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

261–270 of 338 posts

Re: GPT-4 Designed a Programming Language

#261

Post by fho »

UncleEntity wrote: post #234
amoss wrote: post #225

Earlier quoted context omitted.

The interesting part of the exchange is the contrast between the surface level syntax of the exchange and the semantics below. It reminds me of teaching in a lot of ways. The level of polish on the immediately apparent surface level of the conversation is very high: reasonable tenents, good justification and ability to explain them. But then applying them directly into an example falls down a bit. The language is a b…

> I like the use of the arrows in the function definitions though :) I've seen that somewhere before… Python type hints probably. I (ab)used them for good effect when I was fiddling around with the spark earley parser that used to be part of the python build system.

It actually comes from math notation and was used in ML-type languages long before python.

Re: GPT-4 Designed a Programming Language

#262

Post by fho »

Jensson wrote: post #191
RHSman2 wrote: post #186

Earlier quoted context omitted.

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 mos…

It's been a while, but wasn't it two AlphaGo versions? One that was trained on existing games and "trained" with existing engines. One that was retrained from scratch without any external input? I might be wrong.

Re: GPT-4 Designed a Programming Language

#263

Post by Jensson »

fho wrote: post #262
Jensson wrote: post #191

Earlier quoted context omitted.

> 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 mos…

It's been a while, but wasn't it two AlphaGo versions? One that was trained on existing games and "trained" with existing engines. One that was retrained from scratch without any external input? I might be wrong.

Both had a program running it with real Go rules. We don't have a program that can run with the real rules for logic and text to train a language model from scratch.

Re: GPT-4 Designed a Programming Language

#266

Post by vidarh »

midoridensha wrote: post #253
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…

>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. So, like the average voter?

You're being a bit glib, but I tend to agree that a lot of people seriously overestimate the reasoning done by the average human.

I think GPT is on the other hand both over- and underestimated because it speaks well but often makes reasoning mistakes we only expect of someone less eloquent, and it throws us.

If it had come across as an inquisitive child, we'd have been a lot more overbearing of it's "hallucinations" for example, because kids do variations over that all the time.

At the same time, it can do some things most children would have no hope of.

It's a category of "intelligence" we're unfamiliar with, additionally hobbled with no dynamic long term memory.

Re: GPT-4 Designed a Programming Language

#267

Post by amoss »

dunefox wrote: post #250
UncleEntity wrote: post #234

Earlier quoted context omitted.

> I like the use of the arrows in the function definitions though :) I've seen that somewhere before… Python type hints probably. I (ab)used them for good effect when I was fiddling around with the spark earley parser that used to be part of the python build system.

Also haskell signatures, for example.

lol, of course. I hadn't realised it is so long since I wrote any Haskell...

Re: GPT-4 Designed a Programming Language

#268

Post by redbar0n »

It's funny that everyone replies with "That language exists already.", and then proclaim it to be either: TypeScript, Python, Swift, Scala or F# etc.

Why is it funny? Because GPT-4 was probably trained on examples from all of those languages, and has produced an averaged mashup of languages: so everyone can find something which is similar in it, and then pattern-match it to a (rather mainstream) language that they use!

Re: GPT-4 Designed a Programming Language

#269

Post by zamnos »

dx034 wrote: post #129
cryptozeus wrote: post #113

"But let’s talk about today’s “frontier” of jobs that haven’t been “automated away”. There’s one category that in many ways seems surprising to still be “with us”: jobs that involve lots of mechanical manipulation, like construction, fulfillment, food preparation, etc. But there’s a missing piece of technology here: there isn’t yet good general-purpose robotics (as there is general-purpose computing), and we humans s…

Absolutely. We've been great at building AI in software, but hardware is still absolutely lacking. Robots are nowhere near usable for even simple tasks, at least if they don't follow the same pattern each time. Just look at households, there's still no robot that can empty a dishwasher reliably (unless maybe you build a specialized one for just that task), while it's a task much simpler than what GPT-4 can perform on…

I wouldn't hold your breath either, Google shut down their attempt.

https://www.theverge.com/2023/2/24/23613214/everyday-robots-...

Re: GPT-4 Designed a Programming Language

#270

Post by chimprich »

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…

> We're all just remixing ideas we've heard before.

We're largely remixing ideas we've heard before, but not just I think. If you're just remixing ideas that came before... where did those ideas come from?

I think you can get quite far remixing ideas but for more novel concepts to emerge you have to actually create new stuff.

In biology it seems that evolution has found it worthwhile not to minimise mutations too much. In genetic programming you need both mutation and crossover for evolution.

I don't think LLMs really have that mutation of ideas (at the moment!), and I suspect humans create genuinely new concepts in a much more sophisticated way than mere random mutation.

Post reply on HN