Comment by Davidzheng
16 days ago
"If much of your research paper can be written by AI, I call into question whether or not it represents actual research" And what happens to this statement if next year or later this year the papers that can be autonomously written passes median human paper mark?
What does it mean to cross the median human paper mark? How os that measured?
It seems to me like most of the LLM benchmarks wind up being gamed. So, even if there were a good benchmark there, which I do not believe there is, the validity of the benchmark would likely diminish pretty quickly.