News for hackers. Stuff that matters.

A comment on Undergraduate Upends a 40-Year-Old Data Science Conjecture. Parent comment

Re:Undergraduate Upends a 40-Year-Old Data Science Conjecture by blablablerg on Tuesday February 11, 2025 @05:34AM (#43011202)
It is, because you are wasting time reinventing the wheel. Also if something is already well researched, you might miss intricacies, traps, optimizations etc. previous researchers have stumbled upon.
[ Parent | on HN ]
Re:Undergraduate Upends a 40-Year-Old Data Science Conjecture by dwaltrip on Tuesday February 11, 2025 @11:48AM (#43015004)
It isn’t necessarily “wasted” time. There are more ways to look at it, as well as 2nd order and 3rd order effects (and so on).

It’s a powerful skill to be able to try to solve things from first principles. And it’s a muscle you can strengthen.

It would be a bit silly to never look anything up, but it isn’t so black and white.

[ Parent | on HN ]
Re:Undergraduate Upends a 40-Year-Old Data Science Conjecture by Brian_K_White on Tuesday February 11, 2025 @12:46PM (#43015736)
This is a good example of how the most obvious intuition can be wrong, or at best incomplete.
[ Parent | on HN ]
Re:Undergraduate Upends a 40-Year-Old Data Science Conjecture by Shorel on Tuesday February 11, 2025 @05:00PM (#43018901)
You need to be able to do both.

Only reading the existing literature is not good enough.

The capacity to create ideas is also something that needs to be practiced.

[ Parent | on HN ]