ChatGPT Pro Improves Capacity Bounds for Binary Deletion Channel by 4%
DimitrisPapail · x · 2026-08-02
A researcher tested ChatGPT Pro on a classic open problem in information theory: the capacity bounds of the binary deletion channel. At a 50% deletion probability, the model successfully derived a new result, improving the best current lower bound by about 4%. This demonstrates the potential of LLMs in assisting advanced pure mathematics research.
Related event: ChatGPT Solves 15-Year Information Theory Puzzle(2 posts)→
More from Research
- It's not gradient descent: burny_tech corrects the diagnosis to RLHF mode collapse — burny_tech · 2026-10-16
- A beginner-friendly introduction to causal inference kicks off, Part 1 — Nasereliver · 2026-10-16
- FBI method trains for Pass@K with one sample per update at 12.3% of the cost — EmtiyazKhan · 2026-10-16
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16