AI agents spend 4 weeks and $3k in GPUs to produce a new math result

giannis_daras · x · 2026-09-15

Dimitris Papail previewed a research result produced by a 4+ week collaboration among AI agents (Astra, Sol & Fable), where his only role was asking questions and paying $3k in GPU costs. A draft plus 100GB of verification certificates will be shared.

Key details from the thread: the GPU budget went to parallelizing lower/upper bound computations, with agents exploring many strategies—different input sources, bounding approaches, and deeper complexity relaxations. The setup used vanilla Codex and Claude Code with no harness optimization, just models talking to each other with handoffs; the process was messy and hard to replicate, though the result itself is reproducible.

Related event: AI Agents Collaborate for Four Weeks to Produce New Math Results for $3,000 in GPU Costs(10 posts)→

Original post →

More from coding & agent

coding & agent channel →