I was curious if LLMs are good for this problem. ChatGPT-5.1-Thinking one-shotted a correct Python script without any library use (https://pastecode.io/s/jg6ggxpm).

Claude Opus failed to solve after trying for a while.

▲

whimsicalism 8 hours ago | parent | next [-]

project euler problems are likely in the RL corpora

▲

mvdtnz 7 hours ago | parent | prev [-]

First of all, don't do this. No one cares. Secondly obviously every Euler solution is going to appear in the training data many times over. It's no surprise at all that an LLM can regurgitate data that was given to it.

▲

kragen 7 hours ago | parent [-]

I thought it was interesting, and I wouldn't be surprised if Euler solutions weren't in the training data, especially for the later problems like this one.

▲

kami23 3 hours ago | parent [-]

I appreciate you trying it! So at least I care.

I used to do these in college to procrastinate my homework. I always had the most difficulty with the problems that required data structures I wasn't exposed to previously and ended up making really complicated solutions that were inefficient as hell, but fun nonetheless.

I might give them a try with golang now that it's my preferred language. I used to do them in python as that was our intro language.

	▲	kragen 3 hours ago \| parent [-]
		Perhaps you meant to reply to webo? I'm not sure what you think I might have been trying.