“best where the actual logic isn’t very hard”?
yeah, well it’s also one of the top scorers on the Math olympiads
yeah, well it’s also one of the top scorers on the Math olympiads
My current project is nothing too bizarre, it's a 3D renderer. Well-trodden ground. But my project breaks a lot of core assumptions and common conventions, and so any LLM I try to introduce—Gemini 2.5 Pro, Claude 3.7 Thinking, o3—they all tangle themselves up between what's actually in the codebase and the strong pull of what's in the training data.
I tried layering on reminders and guidance in the prompting, but ultimately I just end up narrowing its view, limiting its insight, and removing even the context that this is a 3D renderer and not just pure geometry.
And so will almost all humans. It's weird how people refuse to ascribe any human-level intelligence to it until it starts to compete with the world top elite.
LLMs apologize and then proudly present the exact same output as before, repeatedly, forever spinning their wheels at the first major obstacle to their reasoning.
So basically like a human, at least up to young adult years in teaching context[0], where the student is subject to authority of the teacher (parent, tutor, schoolteacher) and can't easily weasel out of the entire exercise. Yes, even young adults will get stuck in a loop, presenting "the exact same output as before, repeatedly, forever spinning their wheels at the first major obstacle to their reasoning", or at least until something clicks, or they give up in shame (or the teacher does).
--
[0] - Which is where I saw this first-hand.
Reminding LLMs of the constraints they're bumping into doesn't help. They haven't forgotten, after all. The best performance I got out of the LLMs in my project I mentioned upthread was a loop of trying out different functions, pausing, re-evaluating, realizing in its chain of thought that it didn't fit the constraints, and trying out a slightly different way of phrasing the exact same approach. Humans will stop slamming their head into a wall eventually. I sat there watching Gemini 2.5 Pro internally spew out maybe 10 variations of the same function before I pulled the tokens it was chewing on out of its mouth.
Yes, sometimes students get frustrated and bail, but they have the capacity to learn and try something new. If you fall into an area that's adjacent to but decidedly not in their training data, the LLMs will feel that pull from the training data too strongly and fall right into that rut, forgetting where they're at.
Yeah, I tried playing tictactoe with chatGPT and it did not do well.
Humans neural networks are constantly being retrained, so their effective context window is huge. The LLM may be better at a complex, well specified 200 line python program, but the human brain is better at the 1M line real-world application. It takes some study though.