Another followup to the big "AlphaEvolve improves math conjectures" paper: https://arxiv.org/abs/2506.16750
100x improvement on one of the conjectures. "Our function was found using simulated annealing and gradient based methods rather than using large language models."
IIUC, the AlphaEvolve examples ran for _weeks_ to find a new solution.
Apparently it seems most of these conjectures had not been seriously attacked by computational methods before the AlphaEvolve paper.
Jeremy Kun
npub1pe…4h36q
2025-11-17 17:05:22 UTC
Author Public Key
npub1pe67uceztjyefem3xmphw05e65200df0hrrv60464v6w8xjtgvgqp4h36qSeen on
wss://relay.ditto.pubPublished at
2025-11-17 17:05:22 UTCEvent JSON
{
"id": "f966fe970561103579826230492e627a7c4fdb78dc8b85fc4494c381c6b2b222",
"pubkey": "0e75ee63225c8994e77136c3773e99d514f7b52fb8c6cd3ebaab34e39a4b4310",
"created_at": 1763399122,
"kind": 1,
"tags": [
[
"proxy",
"https://mathstodon.xyz/users/j2kun/statuses/115566124880267249",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub/"
]
],
"content": "Another followup to the big \"AlphaEvolve improves math conjectures\" paper: https://arxiv.org/abs/2506.16750\n\n100x improvement on one of the conjectures. \"Our function was found using simulated annealing and gradient based methods rather than using large language models.\"\n\nIIUC, the AlphaEvolve examples ran for _weeks_ to find a new solution.\n\nApparently it seems most of these conjectures had not been seriously attacked by computational methods before the AlphaEvolve paper.",
"sig": "b9a2fa7065c2c7ee6c96adc4900c3a7050818970b1152a2d5a3ac85bb5f9d74e6645cee7f867b17928d08c4433d290275f6fb90fa27b4d1ca64cacc22f80302d"
}