← @bgSponge

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).

  1. 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.

  2. 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.

  3. 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.

  4. 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

  5. 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.

More from @bg

All readings →