[HN Gopher] What's Going on in Machine Learning? Some Minimal Mo...
       ___________________________________________________________________
        
       What's Going on in Machine Learning? Some Minimal Models
        
       Author : taywrobel
       Score  : 183 points
       Date   : 2024-08-22 19:05 UTC (1 days ago)
        
 (HTM) web link (writings.stephenwolfram.com)
 (TXT) w3m dump (writings.stephenwolfram.com)
        
       | ralusek wrote:
       | There should be a Godwin's Law for Stephen Wolfram. Wolfram's
       | Law: as the length of what he's saying increases, the probability
       | it will be about cellular automata approaches 1.
       | 
       | That being said, I'm enjoying this. I often experiment with
       | neural networks in a similar fashion and like to see people's
       | work like this.
        
         | nxobject wrote:
         | ...and the probability that he names something after himself
         | approaches 1/e.
        
         | throwup238 wrote:
         | There's a Wolfram Derangement Syndrome to go along with it,
         | too: https://news.ycombinator.com/item?id=38975876
        
       | wrsh07 wrote:
       | Because of the computational simplicity, I think there's a
       | possibility that we will discover very cheap machine learning
       | techniques that are discrete like this.
       | 
       | I think this is novel (I've seen BNN
       | https://arxiv.org/pdf/1601.06071 This actually makes things
       | continuous for training, but if inference is sufficiently fast
       | and you have an effective mechanism for permutation, training
       | could be faster using that)
       | 
       | I am curious what other folks (especially researchers) think. The
       | takes on Wolfram are not always uniformly positive but this is
       | interesting (I think!)
        
         | sdenton4 wrote:
         | So, the thing is that linear algebra operations are very cheap
         | already... you just need a lot of them. Any other 'cheap'
         | method is going to have a similar problem: if the unit is small
         | and not terribly expressive, you need a whole lot of them. But
         | it will be compounded by the fact that we don't have decades of
         | investment in making these new atomic operations as fast and
         | cheap as possible.
         | 
         | A good take-away from the Wolfram writeup is that you can do
         | machine learning on any pile of atoms you've got lying around,
         | so you might as well do it on whatever you've got the best
         | tooling for - right now this is silicon doing fixed-point
         | linear algebra operations, by a long shot.
        
           | wrsh07 wrote:
           | Sort of, yes. But if the existing thing were "the cheapest",
           | quantization wouldn't exist.
           | 
           | It depends on what your constraint is! So if you're memory
           | constrained (or don't have a GPU), a bunch of 1 bit atoms
           | with operations that are very fast on CPU might be better
           | 
           | I haven't thought very deeply about whether it's provably
           | faster to do gradient descent on 32 bits vs 8, but it
           | probably always is. What's the next step to speed up
           | training?
        
           | wrsh07 wrote:
           | But to your point - that is how I feel about graph nns vs
           | transformers or the fully connected set (GPUs are so good at
           | transformers and fully connected nns, even if there is a
           | structure that makes sense we don't have the hardware to have
           | it make sense.... Unless grok makes it cheap??)
        
           | dboreham wrote:
           | My take is that the neural network is a bit of a red herring
           | -- people poked around in brains to see what was going on and
           | noticed a network structure with many apparently simple
           | computing nodes. So they tried making similar structures in
           | software and quickly discovered they could do some
           | interesting things. But it may turn out that the neural
           | network was just nature's best implementation for "field
           | programmable matrix manipulation". You can implement the
           | functionality in other ways, not resembling neural networks.
        
             | wrsh07 wrote:
             | I think the point of wolfram's essay is that you don't need
             | the base unit of computation to be a dot product
        
       | krackers wrote:
       | >Instead what seems to be happening is that machine learning is
       | in a sense just "hitching a ride" on the general richness of the
       | computational universe. It's not "specifically building up
       | behavior one needs"; rather what it's doing is to harness
       | behavior that's "already out there" in the computational
       | universe.
       | 
       | Is this similar to the lottery ticket hypothesis?
       | 
       | Also the visualizations are beautiful and a nice way to
       | demonstrate the "universal approximation theorem"
        
       | jmount wrote:
       | Wow- Wolfram "invented" cellular automata, neural nets, symbolic
       | algebra, physics and so much more.
        
