Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-4 Designed a Programming Language

lukebechtel.com

Post reply on HN
Print view View original

191–200 of 338 posts

Re: GPT-4 Designed a Programming Language

#191

Post by Jensson »

RHSman2 wrote: post #186
yowzadave wrote: post #141

Last year, when Blake Lemoine was fired by Google for claiming his AI was sentient, a lot of people on this website sensibly noted that the danger of these chatbots was not that they were sentient, but that average people could easily be tricked into thinking that they were. And now here we are: it seems we tech people are every bit as susceptible to this kind of thinking as the average joes we looked down on. Actual…

The question is when does guessing become a moot point? AlphaGo guessed it’s way to being the best. Can something guess it’s way to evolving into a less guessy thing? I think so. Look at us? I am aware of how it works and used to be ‘it’s ok, it won’t happen’ but now I am actually pretty concerned. We think GAI as the thing but there maybe a reality that doesn’t require full GAI to completely unhinge us. I mean, what…

> AlphaGo guessed it’s way to being the best.

No it didn't, AlphaGo was backed by an algorithm that perfectly understood go and used that to train itself to play go better. That is a completely different situation.

If you tried to make a go engine that only tried to replicate old moves then you'd have a hard time making it perform valid moves. ChatGPT is like such an engine and we just made it perform valid moves most of the time, and now people say "now that it can make valid chess moves it is only a matter of time until it beats masters!". No just statistically reproducing human moves wont lead to a smart chess engine, so why would you think that would make a smart text engine?

Re: GPT-4 Designed a Programming Language

#192

Post by ummonk »

krupan wrote: post #163
marviel wrote: post #151

Earlier quoted context omitted.

I agree with your point about the dangers of chatbots being mistaken as sentient. And I also recognize the dangers of the self-improving systems like this in general -- that's why I'm not letting it run loose with a LangChainAI Agent script to self-execute a new language (though wouldn't that be fascinating?) While the language it generated needs refinement, the design process is iterative, and it takes time to devel…

Ok, but take a step back and really look at the whole situation here. So you've created a machine that solves problems in kind of the same way humans do. Yay? What overall problem is a machine like this solving? How is this better than just having a human do the job? It seems to have most of the same drawbacks as humans, and then some on top of that

I don’t have a massive pool of skilled slave labor I can delegate work to, but I can delegate work to ChatGPT.

Re: GPT-4 Designed a Programming Language

#193

Post by marviel »

geraneum wrote: post #165
marviel wrote: post #151

Earlier quoted context omitted.

I agree with your point about the dangers of chatbots being mistaken as sentient. And I also recognize the dangers of the self-improving systems like this in general -- that's why I'm not letting it run loose with a LangChainAI Agent script to self-execute a new language (though wouldn't that be fascinating?) While the language it generated needs refinement, the design process is iterative, and it takes time to devel…

> As I mention in the post -- creativity often involves remixing existing ideas This is carrying the weight of your core argument. It’s not wrong but it’s not completely correct either. Creativity involves remixing but is not all remixing. Is it? Not even all humans are at the same level in this. Number of attempts means nothing if you don’t add features that the LLM desperately needs to be grounded in the reality, o…

You're totally right -- random recombination isn't good enough. not trying to make that case at all.

Re: GPT-4 Designed a Programming Language

#194

Post by ummonk »

jmcgeeney wrote: post #72
marviel wrote: post #16

Earlier quoted context omitted.

Author here -- I think it is a stochastic parrot, don't get me wrong. But my argument is that humans are also , at some level, sufficiently advanced stochastic parrots. At least, as it pertains to many creative endeavors. You're always building on the back of something that comes before. We're all just remixing ideas we've heard before. I mean even this comment -- none of the words I'm saying are new, and many of the…

The difference between humans and sophisticated stochastic parrots is reason . The most common kinds of mistakes that chatGPT currently makes are when it says things that are not simply wrong, but don't make sense. Perhaps it will be possible to emulate reason with enough data, training, parameters, etc, but without some representation of the ability to understand what you don't know, what you know, and what follows…

I’m sure a stochastic parrot model could be trained to exhibit reasoning, but the issue is that there isn’t any automated loss function which can discern whether the output of a large language model exhibits reasoning or is illogical. When you train based on text similarity, it will have a hard time learning logic, especially given the amount of illogical writing that is out there.

Re: GPT-4 Designed a Programming Language

#195

Post by RHSman2 »

jmcgeeney wrote: post #72
marviel wrote: post #16

Earlier quoted context omitted.

Author here -- I think it is a stochastic parrot, don't get me wrong. But my argument is that humans are also , at some level, sufficiently advanced stochastic parrots. At least, as it pertains to many creative endeavors. You're always building on the back of something that comes before. We're all just remixing ideas we've heard before. I mean even this comment -- none of the words I'm saying are new, and many of the…

The difference between humans and sophisticated stochastic parrots is reason . The most common kinds of mistakes that chatGPT currently makes are when it says things that are not simply wrong, but don't make sense. Perhaps it will be possible to emulate reason with enough data, training, parameters, etc, but without some representation of the ability to understand what you don't know, what you know, and what follows…

And our reason is controlled by emotions, ego, intellect, etc, etc: our sentience.

Llm’s are the language model. That is it.

