GPT 5.6 Breakthrough on Large Prime Gaps Verified in Lean
cloneofsimo · x · 2026-08-30
Reports indicate GPT 5.6 achieved a stronger result on large prime gaps, improving upon the best bound by Ford-Green-Konyagin-Maynard-Tao [2014] by a factor of log3 X / (log4 X)^2. Terence Tao had previously noted that breaking his result would require genuinely new ideas. The result has also reportedly been verified unconditionally in Lean.
Related event: GPT 5.6 Improves Long-Standing Prime Gap Bound(3 posts)→
More from Research
- IBM Proposes Spatial Matryoshka Training for Multi-Granularity Document Retrieval — _reachsumit · 2026-09-01
- Doc-REFRAG: coarse-compress then selectively expand for faster, more accurate multi-image RAG — _reachsumit · 2026-09-01
- Google Releases RSLM: Training-Free Vector Quantization for ANN Search — _reachsumit · 2026-09-01
- CHAP Framework Enables Personalized Generative Retrieval with Single-Pass Inference — _reachsumit · 2026-09-01
- Alibaba Jointly Trains Embeddings and Codebooks for E-commerce Generative Retrieval — _reachsumit · 2026-09-01
- Alibaba Proposes PAO to Prevent Embedding Collapse in RL Fine-Tuning for Retrieval — _reachsumit · 2026-09-01