       | jksk61 wrote:
       | Is a TL;DR available or at least some of the ideas covered?
       | Because after 3 paragraphs it seems the good old "it is actually
       | something resembling a cellular automata" post by Wolfram.
        
       | usgroup wrote:
       | Tsetlin machines have been around for some time:
       | 
       | https://en.wikipedia.org/wiki/Tsetlin_machine
       | 
       | They are discrete, individually interpretable, and can be
       | configured into complicated architectures.
        
         | saberience wrote:
         | https://www.literal-labs.ai/
         | 
         | These guys are trying to make chips for ML using Tsetlin
         | machines...
        
         | abecedarius wrote:
         | This looks like it might be interesting or might not, and I
         | wish it said more in the article itself about why it's cool
         | rather than listing technicalities and types of machines. Do
         | you have a favorite pitch in those dozens of references at the
         | end?
        
       | delifue wrote:
       | > But now we get to use a key feature of infinitesimal changes:
       | that they can always be thought of as just "adding linearly"
       | (essentially because e2 can always be ignored to e). Or, in other
       | words, we can summarize any infinitesimal change just by giving
       | its "direction" in weight space
       | 
       | > a standard result from calculus gives us a vastly more
       | efficient procedure that in effect "maximally reuses" parts of
       | the computation that have already been done.
       | 
       | This partially explains why gradient descent becomes mainstream.
        
       | achrono wrote:
       | >All one will be able to say is that somewhere out there in the
       | computational universe there's some (typically computationally
       | irreducible) process that "happens" to be aligned with what we
       | want.
       | 
       | >There's no overarching theory to it in itself; it's just a
       | reflection of the resources that were out there. Or, in the case
       | of machine learning, one can expect that what one sees will be to
       | a large extent a reflection of the raw characteristics of
       | computational irreducibility
       | 
       | Strikes me as a very reductive and defeatist take that flies in
       | the face of the grand agenda Wolfram sets forth.
       | 
       | It would have been much more productive to chisel away at it to
       | figure out _something_ rather than expecting the Theory to be
       | unveiled in full at once.
       | 
       | For instance, what I learn from the kinds of playing around that
       | Wolfram does in the article is: neural nets are but one way to
       | achieve learning & intellectual performance, and even within that
       | there are a myriad different ways to do it, but most importantly:
       | there is a breadth vs depth trade-off, in that neural nets being
       | very broad/versatile are not quite the best at going
       | deep/specialised; you need a different solution for that (e.g.
       | even good old instruction set architecture might be the right
       | thing in many cases). This is essentially why ChatGPT ended up
       | needing Python tooling to reliably calculate 2+2.
        
         | jstanley wrote:
         | > ChatGPT ended up needing Python tooling to reliably calculate
         | 2+2.
         | 
         | This is untrue. ChatGPT very reliably calculates 2+2 without
         | invoking any tooling.
        
           | achrono wrote:
           | Sure, but I think you get my point.
        
           | nyrikki wrote:
           | Nit, it predicts that it is the token '4'.
           | 
           | Token frequency in pre-training corpus and the way
           | tokenization is implemented impacts arithmetic proficiency
           | for LLMs.
           | 
           | OpenAI calls this out in the GPT4 technical report.
        
             | SkyBelow wrote:
             | You can see this by giving it broken code and seeing what
             | it can predict.
             | 
             | I gave copilot a number of implementations of factorial
             | with the input of 5. When it recognized the correct
             | implementations, it was able to combine the ideas of
             | "factorial", "5", and "correct implementation" to output
             | 120. But when I gave it buggy implementations, it could
             | recognize they were wrong, but the concepts of "factorial",
             | "5", and "incorrect implementation" weren't enough for it
             | to output the correct wrong result produced. Even when I
             | explained its attempts to calculate the wrong output was
             | itself wrong, it couldn't 'calculate' the right answer.
        
