Factoring RSA-260
Summary
Cognition researcher Eric Lu drove a Devin swarm to factor RSA-260 for about $400k (~4,900 GPU-days), setting a new public RSA Factoring Challenge record after RSA-250 (2020).
Agents closed a public factoring record via performance engineering.
A Devin swarm modified CADO-NFS into a GPU GNFS stack and factored RSA-260 without claiming new algorithms.
I report essentially no algorithmic advancements
About three weeks elapsed from first prompt to RSA-260 factors found.
Cost drops change who can try, not RSA-2048.
GPU sieving ~10× cheaper than prior public SOTA; RSA-1024 ~$30M at market GPU prices; RSA-2048 remains ~billion× harder than RSA-1024.
Spare cluster shards are a real research substrate.
Lattice sieving fits preemptible single-node scraps from NVL72 packing inefficiencies, so the run used spare/disaggregated compute at negligible marginal cost.
Humans still supply executive function.
Priority-setting, benchmarks, redirection, and a unified measurement framework kept parallel Devins productive over ~3 weeks of concurrent sessions.
My role was primarily to set priorities, establish benchmarks, and recognize when work was going off-track.
Devin needed me for executive function, talking through and sanity-checking what it was doing
Human-engineered decompositions still unlock agents.
CADO-NFS’s staged interfaces let the swarm optimize pieces independently; agents grew more confused farther from upstream.
Read the original ↗Save to your Sponge
Summarized with Sponge. Quotes are the author’s own words.