Will anyone post an interesting math/algorithms koan/problem/exercise in the comments of this that I'll spend 30+min on?
6
closes Oct 3
59%
chance

round four!

Unfinished questions from before and recursively before still count

Get Ṁ500 play money

Related questions

Will DALLE3 be consistently able to generate hands with 4 fingers and no thumb?
firstuserhere avatarfirstuserhere
46% chance
Will anyone post a solution to the cipher in the description?
IsaacKing avatarIsaac
42% chance
Will anyone post an interesting math/algorithms koan/problem/exercise in the comments of this that I'll spend 1h+on?
jacksonpolack avatarjackson polack
70% chance
What will be the first year that an AI gets gold on an International Mathematical Olympiad?
Will anyone post an interesting math/algorithms koan/problem/exercise in the comments of this that I'll spend 8h+ on?
jacksonpolack avatarjackson polack
21% chance
Will the #1 system on the November 2023 Top 500 supercomputers list exceed 1.5 exaflop/s?
AaronLehmann avatarAaron Lehmann
45% chance
Which of Landau's Problems will be solved next?
Will a blank-slate AI prove the infinitude of primes by 2025-11-03?
BoltonBailey avatarBolton Bailey
50% chance
Will @Mira solve the 2023 Sudoku challenge?
Mira avatarMira
36% chance
Are any Millennium Prize problems undecidable/unprovable/unsolvable?
NcyRocks avatarN.C. Young
50% chance
Will it be possible to get a correct solution for the quadratic equation from the text-to-image model this year?
In 2025, will I teach people that Projective Geometric Algebra (PGA)'s "dual" is similar to the Fourier transform?
HamishTodd avatarHamish Todd
58% chance
Will *any* remaining Millenium Prize problem be solved entirely or mostly by humans?
vluzko avatarVincent Luczkow
71% chance
Can most humans solve easy Sudoku puzzles? (Resolves to PROB)
Primer avatarPrimer
64% chance
Will Ray Kurzweil win his 2029 Turing Test bet with Mitchell Kapor?
MatthewBarnett avatarMatthew Barnett
53% chance
Will someone beat the 3x3x3 Rubiks Cube world record by the end of 2024?
Dennisb00b avatarDennis
27% chance
Will there be a statistical test for catching superposition? (2023)
firstuserhere avatarfirstuserhere
39% chance
Will we have a formalized proof of Fermat's last theorem by 2029-05-01?
BoltonBailey avatarBolton Bailey
41% chance
Will a matmul algorithm better than O(n^{2.371552}) [Willians et al. 2023] be published before the end of 2025?
Widden avatarWidden
66% chance
Will Lean have proved the most theorems on Freek's list by beginning of 2024?
BoltonBailey avatarBolton Bailey
37% chance
Sort by:
mariopasquato avatar
mario pasquato

More like an open question. Can we optimize digits? Clearly if you look at an expression like 2+3=5 there is no hint in the shape of 2 and 3 as digits that lets you predict the shape of the digit 5. Looking at 4 there is no evidence that it is twice 2 You can't even tell, visually, odd from even.. Digits are essentially just arbitrary squiggles. Can we do better? Given a set of constraints encoded as a loss function and a representation of digits as say 20x20 black and white images can we use a machine learning algorithm to come up with squiggles which respect the constraints? The constraints are the key. For instance you could ask that the digit for k+h looks similar to a combination of the digits for k and for h. Dumb constraints will get you dumb digits, cool constraints maybe will produce cool digits.