               | e12e wrote:
               | This makes very little sense (as a contrast to chatgpt
               | predicted that the likely continuation of factorial and 5
               | is 120).
               | 
               | Perhaps if you are able to share the chat session it's
               | possible to see if you likely confused the issue with
               | various factorial implementations - or got chatgpt to run
               | your code with 5 as input?
               | 
               | I mean the code is redundant:
               | 
               | https://chatgpt.com/share/be249097-5067-4e3d-93c7-3eebedb
               | 510...
        
       | vessenes wrote:
       | Classic Wolfram -- brilliant, reimplements / comes at a current
       | topic using only cellular automata, and draws some fairly deep
       | philosophical conclusions that are pretty intriguing.
       | 
       | The part I find most interesting is his proposal that neural
       | networks largely work by "hitching a ride" on fundamental
       | computational complexity, in practice sort of searching around
       | the space of functions representable by an architecture for
       | something that works. And, to the extent this is true, that puts
       | explainability at fundamental odds with the highest value / most
       | dense / best deep learning outputs -- if they are easily
       | "explainable" by inspection, then they are likely not using all
       | of the complexity available to them.
       | 
       | I think this is a pretty profound idea, and it sounds right to me
       | -- it seems like a rich theoretical area for next-gen information
       | theory, essentially are their (soft/hard) bounds on certain kinds
       | of explainability/inspectability?
       | 
       | FWIW, there's a reasonably long history of mathematicians
       | constructing their own ontologies and concepts and then people
       | taking like 50 or 100 years to unpack and understand them and
       | figure out what they add. I think of Wolfram's cellular automata
       | like this, possibly really profound, time will tell, and unusual
       | in that he has the wealth and platform and interest in boosting
       | the idea while he's alive.
        
         | phyalow wrote:
         | Agree. (D)NNs have a powerful but somewhat loose inductive
         | bias. They're great at capturing surface-level complexity but
         | often miss the deeper compositional structure. This looseness,
         | in my opinion, stems from a combination of factors:
         | architectures that are not optimally designed for the specific
         | task at hand, limitations in computational resources that
         | prevent us from exploring more complex and expressive models,
         | and training processes that don't fully exploit the available
         | information or fail to impose the right constraints on the
         | fitting process.
         | 
         | The ML research community generally agrees that the key to
         | generalization is finding the shortest "program" that explains
         | the data (Occam's Razor / MDL principle). But directly
         | searching for these minimal programs (architecture space,
         | feature space, training space etc) is exceptionally dificult,
         | so we end up approximating the search to look something like
         | GPR or circuit search guided by backprop.
         | 
         | This shortest program idea is related to Kolmogorov complexity
         | (arises out of classical Information Theory) - i.e. the length
         | of the most concise program that generates a given string
         | (because if your not operating on the shortest program, then
         | there is looseness/or overfit!). In ML, the training data is
         | the string, and the learned model is the program. We want the
         | most compact model that still captures the underlying patterns.
         | 
         | (D)NNs have been super successful, their reliance on
         | approximations suggests there's plenty of room for improvement
         | in terms of inductive bias and more program-like
         | representations. I think approaches that combine the
         | flexibility of neural nets with the structured nature of
         | symbolic representations will lead to more efficient and
         | performant learning systems. It seems like a rich area to just
         | "try stuff" in.
         | 
         | Leslie Valiant touches on some of the same ideas in his book
         | "Probably approximately correct" which tries to nail down some
         | of the computational phenomena associated with the emergent
         | properties of reality (its heady stuff).
        
           | jderick wrote:
           | What is GPR?
        
             | phyalow wrote:
             | Gaussian Process Regression (a form of Bayesian
             | Optimisation to try and get to the right "answer"/parameter
             | space sooner) - explained in some context here...
             | 
             | https://brendanhasz.github.io/2019/03/28/hyperparameter-
             | opti...
             | 
             | In saying that random param search still works well enough
             | in many cases.
        
         | mjburgess wrote:
         | > And, to the extent this is true, that puts explainability at
         | fundamental odds with the highest value / most dense / best
         | deep learning outputs -- if they are easily "explainable" by
         | inspection, then they are likely not using all of the
         | complexity available to them.
         | 
         | Could you define explainability in this context?
        
