Agent Helps Advance Math Conjecture
jasondeanlee · x · 2026-07-16
The author provided an update on their progress with the gradient flow conjecture, which has now advanced to 2.25380.
They mentioned being stuck on the problem with their agents (codex, chatgpt) for 3 to 5 days and exhausting their usage limits, so they are returning to "real work."
The core takeaway isn't the tool itself, but a demonstration of how AI agents are actively participating in the research process. The author also noted that so far, only sol 5.6 max/ultra and chatgpt have looked at this problem, and they welcome others to attempt it.
Related event: Researcher Advances Math Conjecture with AI Agents(2 posts)→
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11