Now we have gone down this path to a very useful tool what’s next is connecting it to something that can understand context and memory.

It’s not so hard to imagine being connected to a knowledge graph of all the things and this evolving into a very capable AI.

It’s like Google v1 compared to Google now. Key words versus semantic seo

Re: GPT-4 Designed a Programming Language

#196

Post by dirkt »

marviel wrote: post #16
raincole wrote: post #15

Earlier quoted context omitted.

I'm not so sure. The first sample is: > Indentation-based scoping, similar to Python. Then... > class Person { To me, it's very clear it doesn't really understand what "indentation-based scoping" means. For a human programmer, using both intentation-based and bracket-based scoping is a very unusual design choice, and is begging for further explanation. It talked pages of abstraction, modularity, etc, but not this ? I…

Author here -- I think it is a stochastic parrot, don't get me wrong. But my argument is that humans are also , at some level, sufficiently advanced stochastic parrots. At least, as it pertains to many creative endeavors. You're always building on the back of something that comes before. We're all just remixing ideas we've heard before. I mean even this comment -- none of the words I'm saying are new, and many of the…

> But my argument is that humans are also, at some level, sufficiently advanced stochastic parrots.

But humans have a feedback loop called "consciousness" that sits above the stochastic parrot level, can reason about it, and can separate the wheat from the chaff.

AI still has to reach this level. ChatGPT cannot judge if its answers are right or wrong. It just claims things confidently, and as long as it is parroting correctly, it is right, and that's why humans get fooled into thinking that maybe they can trust it. (That's also why humans get fooled by human bullshitters who claim things confidently).

So if you don't use ChatGPT as what it is, a lookup-tool trained on the content of the internet, which can't even tell you where it got the information from, and the onus is on you to verify if the information is correct or not, and if instead try to use it as some kind of expert you can trust (which I have seen quite a few people do), then you are doing it wrong.

Re: GPT-4 Designed a Programming Language

#197

Post by vidarh »

satisfice wrote: post #12

GTP is interesting enough without people pretending that it is more interesting than it is. This "new programming language" doesn't look new at all. It looks like the same old thing.

That is true for most "new" human produced.programming languages too. The pool of truly novel programming languages is extremely shallow. Even the number of languages bringing anything new to the table is very limited.

So, it doesn't really tell us much (either direction)

Re: GPT-4 Designed a Programming Language

#198

Post by eitland »

geraneum wrote: post #185
cyclotron3k wrote: post #153

Earlier quoted context omitted.

It seems only yesterday that we were marvelling at the capabilities of ChatGPT - it's ability to parse the sum knowledge of humankind and synthesise not trivial responses to questions we posed. But look how far we've come since those heady and carefree days. We're already able to pour buckets of scorn on its capabilities, and brush them aside as if designing a language (albeit a derivative and uninspired one) is a tr…

> designing a language (albeit a derivative and uninspired one) is a trivial task that any human could achieve. It is, isn’t it? You just need to be able to read and write words and symbols that reassemble a programming language coherently and follow the pattern. This is what humans do after all; remixing. Anyone can do this.

Sorry if I am missing something here, but I think we all know well functioning, productive humans, maybe even in our field, who wouldn't have been able to create this language or a similarly well thought out one.

I know a competent man should be able to "change a diaper, plan an invasion, butcher a hog, conn a ship, design a building, write a sonnet, balance accounts, build a wall, set a bone, comfort the dying, take orders, give orders [...]" and what not and specialization is for insects, but even on the Mysterious Island not everyone is Cyrus Smith (Harding).

Re: GPT-4 Designed a Programming Language

#199

Post by RHSman2 »

raincole wrote: post #139
jmcgeeney wrote: post #72

Earlier quoted context omitted.

The difference between humans and sophisticated stochastic parrots is reason . The most common kinds of mistakes that chatGPT currently makes are when it says things that are not simply wrong, but don't make sense. Perhaps it will be possible to emulate reason with enough data, training, parameters, etc, but without some representation of the ability to understand what you don't know, what you know, and what follows…

It's totally possible that humans don't do reason. It's possible that the parrot in our brain makes the decision, and then the "frontend" of our mind makes fake reasons that sound logical enough. But it's just a possibility, and I don't find it's particularly convincing.

Fast thinking/slow thinking by Daniel Kannerman (and the Unlocking Project) is a book people need to read and understand. When we slow think, we work things out, when we fast think we are parrots.

Re: GPT-4 Designed a Programming Language

#200

Post by RHSman2 »

HervalFreire wrote: post #46
BoiledCabbage wrote: post #32

Earlier quoted context omitted.

> yeah, but colloquially when people start using the term "stochastic parrot" they're referring to something far stupider. From a Technical and pedantic standpoint it could be said ALL intelligence is isomorphic to a stochastic parrot I mean that's somewhat his point (if I understand him correctly). All intelligence could effectively be described as a "stochastic parrot" as a result, calling something a "stochastic p…

>I mean that's somewhat his point His point is humans and GPT are both stochastic parrots. I'm saying ALL intelligence even the one in an ant or a chess AI is a stochastic parrot. Thus it's pointless to use this term to compare intelligence. Therefore people must not actually be referring to the technical definition when they use the word "stochastic parrot." >If you replace "stochastic parrot" in most of those comme…

I’m dumber than you
Post reply on HN