         | captainclam wrote:
         | "Classic Wolfram -- brilliant, reimplements / comes at a
         | current topic using only cellular automata, and draws some
         | fairly deep philosophical conclusions that are pretty
         | intriguing."
         | 
         | Wolfram has a hammer and sees everything as a nail. But its a
         | really interesting hammer.
        
         | taneq wrote:
         | > searching around the space of functions representable by an
         | architecture for something that works
         | 
         | That's... why we're here?
        
         | taneq wrote:
         | > searching around the space of functions representable by an
         | architecture for something that works
         | 
         | That's... why we're here? How else could we characterise what
         | any learning algorithm does?
        
         | bob1029 wrote:
         | > neural networks largely work by "hitching a ride" on
         | fundamental computational complexity
         | 
         | If you look at what a biological neural network is _actually_
         | trying to optimize for, you might be able to answer The Bitter
         | Lesson more adeptly.
         | 
         | Latency is a caveat, not a feature. Simulating a biologically-
         | plausible amount of real-time delay is almost certainly
         | wasteful.
         | 
         | Leaky charge carriers are another caveat. In a computer
         | simulation, you can never leak any charge (i.e. information) if
         | you so desire. This would presumably make the simulation more
         | efficient.
         | 
         | Inhibitory neurology exists to preserve stability of the
         | network within the constraints of biology. In a simulation,
         | resources are still constrained but you could use heuristics
         | outside biology to eliminate the fundamental need for this
         | extra complexity. For example, halting the network after a
         | limit of spiking activity is met.
         | 
         | Learning rules like STDP may exist because population members
         | learned experiences cannot survive across generations. If you
         | have the ability to copy the exact learned experiences from
         | prior generations into new generations (i.e. cloning the
         | candidates in memory), this learning rule may represent a
         | confusing distraction more than a benefit.
        
       | DataDive wrote:
       | I find it depressing that every time Stephen Wolfram wants to
       | explain something, he slowly gravitates towards these simplistic
       | cellular automata and tries to explain everything through them.
       | 
       | It feels like a religious talk.
       | 
       | The presentation consists of chunks of hard-to-digest, profound-
       | sounding text followed by a supposedly informative picture with
       | lots of blobs, then the whole pattern is repeated over and over.
       | 
       | But it never gets to the point. There is never an outcome, never
       | a summary. It is always some sort of patterns and blobs that are
       | supposedly explaining everything ... except nothing useful is
       | ever communicated. You are supposed to "see" how the blobs are
       | "everything..." a new kind of Science.
       | 
       | He cannot predict anything; he can not forecast anything; all he
       | does is use Mathematica to generate multiplots of symmetric
       | little blobs and then suggests that those blobs somehow explain
       | something that currently exists
       | 
       | I find these Wolfram blogs a massive waste of time.
       | 
       | They are boring to the extreme.
        
         | ActionHank wrote:
         | Got me feeling self conscious here.
         | 
         | I often explain boring things with diagrams consisting of boxes
         | and arrows, some times with different colours.
        
         | benlivengood wrote:
         | I think that unless Wolfram is directly contradicting the
         | Church-Turing thesis it is ok to skip over the finite automata
         | sections.
         | 
         | It is a given from Church-Turing that some automata will be
         | equivalent to some turing machines, and while it is a profound
         | result the specific details of the equivalence isn't super
         | important unless, perhaps, it becomes super fast and efficient
         | to run the automata instead of Von Neumann architecture.
        
       | nuz wrote:
       | I can never read comments on any wolfram blog on HN because
       | they're always so mean spirited. I'm seeing a nerdy guy
       | explaining things from a cool new perspective I'm excited to read
       | through. The comments almost always have some lens against him
       | being 'self centered' or obsessing about cellular automata (who
       | cares we all have our obsessions)
        
         | whalee wrote:
         | The complaint about his ego is warranted, but he also earned
         | it. Wolfram earned his PhD in particle physics from cal tech at
         | 21 years old. Feynman was on his thesis committee. He spent
         | time at the IAS. When he speaks about something, no matter in
         | which configuration he chooses to do so, I am highly inclined
         | to listen.
        
