Skip to content

Educational Implementation · Jupyter Notebook

simon-arc-lab-legacy

Predecessor to simon-arc-lab

What it is

This repository contains code and experiments for attempting to solve the ARC Prize 2024 using large language models with RLE-based input compression. It includes data generation, model wrapping, inference scripts, and various proof-of-concept implementations, though the main training notebooks have not been executed.

Scored at63b90c914 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
Machine Learning: 24.3%NLP & LLMs: 24.3%Computer Vision: 21.6%Data Science: 18.9%MLOps: 8.1%AI Agents: 2.7%
  • Machine Learning24%
  • NLP & LLMs24%
  • Computer Vision22%
  • Data Science19%
  • MLOps8%
  • AI Agents3%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

  • Clear explanation of RLE compression approach for ARC puzzles in the README.
  • Implementation of auxiliary algorithms (cellular automaton, connected components) from scratch.
  • Variety of experiments with different models and encoding schemes in the legacy code.

Limitations

The owner keeps this project's limitations private.

Around it on the Machine Learning board

Whole board
  1. 114Exploring-AutoEncodersTraining Experiment · Jupyter Notebook47.8/100ImplementationMohamed Khayat
  2. 115, shared rankSafe-HomeML Application · HTML47.5/100ImplementationIrine Milton
  3. 115, shared ranksimon-arc-lab-legacyEducational Implementation · Jupyter Notebook47.5/100ImplementationSimon Strandgaard
  4. 117, shared rankarc-vitTraining Experiment · Jupyter Notebook47.3/100ImplementationSimon Strandgaard
  5. 117, shared rankLSIS-ISLML Application · Jupyter Notebook47.3/100ImplementationKashish gupta

More from Simon Strandgaard