[quirino]

Small anecdote:

In the IEEEXTREME university programming competition there are ~10k participating teams.

Our university has a quite strong Competitive Programming program and the best teams usually rank in the top 100. Last year a team ranked 30 and it's wasn't even our strongest team (which didn't participate)

This year none of our teams was able to get in the top 1000. I would estimate close to 99% of the teams in the Top 1000 were using LLMs.

Last year they didn't seem to help much, but this year they rendered the competition pointless.

I've read blogs/seen videos of people who got in the AOC global leaderboard last year without using LLMs, but I think this year it wouldn't be possible at all.

[letmetweakit]

Man, those people using LLMs in competitive programming ... where's the fun in that? I don't get people for whom it's just about winning, I wish everyone would just have some basic form of dignity and respect.

[Aurornis]

I’m a very casual gamer but even I run into obvious cheaters in any popular online game all the time.

Cheating is rampant anywhere there’s an online competition. The cheaters don’t care about respecting others, they get a thrill out of getting a lot of points against other people who are trying to compete.

Even in the real world, my runner friends always have stories about people getting caught cutting trails and all of the lengths their running organizations have to go through now to catch cheaters because it’s so common.

The thing about cheaters in a large competition is that it doesn’t take many to crowd out the leaderboard, because the leaderboard is where they get selected out. If there are 1000 teams competing and only 1% cheat, that 1% could still fill the top 10.

[hoherd]

Yeah. I was happy to see this called out in their /about

> Should I use AI to solve Advent of Code puzzles? No. If you send a friend to the gym on your behalf, would you expect to get stronger? Advent of Code puzzles are designed to be interesting for humans to solve - no consideration is made for whether AI can or cannot solve a puzzle. If you want practice prompting an AI, there are almost certainly better exercises elsewhere designed with that in mind.

[evil-olive]

> I don't get people for whom it's just about winning, I wish everyone would just have some basic form of dignity and respect.

reminds me of something I read in "I’m a high schooler. AI is demolishing my education." [0,1] emphasis added:

> During my sophomore year, I participated in my school’s debate team. I was excited to have a space outside the classroom where creativity, critical thinking, and intellectual rigor were valued and sharpened. I love the rush of building arguments from scratch. ChatGPT was released back in 2022, when I was a freshman, but the debate team weathered that first year without being overly influenced by the technology—at least as far as I could tell. But soon, AI took hold there as well. Many students avoided the technology and still stand against it, but it was impossible to ignore what we saw at competitions: chatbots being used for research and to construct arguments between rounds.

high school debate used to be an extracurricular thing students could do for fun. now they're using chatbots in order to generate arguments that the students can just regurgitate.

the end state of this seems like a variation on Dead Internet Theory - Team A is arguing the "pro" side of some issue, Team B is arguing the "con" side, but it's just an LLM generating talking points for both sides and the humans acting as mouthpieces. it still looks like a "debate" to an outside observer, but all the critical thinking has been stripped away.

0: https://www.theatlantic.com/technology/archive/2025/09/high-...

1: https://archive.is/Lda1x

[Aurornis]

> high school debate used to be an extracurricular thing students could do for fun.

High school debate has been ruthless for a long time, even before AI. There has been a rise in the use of techniques designed to abuse the rules and derail arguments for several years. In some regions, debates have become more about teams leveraging the rules and technicalities against their opponents than organically trying to debate a subject.

[DangitBobby]

It sucks that the fun is being sucked out of debate, but I guess a silver lining is that the abuse of these tactics helps everyone understand that winning debates isn't about being correct, it's about being a good debater. And a similar principle can be applied to the application of law and public policy as well.

[jvanderbot]

Yeah, it's like bringing a ~bike~ motorcycle to your marathon. But if you can get away with it, there will always be people doing it.

Imagine the shitshow that gaming would be without any kind of anti-cheat measures, and that's the state of competitive programming.

[integralid]

Why is that strange? Competitive programming, as the name suggests, is about competing. If the rules allow that, not using LLM is actually more like running tour de France.

If the rules don't allow that and yet people do then well, you need online qualifiers and then onsite finals to pick the real winners. Which was already necessary, because there are many other ways to cheat (like having more people than allowed in the team).

[jvanderbot]

I'm a bit surprised you can honestly believe that a competition of humans isn't somehow different if allowed to use solution-generators. Like using a calculator in an arithmetic competition. Really?

It's not much different than outlawing performance enhancing drugs. Or aimbots in competitive gaming. The point is to see what the limits of human performance are.