         | leobg wrote:
         | Same here on anything Elon. HN is like an uncle who knows a lot
         | and teaches you new things every time you hang out with him...
         | but who also has a few really weird sore spots that you better
         | never mention in his presence.
        
           | aantix wrote:
           | Agree - the whole "he's great" vs "he's evil and a con" just
           | gets old.
           | 
           | Everyone is a complex mixture of both.
           | 
           | My dad loved reading and sharing technical subjects with me
           | and is probably part of the reason why I enjoy a good career
           | today.
           | 
           | He also cheated on my mom for 30 years for which we didn't
           | discover until the last 3 years of his life. We didn't have
           | much money growing up. He probably took her out to dinner
           | with money we didn't have.
           | 
           | It's perfectly normal to both love and hate parts of someone,
           | but not reject them as a whole.
        
             | tines wrote:
             | Elon's not more evil than anyone else, he's just way dumber
             | than everyone expected him to be when we were in the
             | honeymoon phase.
        
               | jandrese wrote:
               | Elon is unusual not in how much his fans adore him (and
               | they do), but the degree to which his haters hate him.
               | I've seen plenty of places where people simply stating
               | facts or talking about their own experiences gets
               | downvoted to invisibility.
               | 
               | Even points that you wouldn't think would be
               | controversial, like "Tesla disrupted the EV industry that
               | was previously only interested in building compliance
               | cars for rich crunchy-granola city weirdos", are almost
               | instantly shot down. Anything that isn't just outright
               | hatred for Elon gets slammed to hell. It's almost
               | impossible to have a balanced discussion about him or his
               | companies.
               | 
               | I also don't think he's as dumb as people think. He has
               | an eye for industries that are ripe for disruption and
               | has actually managed to deliver at least twice so far.
               | There is no question at all that SpaceX is the premier
               | launch provider in the world today (I know I'm getting
               | downvoted for saying this). Tesla sells about half of the
               | EVs sold in the US and basically didn't exist 10 years
               | ago. The jury is still out on the Boring company.
               | Neuralink and Optimus are still too new to tell. Even
               | Paypal is a good example of seeing a market gap and
               | exploiting it. Twitter/X was the real stinker. Elon is
               | exactly the wrong guy to be running a social media
               | company, and worse he thinks he is winning by out-foxing
               | Fox News. He's got that engagement algorithm brain that
               | results when you chase bigger numbers. It is the biggest
               | right wing black hole you could imagine and Elon himself
               | has fallen right down the center. You couldn't ask for a
               | more perfect radicalization system than he has built with
               | the "pay for voice" scheme with basically no bot
               | protection.
        
               | tines wrote:
               | Agree about SpaceX, but I'm not sure how much of that is
               | about Elon. Tesla used to be awesome, its nascency is
               | what I was referring to as the "honeymoon phase," but it
               | definitely feels like it's gone downhill with the
               | Cybertruck goofiness. Like it feels like it has some
               | awesome engineers that do the cool stuff, and then you
               | have Elon interfering from the top and injecting his
               | goofy ass ideas while everyone else is trying to make the
               | company work. Feels like Tesla is like, super cool
               | engineering and then oh yeah there's Elon over there in
               | the corner playing with his toys and we try to keep him
               | from messing things up too much. Every Tesla engineer
               | I've heard from echoes this, he springs random
               | requirements on them and they often learn of new product
               | requirements or features from his Twitter posts and then
               | they're in panic mode trying to implement whatever half-
               | baked stupid idea he had on the toilet at 3 AM.
               | 
               | Most of your last paragraph about Twitter is what has
               | caused me to think he's dumb, in spite of having a few
               | early successes which may be attributable to survivor
               | bias (you have millions of people taking random risks,
               | some of them are going to pan out randomly, and after the
               | first one you have money so it's easy to make more
               | money). Calling the rescuer guy a "pedo guy" during the
               | crisis in Thailand and just myriad other inane utterances
               | have tanked his valuation in my eyes.
               | 
               | But I think I might agree with you that "dumb" is the
               | wrong word. Perhaps "unwise" is what I'm feeling. He may
               | have skills and intelligence to apply those skills to
               | start businesses or make money or whatever. But he
               | doesn't apply that intelligence to the end that we might
               | call wisdom, and I think that's what I as well as a lot
               | of other people are trying to articulate when they say
               | he's dumb. Agree with you though, people aren't black and
               | white.
        
