News for hackers. Stuff that matters.
Re:Recent AI model progress feels mostly like bullshit by TrackerFF on Monday April 07, 2025 @04:11AM (#43609068)
What would the average human score be?

I.e. if you randomly sampled N humans to take those tests.

Re:Recent AI model progress feels mostly like bullshit by sanxiyn on Monday April 07, 2025 @04:17AM (#43609102)
The average human score on USAMO (let alone IMO) is zero, of course. Source: I won medals at Korean Mathematical Olympiad.
Re:Recent AI model progress feels mostly like bullshit by vintermann on Monday April 07, 2025 @04:33AM (#43609193)
Average, hmmm?
Re:Recent AI model progress feels mostly like bullshit by lordgrenville on Monday April 07, 2025 @09:10AM (#43610920)
I am hesitant to correct a math Olympian, but don't you mean the median?
Re:Recent AI model progress feels mostly like bullshit by nhinck3 on Tuesday April 08, 2025 @09:44AM (#43621718)
Average is fine.
Re:Recent AI model progress feels mostly like bullshit by hyperbovine on Monday April 07, 2025 @11:04AM (#43612359)
This is a disappointing answer from an MO alum. Pick a quantile, any quantile...