If an alien race came along and said "you will all die unless you beat us in the IEEE programming competition", I would be all for LLM use. Like if they challenged us to Go, I think we'd probably / certainly use AI. Or chess - yeah, we'd be dumb to not use game solvers for this.

But that's not in the spirit of the competition if it's University of Michigan's use of Claude vs MIT's use of Claude vs ....

Imagine if the word "competition" meant "anything goes" automatically.

[zulban]

It's a different kind of fun. Just like doing math problems on paper can be fun, or writing code to do the math can be fun, or getting AI to write the code to do the math can be fun.

They're just different types of fun. The problem is if one type of fun is ruined by another.

[Isamu]

It can be a matter of values from your upbringing or immediate environment. There are plenty of places where they value the results, not the journey, and they think that people who avoid cheating are chumps. Think about that: you are in a situation where you just want to do things for fun but everyone around you will disrespect you for not taking the easy way out.

[zerr]

I believe the reason is that many still use CP for hiring, so people go into leetcode (or AdventOfCode) grind, sadly.

[Ekaros]

Weirdly I feel lot more accepting of LLMs in this type of environment than in making actual products. Point is doing things fast and correct enough. So in someways LLM is just one more tool.

With products I want actual correctness. And not something thrown away.

[jama211]

We’re starting to get to a point where the ai can generate better code than your average developer, though. Maybe not a great developer yet, but a lot of products are written by average developers.

[throwaway0123_5]

Given what I understand about the nature of competitive programming competitions, using an LLM seems kind of like using a calculator in an arithmetic competition (if such a thing existed) or a dictionary in a spelling bee.

[jama211]

I feel like it’s more like using an electronic dictionary in a spelling bee that already allowed you to use a paper dictionary. All it really does is demonstrate that the format isn’t suited to be a competition in the first place.

Which is why I think it’s great they dropped the competitive part and have just made it an advent calendar. Much better that way.

[loeg]

These contests are about memorizing common patterns and banging out code quickly. Outsourcing that to an LLM defeats the point. You can say it's a stupid contest format, and that's fine.

(I did a couple of these in college, though we didn't practice outside of competition so we weren't especially good at it.)

[mbb70]

The goal of "actual projects" is also fast and correct enough though

[matsemann]

When I did competitions like these at uni (~10-15 years ago), we all used some thin-clients in the computer lab where the only webpages one could access were those allowed by the competition (mainly the submission portal). And then some admin/organizers would feed us and make sure people didn't cheat. Maybe we need to get back to that setup, heh.

[quirino]

Serious in-person competitions like ICPC are still effective against cheating. The first phase happens in a limited number of venues and the computers run a custom OS without internet access. There are many people watching so competitors don't user their phones, etc.

The Regional Finals and World Finals are in a single venue with a very controlled environment. Just like the IOI and other major competitions.

National High School Olympiads have been dealing with bigger issues because there are too many participants in the first few phases, and usually the schools themselves host the exams. There has been rampant cheating. In my country I believe the organization has resorted to manually reviewing all submissions, but I can only see this getting increasingly less effective.

This year the Canadian Computing Competition didn't officially release the final results, which for me is the best solution:

> Normally, official results from the CCC would be released shortly after the contest. For this year’s contest, however, we will not be releasing official results. The reason for this is the significant number of students who violated the CCC Rules. In particular, it is clear that many students submitted code that they did not write themselves, relying instead on forbidden external help. As such, the reliability of “ranking” students would neither be equitable, fair, or accurate.

Available here: [PDF] https://cemc.uwaterloo.ca/sites/default/files/documents/2025...

Online competitions are just hopeless. AtCoder and Codeforces have rules against AI but no way to enforce them. A minimally competent cheater is impossible to detect. Meta Hacker Cup has a long history and is backed by a large company, but had its leaderboard crowded by cheaters this year.

[armchairhacker]

In 1997, Deep Blue beat Gary Kasparov, the world chess champion. Today, chess grandmasters stand no chance against Stockfish, a chess engine that can run on a cheap phone. Yet chess remains super popular and competitive today, and while there are occasional scandals, cheating seems to be mostly prevented.

I don’t see why competitive debate or programming would be different. (But I understand why a fair global leaderboard for AOC is no longer feasible).

[ewidar]

Online chess competitions actually spend quite a lot on preventing cheating, and even then it's a common talking point.

[gregdeon]

Oof. I had a great time cracking the top 100 of Advent of Code back in 2020. Bittersweet to know that I got in while it was still a fun challenge for humans.