               | jandrese wrote:
               | Maybe "poor emotional intelligence". Like you said, a
               | person can plausibly get lucky on their first business
               | and make it big once. But to do it repeatedly and to such
               | a large degree takes skill. Say what you will about his
               | politics, but his companies deliver. Even Hyperloop,
               | which is basically just a bad subway, still has more
               | buildout than pretty much any subway system in the US in
               | the past decade. That might just be Elon willing to lose
               | a ton of money on it to get it built though.
               | 
               | Might be interesting to compare and contrast the Las
               | Vegas Hyperloop vs. the Las Vegas Monorail. Which is more
               | of a boondoggle?
        
       | dbrueck wrote:
       | I believe that this is one of the key takeaways for reasoning
       | about LLMs and other seemingly-magical recent developments in AI:
       | 
       | "tasks--like writing essays--that we humans could do, but we
       | didn't think computers could do, are actually in some sense
       | computationally easier than we thought."
       | 
       | It hurts one's pride to realize that the specialized thing they
       | do isn't quite as special as was previously thought.
        
         | wredue wrote:
         | Computers still aren't writing essays. They are stringing words
         | together using copied data.
         | 
         | If they were writing essays, I would suggest that it wouldn't
         | be so ridiculously easy to pick out the obviously AI articles
         | everywhere.
        
           | dboreham wrote:
           | > They are stringing words together using copied data.
           | 
           | Which is what we will eventually realize is what humans are
           | doing too.
        
           | GaggiX wrote:
           | >They are stringing words together using copied data
           | 
           | Ah yes and image generators are just rearranging stolen
           | pixels.
        
       | deng wrote:
       | Say what you will about Wolfram: he's a brilliant writer and
       | teacher. The way he's able to simplify complex topics without
       | dumbing them down is remarkable. His visualizations are not only
       | extremely helpful but usually also beautiful, and if you happen
       | to have Mathematica on hand, you can easily reproduce what he's
       | doing. Anytime someone asks me for a quick introduction to LLMs,
       | I always point them to this article of his, which I still think
       | is one of best and most understandable introductions to the
       | topic:
       | 
       | https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-...
        
         | mebiles wrote:
         | "entropy is the log of the number of states that a system can
         | be in that are consistent with all the information known about
         | that system". he is amazing at explaining things.
        
       | aeonik wrote:
       | This article does a good job laying the foundation of why I think
       | homiconic languages are so important, and doing AI in languages
       | that aren't, are doomed to stagnation in the long term.
       | 
       | The acrobatics that Wolfram can do with the code and his analysis
       | is awesome, and doing the same without the homoiconicity and
       | metaprogramming makes my poor brain shudder.
       | 
       | Do note, Wolfram Language is homoiconic, and I think I remember
       | reading that it supports Fexprs. It has some really neat
       | properties, and it's a real shame that it's not Open Source and
       | more widely used.
        
         | jderick wrote:
         | I'd be curious to see an example of what you are talking about
         | wrt his analysis here.
        
