jerpint
Born on January 25, 2022•1213 Karma
[0] https://www.jerpint.io/blog/2024-12-30-advent-of-code-llms/
The difference when working on larger tasks that require reasoning is night and day.
In theory it would be very interesting to go back and retry the 2024 tasks, but those will likely have ended up in the training data by now...
I see people assert this all over the place, but personally I have decreased my usage of LLMs in the last year. During this change I’ve also increasingly developed the reputation of “the guy who can get things shipped” in my company.
I still use LLMs, and likely always will, but I no longer let them do the bulk of the work and have benefited from it.
It's true this was 4 months after AoC 2024 was out, so it may have been trained on the answer, but I think that's way too soon.
Day 3 in 2024 isn't a Math Olympiad tier problem or anything but it seems novel enough, and my prior experience with LLMs were that they were absolutely atrocious at assembler.
But as others have said, it’s a night and day difference now, particularly with code execution.
From watching them work, they read the spec, write the code, run it on the examples, refine the code until it passes, and so on.
But we can’t tell whether the puzzle solutions are in the training data.
I’m looking forward to seeing how well current agents perform on 2025’s puzzles.
Thank you for any response!
https://github.com/jerpint/context-llemur
Major difference is a conversation doesn’t get stored, the LLM (or you) can use the MCP/CLI to update with the relevant context updates
https://github.com/jerpint/context-llemur
Though instead of being a single file, you and LLMs cater your context to be easily searchable (folders and files). It’s all version controlled too so you can easily update context as projects evolves.
I made a video showing how easy it is to pull in context to whatever IDE/desktop app/CLI tool you use https://m.youtube.com/watch?v=DgqlUpnC3uw