Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Two years give or take 6 months.


Give a group of "average human" two years, give or take 6 months, and they will also saturate the benchmark and probably some humans would beat the SOTA LLM/RLM.

People tend to do so all the time, with games for example.


Average humans cannot be copy-pasted.


Average companies also don't pay humans to complete a benchmark consisting of a fixed set of problems.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: