GPT 5.6 Pro Helps Break Record for Prime Gaps, Result Formalized in Lean
thomasahle · x · 2026-09-01
Mathematician Thomas Bloom reported that GPT 5.6 Pro, prompted by user DottedCalculator, has improved the bound on prime gaps by combining new sieving ideas with the established [FGKMT18] framework. The new bound saves a factor of approximately log3(n) compared to the previous record set in 2018. Furthermore, this result has been formally verified in Lean by Alexeev, highlighting the growing role of AI in advancing mathematical research.
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