Simo Ryu Shares GPT 5.6 Prime Gap Claim
AI researcher shares apparent breakthrough on large prime gaps from GPT 5.6.
Simo Ryu posted on X that GPT 5.6 produced a stronger bound on large prime gaps. The tweet states the new result improves on the 2014 Ford-Green-Konyagin-Maynard-Tao bound by a factor of log3 X over (log4 X) squared. Ryu recalls Terence Tao saying a genuine new idea would be needed to surpass that work. The post links to an erdosproblems.com forum thread titled proof claims. No verification or independent sources appear in the packet.
Combined views
151.4K
3 posts, first seen 2d ago
Reactions
3 postsSR 
Simo Ryu@cloneofsimowow apparently there is now stronger result on large prime gap by GPT 5.6, improving beyond the previous best result of Ford-Green-Konyagin-Maynard-Tao [2014] by factor of log3 X / (log4 X)^2. I recall tao mentioning that it would require genuinely new idea to break his result,…
- likes: 427
- replies: 4
- bookmarks: 105
- reposts: 29
JD Jared Duker Lichtman@jdlichtmanVery nice!! GPT 5.6 has broken the record on large gaps between primes. The new bound saves a factor of ≈ log_3(n) over the prior record by Ford-Green-Konyagin-Maynard-Tao from 2018. The result is also now formalized by Alexeev in Lean.
- likes: 787
- replies: 15
- bookmarks: 224
- reposts: 91
JD Jared Duker Lichtman@jdlichtmanAlso note also Greens' comments, in particular on the speed of verification vs. digestion:
- likes: 98
- replies: 2
- bookmarks: 16
- reposts: 7