intelligence" words to AI and LLMs. If he wasn't so anti-religious, I would think he was some kind of fundamentalist.

In any case, thank you for the article link to SciAm. It was interesting.

Yes, definitely.

I've been using both Claude and ChatGPT to help me understand a PL/B (a.k.a. DATABUS, similar to COBOL) codebase that I've inherited. It's been great to help with that. The constant gotos, subroutines spread across multiple files, modules, etc., can be really hard to follow across a million+ lines. The company that developed it originally had the same programmers working on it from 1970 to the 2010s. It's dead now, legacy, but still in usage. I have not implemented any LLM generated code, but I did use claude to analyze the compiler and the PL/B source to implement a C program that works with the same file database locking semantics.

FreeBSD has a statically linked /rescue directory that still contains static vi. I haven't had to rely on those tools in years, but they can really come in handy when they're needed.

du -sh /rescue/vi
  12M /rescue/vi

:w!

actually ;-)

I've been using vi/vim for about 30 years. It does have a learning curve, but to get to "basic text editor" level there are really only about 5-6 commands you need to learn. I navigate around a file with regexes, syntax aware shortcuts, etc, and it's just so fast. I can't think of any reason to switch.

I assume this is a joke but vim is (always has been) built-in as long as Macs have been on OS X. Kinda hard to believe that Macs have been UNIX longer than they were on the original MacOS.

% which vim /usr/bin/vim

There's also a pretty reasonable gui port called MacVim, though I rarely use it.

What hardware are you running for local models? (I may have asked this before!)