Ciro Santilli @cirosantilli 40

Hard input constraints:

inputs have two colors: green and black

Hard output constraints:

output has three colors: black, green and yellow
output has same size as input
green is copied from input to output
- output differs from input by making some black pixels yellow. Which pixels are becoming yellow?
  - output differs from input by making inner regions (non-diagonal) yellow with non-diagonal flood fill

 Read the full article

ARC-AGI-1 problem / 007bbfb 2025-12-13

 View more

arcprize.org/play?task=007bbfb7

Hard input constraints:

inputs are 3x3
inputs contain only 2 colors monocolored: black and another

Hard output constraints:

output is 3x input width and height. Suggests that the output is a 3x3 grid based on the input.
- stronger: if output is split as a 3x3 grid, then each 3x3 block is either black or a copy as input. Which is which?
  - stronger: each pixel of the input determines if block is black or copy (final solution)
output contains only two colors: black and another
- stronger: the same two colors as input

Input output comparison:

input appears pasted on output multiple times: suggests it is being copy pasted

Hard output constraints:

output is 3x input width and height: suggests that the output is a 3x3 grid based on the input
If that is the case, let's try to figure out what is placed on each output grid.
Notice: each grid element is either blank or the input.
OK so let's determine what in the input determines each output grid.
Because input in 3x3 maybe there's a direct mapping.

 Read the full article

arc-like 2025-12-13

 Read the full article

re-arc 2025-12-13

 View more

github.com/michaelhodel/re-arc

By the author of ARC-DSL.

README says:

This repository presents code to procedurally generate examples for the ARC training tasks. For each of the 400 tasks, an example generator is provided.

arxiv.org/html/2404.07353v1 says:

Each generator is a standalone Python function merely making use of the DSL and functions from the random module from the standard library. The median generator consists of 40 lines of code and uses 22 DSL primitive calls and 10 calls to the random module.

Cool!

Original:

Generated:

 Read the full article

ARC-AGI problem generator 2025-12-13

 Read the full article

Unofficial ARC-AGI problem set 2025-12-13

 View more

This section is about unofficial ARC-AGI-like problem sets.

These are interesting from both a:

practical point of view, as they provide more training data for potential solvers. If you believe that they are representative that is of course.
theoretical point of view, as they might help to highlight missing or excessive presumptions of the official datasets

github.com/neoneye/arc-dataset-collection contains a fantastic collection of such datasets, with visualization at: neoneye.github.io/arc/

 Read the full article

Project Euler problem 974 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=974

 Read the full article

Project Euler problem 973 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=973

 Read the full article

Project Euler problem 968 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=968

 Read the full article

Project Euler problem 963 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=963

 Read the full article

Project Euler problem 962 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=962

 Read the full article

Project Euler problem 960 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=960

 Read the full article

Project Euler problem 957 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=957

 Read the full article

Project Euler problem 956 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=956

 Read the full article

Project Euler problem 955 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=955

 Read the full article

Project Euler problem 954 Created 2025-12-13 Updated 2026-04-25

 View more

projecteuler.net/problem=954

 Read the full article

MathArena Apex 2025-12-13

 View more

matharena.ai/apex/

A subsets of problems that they curate from competitions.

 Read the full article

Elliot Glazer 2025-12-13

 View more

Creator of FrontierMath.

Socials:

x.com/ElliotGlazer

 Read the full article

Information theoretical musings inspired by ARC-AGI 2025-12-13

 View more

The extreme overfitting case of training is to have a map where each input leads to one output.

However it is cool that this overfit does not allow you to compute the final input for which there is no known output.

This therefore forces the creation of more general solution rules.

While in some cases solutions can work for any input, in many others they require specific assumptions about input, but the model could simply check that the assumptions apply to all inputs and use them for the final algorithm.

Bibliography:

lewish.io/posts/how-to-beat-arc-agi-2

 Read the full article

Official ARC-AGI problem set 2025-12-13

 Read the full article

 Unlisted articles are being shown, click here to show only listed articles.