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

Advent of Code 2023's new AI/LLM Policy

adventofcode.com

Post reply on HN
Print view View original

101–110 of 133 posts

Re: Advent of Code 2023's new AI/LLM Policy

#101

Post by withinboredom »

polygamous_bat wrote: post #92
uvesten wrote: post #70

Earlier quoted context omitted.

I’m sure you feel like you’re getting better by working with an AI, but make sure to test your skills without any AI help. The ”illusion of competence” effect can be really strong, and it sneaks up on you without you noticing it.

I am curious, why is this an illusion? I have experienced the same (or at least similar) feeling of getting better after getting my hands on a search engine like google. I never stopped using a search engine since then to check if I am suffering from this “illusion” you’re talking about. Should we?

I seriously suggest getting a book and typing out a listing totally from scratch. It's interesting to actually type out another person's style of solving a problem because not only is it alien feeling to "solve it that way", it's also interesting to physically solve it that way. I did this recently and was surprised to see myself solving the problem "that way" at work. It was much more elegant and more readable than what the AI was suggesting.

Re: Advent of Code 2023's new AI/LLM Policy

#102

Post by Jtsummers »

candiddevmike wrote: post #63
lsy wrote: post #22

Maybe I'm a dinosaur but I'm utterly mystified by folks who are interested in making the leaderboard or even solving AoC puzzles with AI assistance. To me it feels like going to a 5k charity run, taking a motorcycle to the finish line, and parading your gold medal around. Like, who are you impressing? And are you even proud of yourself? I understand the appeal of using the best and fastest means when there are real-w…

Why even have a leaderboard for this? At least make it anonymous.

It's optionally anonymous. People don't have to publicize their names on AoC. With Github (and I assume the other identity providers) you get an option of: anonymous #some number, your name (from Github), your username (from Github). IIRC, the anonymous option is the default.

Re: Advent of Code 2023's new AI/LLM Policy

#103

Post by manicennui »

postalrat wrote: post #4

"(If you want to use AI to help you solve puzzles, I can't really stop you, but I feel like it's harder to get better at programming if you ask an AI to do the programming for you.)" I'd say that whatever "better at programming" is quickly evolving. AI is a tool like high level languages, IDEs, autocomplete or all the different types of code analyzers. How is ignoring a powerful tool like AI going to get you better a…

At best CodeGPT helped semi-incompetent developers who relied on SO to do their jobs work a little faster. No one competent is in any danger.

Re: Advent of Code 2023's new AI/LLM Policy

#104

Post by tmtvl »

danjoredd wrote: post #86
postalrat wrote: post #4

"(If you want to use AI to help you solve puzzles, I can't really stop you, but I feel like it's harder to get better at programming if you ask an AI to do the programming for you.)" I'd say that whatever "better at programming" is quickly evolving. AI is a tool like high level languages, IDEs, autocomplete or all the different types of code analyzers. How is ignoring a powerful tool like AI going to get you better a…

For the same reason giving a 5 year old a calculator to "learn" addition doesn't teach them math. You still need to know why shit works in order to use it in a fully educated way. Otherwise you are just "putting magic words into the text editor" and your code will be held together with bailing wire and chewing gum. For day-to-day use, as long as you know what the code is doing when you run it, its fine. But to get to…

> For day-to-day use, as long as you know what the code is doing when you run it, its fine.

I think that'd exclude most Python, Ruby, Java, JS, Haskell,... developers. Heck, it'd even exclude a bunch of C developers who don't appreciate the fact they're not working on a PDP-11.

Re: Advent of Code 2023's new AI/LLM Policy

#106

Post by cyrialize »

I think this absolutely makes sense.

I'd use LLMs to help unblock me in the same way I use Google, since lately I've been finding it more difficult to find easy answers to "how do I do X with Y library" with Google. I've been finding the first page of Google showing SEO pages for programming questions rather than Stack Overflow or official documentation.

I wouldn't just copy-paste the problem into ChatGPT and then use prompts to solve it. I want to have fun solving the puzzle, rather than asking ChatGPT what the answer to the puzzle would be.

