How to pass an AI coding benchmark: train on the questions
How to pass an AI coding benchmark: train on the questions
SWE-Bench Verified by OpenAI tests how well a model can solve real bugs in real Python code from GitHub. These bugs are all public information — so the AI models have almost certainly trained on th…
You're viewing a single thread.
I also likes to cheat on tests by studying every answer on the subject the test giver might put in the test??? We've got a computer than can study and pass tests, cmon. Where's the real story?
This isn't studying possible questions, this is memorizing the answer key to the test and being able to identify that the answer to question 5 is "17" but not being able to actually answer it when they change the numbers slightly.
LLMs are seven or eight bipartite graphs in a trench coat. Is your brain seven neurons thick, because that would explain a few things.
Hey mate what do you think learning is. Like genuinely, if you were to describe the process of learning a subject to me.
i have a potato that can study, send me your venmo if interested
it’s appropriate that you think your brain works like an LLM, because you regurgitated this shitty opinion from somewhere else without giving it any thought at all
Yeah I'm thinking that people who think their brains work like LLM may be somewhat correct. Still wrong in some ways as even their brains learn from several orders of magnitude less data than LLMs do, but close enough.