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

AI solves Advent of Code 2022

note89.github.io

Post reply on HN
Print view View original

61–70 of 82 posts

Re: AI solves Advent of Code 2022

#61

Post by californiadreem »

lgrapenthin wrote: post #23

This day I asked it not too fundamental questions about Clojure and it was able to provide impressive, accurate answers and provide correct code examples. However if you continue the dialogue and ask it to do more advanced stuff, it will just make up stuff out of thin air. For instance it will use functions that don't exist and claim that they can be imported from packages that don't exist or don't have them. Once yo…

Some men see things as they are and say why, I dream things that never were and say, why not?

Re: AI solves Advent of Code 2022

#62

Post by pedrosorio »

jcims wrote: post #59
pedrosorio wrote: post #53

Earlier quoted context omitted.

Isn't the expected output YES YES NO YES NO?

Yes according to the puzzle, but the operation as described isn’t clear (to me anyway) about which value should be used for the final assignment. It just says to use the value from the first element, but it’s unclear if it’s before or after that first element is replaced by the first operation.

I see, your description to GPT does not match the problem statement.

> It just says to use the value from the first element, but it’s unclear if it’s before or after that first element is replaced by the first operation.

Is the following python code unclear to you?

a = 0 b = 1 a, b = b, a

or alternatively:

a = [1,2,3,4,5] a[0:3] = a[1:3] + [a[0]]

There's nothing in the statement that indicates the assignments should be done one element at a time (if so, the order of the assignments would need to be specified). It's an atomic operation that circularly shifts the values in the array in the range l...r

Re: AI solves Advent of Code 2022

#63

Post by baandam »

tartoran wrote: post #46
Waterluvian wrote: post #12

Earlier quoted context omitted.

I’ve had this skepticism until I started asking the bot to do things like “create a limerick using some words that have never existed before and then explain the definition of those words.” I don’t believe the AI is generalized by any means. But I think it’s more than a Eliza-style parlour trick. It does really well with facts but misses subjectivity and nuance. Like I ask it to write stories for Seinfeld or Raymond…

Though it may look amazing it is not really thinking. It is simply capable of using a placeholder word. For HN’s sake AI does not understand anything, it’s just leveraging patterns, patterns that are sometimes complicated for us and that does make a great tool. But it’s just a tool for now.

AlphaZero and Stockfish are not really thinking either when it comes to chess.

I just don't understand how a thinking human can not see that this is basically irrelevant.

Re: AI solves Advent of Code 2022

#64

Post by swid »

jstanley wrote: post #29
monsieurbanana wrote: post #27

Earlier quoted context omitted.

I think it's pretty different from using high-level languages. I'm not interested in a competition that would be decided before even starting by who has the best AI program.

That's why it needs to be free software. I'm not interested in a competition that is decided by who has the best Python interpreter, but since we all have the same Python interpreter that isn't a problem.

Even if it is free, I have no interest in playing chess against a superhuman chess bot. You don’t even have to know how to play chess to use the moves the bots recommend and win against a grandmaster.

The line is blurry today, but we are moving into territory where humans will not be able to solve programming challenges that require under 200 lines of code faster than AI - we are slower to read and type. The AIs will likely get better at understanding the problems, requiring less help from humans and fewer attempts to find a solution.

At some point using a language model to compete in these kinds of programming contests will absolutely be like using a poker or chess bot to compete in those games.

Re: AI solves Advent of Code 2022

#65

Post by OctopusLupid »

swid wrote: post #60
pps wrote: post #48

Earlier quoted context omitted.

Does it have access to the web? For one of my questions it answered: "Unfortunately, I am unable to provide a detailed description of the education system in Poland and its changes over the last 30 years because I have limited access to information and cannot browse the internet." but I have no idea if it's not lying :)

Some posts yesterday showed that network is usually disabled, but with the right prompt, you can enable network and someone got it to like a Twitter post.

I think the “liking Twitter post” part was just a coincidental joke.

