# Barriers to Complexity-Theoretic Proofs that "AGI" Using Machine Learning is Impossible

arXiv: https://arxiv.org/abs/2411.06498 · HTML: https://mlsanity.com/paper/2411.06498/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 12 references that are in the map.
- First posted on arXiv 10 Nov 2024.

## Builds on (most cited first, 2 of 2)

- [Theoretical Analysis of Inductive Biases in Deep Convolutional Networks](https://mlsanity.com/paper/2305.08404/) (2023)
- [Occam's Razor and Bender and Koller's Octopus](https://mlsanity.com/paper/2407.21070/) (2024)

## Abstract (arXiv)

A recent paper (van Rooij et al. 2024) claims to have proved that achieving human-like intelligence using learning from data is intractable in a complexity-theoretic sense. We point out that the proof relies on an unjustified assumption about the distribution of (input, output) tuples in the data. We briefly discuss that assumption in the context of two fundamental barriers to repairing the proof: the need to precisely define ``human-like," and the need to account for the fact that a particular machine learning system will have particular inductive biases that are key to the analysis. Another attempt to repair the proof, by focusing on subsets of the data, faces barriers in terms of defining the subsets.