Re: Advent of Code 2023's new AI/LLM Policy

#107

Post by ebiester »

postalrat wrote: post #4

"(If you want to use AI to help you solve puzzles, I can't really stop you, but I feel like it's harder to get better at programming if you ask an AI to do the programming for you.)" I'd say that whatever "better at programming" is quickly evolving. AI is a tool like high level languages, IDEs, autocomplete or all the different types of code analyzers. How is ignoring a powerful tool like AI going to get you better a…

What if I'm looking to practice my ability to augment myself using AI?

(This isn't theoretical - I've done Advent of Code a few times, but I don't get to code too much these days. I am curious about its abilities and having a fun way to approach it might be a reason to do Advent of Code.)

That said, I'm not trying to push to the top of the leaderboard.

Re: Advent of Code 2023's new AI/LLM Policy

#108

Post by drdaeman »

danjoredd wrote: post #86
postalrat wrote: post #4

"(If you want to use AI to help you solve puzzles, I can't really stop you, but I feel like it's harder to get better at programming if you ask an AI to do the programming for you.)" I'd say that whatever "better at programming" is quickly evolving. AI is a tool like high level languages, IDEs, autocomplete or all the different types of code analyzers. How is ignoring a powerful tool like AI going to get you better a…

For the same reason giving a 5 year old a calculator to "learn" addition doesn't teach them math. You still need to know why shit works in order to use it in a fully educated way. Otherwise you are just "putting magic words into the text editor" and your code will be held together with bailing wire and chewing gum. For day-to-day use, as long as you know what the code is doing when you run it, its fine. But to get to…

> 5 year old a calculator to "learn" addition doesn't teach them math

Yes, using machines to give an answer, without providing any explanations of the process is not learning. One cannot generally give a young kid a calculator and expect them to learn how adder in the calculator's ALU works.

However, using machines to get an answer that you know how to get to is beneficial. No learning is involved in either process, and it saves time. So if you give a kid, who already knows well how to perform addition, understands the principles, and knows the properties, a calculator to quickly get through their homework, it merely saves their time. You know, just like most people don't exactly like to write boilerplate code that they can type in their sleep.

And using machines that can provide explanations how they got to the answer then reading it is learning. And learning by example could be powerful in certain situations - e.g. when one already knows some stuff, but needs some hints how to apply it to a different problem.

Surely, just asking the machine to solve a puzzle is unlikely to get one anywhere. Asking the machine to guide towards a solution might be very beneficial (if it manages to get things right, of course).

Re: Advent of Code 2023's new AI/LLM Policy

#109

Post by lgeorget »

HKH2 wrote: post #69
lgeorget wrote: post #48

Earlier quoted context omitted.

The incentives to cheat in a professional competition are more obvious since the money you earn is related to your performance. In the case of AoC, the only objective incentive I can think about is impressing a recruiter. Maybe it's enough if you're motivated enough.

Why do people cheat in video games?

Good point.

I play chess and some players end up thinking that cheating allows them to reach their real level and that it's just bad luck or conspiracy that prevent them to get to that level without resorting to cheating. Talk about cognitive dissonance.

Re: Advent of Code 2023's new AI/LLM Policy

#110

Post by rafaelmn »

danjoredd wrote: post #86
postalrat wrote: post #4

"(If you want to use AI to help you solve puzzles, I can't really stop you, but I feel like it's harder to get better at programming if you ask an AI to do the programming for you.)" I'd say that whatever "better at programming" is quickly evolving. AI is a tool like high level languages, IDEs, autocomplete or all the different types of code analyzers. How is ignoring a powerful tool like AI going to get you better a…

For the same reason giving a 5 year old a calculator to "learn" addition doesn't teach them math. You still need to know why shit works in order to use it in a fully educated way. Otherwise you are just "putting magic words into the text editor" and your code will be held together with bailing wire and chewing gum. For day-to-day use, as long as you know what the code is doing when you run it, its fine. But to get to…

> Otherwise you are just "putting magic words into the text editor" and your code will be held together with bailing wire and chewing gum.

That's just abstraction ? We're constantly dealing with legacy abstractions built 30-40+ years ago when we had fundamentally different constraints from today. Leaky abstractions are a fact of life and there's only so much you can reliably know about the stack.

My problem with learning with LLMs is how bad they are at the moment - people are betting big that they will eventually get better - but so far I'm only seeing scaling walls and negative cost/benefit footed by big tech $$$.

Post reply on HN