Re: AI solves Advent of Code 2022

#66

Post by motoxpro »

tartoran wrote: post #46
Waterluvian wrote: post #12

Earlier quoted context omitted.

I’ve had this skepticism until I started asking the bot to do things like “create a limerick using some words that have never existed before and then explain the definition of those words.” I don’t believe the AI is generalized by any means. But I think it’s more than a Eliza-style parlour trick. It does really well with facts but misses subjectivity and nuance. Like I ask it to write stories for Seinfeld or Raymond…

Though it may look amazing it is not really thinking. It is simply capable of using a placeholder word. For HN’s sake AI does not understand anything, it’s just leveraging patterns, patterns that are sometimes complicated for us and that does make a great tool. But it’s just a tool for now.

Take a look at the sibling. Maybe be less than understanding but it’s a lot more than a placeholder.

Re: AI solves Advent of Code 2022

#67

Post by baandam »

asim wrote: post #18

How long before software engineering roles are in decline because one engineer can leverage GPT to do the work of ten? It's truly a new innovation that requires relearning the toolset. Every generation seems to have some abstraction over the last. This feels like a new way to program.

I don't know how long but we are clearly hitting an exponential curve here as improvements build on improvements that build on improvements.

A deeper question is how long until hand written code has too many bugs that it is worthless compared to AI code?

There is also the problem that once AI code is that good, there is no point in all this abstraction and overhead from language features aimed at human programmers. An AI programming language can be much faster and closer to binary.

I just can't imagine not seeing in my lifetime some kind of prompt that I can make a clone of this website in 2 seconds along with a 1000 variations along with the site being as fast as possible.

Re: AI solves Advent of Code 2022

#68

Post by tasuki »

Waterluvian wrote: post #35
tasuki wrote: post #28

Earlier quoted context omitted.

> I’ve had this skepticism until I started asking the bot to do things like “create a limerick using some words that have never existed before and then explain the definition of those words.” Sounds interesting! Mind sharing the results?

I’m not saying they’re good. Just that they’re (mostly) following the rules and aren’t just thematically random. https://ibb.co/RpSxcV8 https://ibb.co/883GpHY

Perhaps they aren't good, but they aren't that bad either. Probably better than I'd manage...

Re: AI solves Advent of Code 2022

#69

Post by jcims »

pedrosorio wrote: post #62
jcims wrote: post #59

Earlier quoted context omitted.

Yes according to the puzzle, but the operation as described isn’t clear (to me anyway) about which value should be used for the final assignment. It just says to use the value from the first element, but it’s unclear if it’s before or after that first element is replaced by the first operation.

I see, your description to GPT does not match the problem statement. > It just says to use the value from the first element, but it’s unclear if it’s before or after that first element is replaced by the first operation. Is the following python code unclear to you? a = 0 b = 1 a, b = b, a or alternatively: a = [1,2,3,4,5] a[0:3] = a[1:3] + [a[0]] There's nothing in the statement that indicates the assignments should…

I didn’t spend any time at all on it, I was curious to see if the results would be improved by describing the algorithm in prose rather than mathematical notation.

Re: AI solves Advent of Code 2022

#70

Post by thethirdone »

klohto wrote: post #37

I'm trying to use it to generate Elixir code, and it's getting ~80% there. Compared to huge datasets of other languages, I'm still surprised by the quality of code it generates. While I did say 80%, the 20% is most crucial and without it, the code is useless. For example, it doesn't understand scope and assignment in Elixir. Getting it to write in more pure functional style is close to impossible (or I just haven't f…

> Even after I started to correct its mistakes, like "your Enum.reduce/3 return is not assigned anywhere", it couldn't get a solution and started reverting to previous answers.

This is the biggest problem I see for actually getting it to do anything. It can only go so far from its first attempt. No amount of nudging can get it to correctly solve some problems.

You probably just need to start a new thread with a better initial prompt which removes the benefit of the chat approach.

Post reply on HN