           | aeonik wrote:
           | I don't know how to express my thoughts coherently in such a
           | small space and time, but I will try. There isn't "one"
           | example.
           | 
           | ----------
           | 
           | Almost all the code and its display is some form of meta-
           | programming. Stephen Wolfram is literally brute-
           | forcing/fuzzing all combinations of "code".
           | - Permuting all the different rules/functions in a given
           | scope         - evolutionary adapting/modifying them
           | - graphing and analyzing those structures         - producing
           | the HTML for display
           | 
           | I get that "normal machine learning" is also permuting
           | different programs. But it's more special when you are using
           | the same language for the whole stack. There is a canyon that
           | you have to cross without homoiconicity, (granted I don't
           | know exactly how Wolfram generated and analyzed everything
           | here, but I have used his language before, and I see the
           | hallmarks of it).
           | 
           | I can't really copy and paste an example for you, because
           | plaintext struggles. Here is an excerpt some fanciness in
           | there:                  And as an example, here are the
           | results of the forward and backward methods for the problem
           | of learning the function f[x] = <graph of the function>  ,
           | for the "breakthrough" configurations that we showed above:
           | 
           | You might see a "just" a small .png interspersed in plain
           | text. The language and runtime itself has deep support for
           | interacting with graphics like this.
           | 
           | The only other systems that I see that can juggle the same
           | computation/patterns around like this are pure object
           | oriented systems like Smalltalk/Pharo. You necessarily need
           | first class functions to come even close to the capability,
           | but as soon as you want to start messing with the rules
           | themselves, you need some sort of term re-writing, lisp
           | macro, or fexpr (or something similar?).
           | 
           | Don't get me wrong, you can do it all "by hand" (with
           | compiler or interpreter help), you can generate the strings
           | or opcodes for a processor or use reflection libraries,
           | generate the graphs and use some HTML generator library to
           | stitch it all together. But in the case of this article, you
           | can clearly see that he has _direct command over the contents
           | of these computations_ in his Wolfram Language compared to
           | other systems, because _it 's injected right into his prose_.
           | The outcome here can look like Jupyter labs or other
           | notebooks. But in homoiconic languages there is a lot more
           | "first-class citizenry" than you get with notebooks. The
           | notebook format is just something that can "pop out" of
           | certain workflows.
           | 
           | If you try to do this with C++ templates, Python Attribute
           | hacking, Java byte-code magic... like... you can, but it's
           | too hard and confusing, so most people don't do it. People
           | just end up creating specific DSLs or libraries for different
           | forms of media/computations, with templating smeared on top.
           | Export to a renderer and call it a day -> _remember to have
           | fun designing a tight feedback loop here_.  /s
           | 
           | Nothing is composable, and it makes for very brittle systems
           | as soon you want to inject some part of a computation into
           | another area of the system. It's way _way_ overspecified.
           | 
           | Taking the importance of homoiconicty further, when I read
           | this article I just start extrapolating, moving past xor or
           | "rule 12", and applying these techniques to the symbolic
           | logic, like Tseltin machine referenced in another part of
           | this thread: https://en.wikipedia.org/wiki/Tsetlin_machine
           | 
           | Or using something like miniKanran:
           | https://en.wikipedia.org/wiki/MiniKanren
           | 
           | It seems to me that training AI on these kinds systems will
           | give them far more capability in producing useful code that
           | is compatible with our systems, because, for starters, you
           | have to dedicate less neuronal connections on syntax parsing
           | with a grammar that is actually fundamentally broken and ad
           | hoc. But I think there are far deeper reasons than just this.
           | 
           | ----------
           | 
           | I think it's so hard to express this idea because it's like
           | trying to explain why having arms and legs is better than
           | not. It's applied to every part of the process of getting
           | from point A to point B.
           | 
           | Also, addendum, I'm not 100% sure homoiconicity it "required"
           | per se. I suppose any structured and reversible form of
           | "upleveling" or "downleveling" logic that remains accessible
           | from all layers of the system would work. Even good ol' Lisp
           | macros have hygiene problems that can be solved, e.g. by
           | Racket's _syntax-parse_.
        
       | jderick wrote:
       | It is interesting to see the type of analysis he does and the
       | visualizations are impressive, but the conclusions don't really
       | seem too surprising. To me, it seems the most efficient learning
       | algorithm will not be simpler but rather much more complex,
       | likely some kind of hybrid involving a multitude of approaches.
       | An analogy here would be looking at modern microprocessors --
       | although they have evolved from some relatively simple machines,
       | they involve many layers of optimizations for executing various
       | types of programs.
        
       ___________________________________________________________________
       (page generated 2024-08-23 23:01 UTC)