Researchers Use AI To Discover Simplified Formula
A recent collaboration between OpenAI and amplitudes researchers used chain-of-thought reasoning models to discover a simpler mathematical formula for certain particle-collider amplitude calculations, which researchers then mathematically proved. The work follows similar AI-aided problem solving in mathematics, notably Erdös problem studies, and highlights that language-model reasoning can assist discovery while being constrained by lack of informal documented creative processes.
Key Points
- 1Applied reasoning models to discover and prove a simpler amplitudes formula.
- 2Demonstrates reasoning models can assist in nontrivial mathematical discovery beyond database searches.
- 3Implies creativity may be mechanizable but hindered by missing informal scientific problem-solving documentation.
Scoring Rationale
Relevant demonstration of reasoning-model utility in math/physics, limited by niche scope and shallow public explanation.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
