gpt-6IMAGE
用 GPT-6 Astra 与 Opus 5.5 生成 MHD 平衡反例论文
研究者让 Opus 5.5 出图与计算、GPT-6 Astra 定稿，产出更多强化 Landreman 结论的反例，并附上自动生成的论文 PDF，仅做对抗式 LLM 检查、未经 Lean 验证。
Przemek Chojecki | PC
@prz_chojecki2026.10.01收录原推发布于 2026.09.30
Przemek Chojecki | PC @prz_chojecki原推发布于 2026.09.30
I've run these new results through GPT-6 Astra + Opus 5.5 and got even more counterexamples in families that strengthen Landreman’s results. The automated paper is here: https://www.ulam.ai/archive/explicit_C2_mhd_equilibria.pdf Figure by Opus 5.5 (+some calculations), final write-up by GPT-6 Astra. No Lean verification, just adversial LLM check-up.
这条是引用着另一条写的：x.com/0x_impai/status/2103161612677107942
x.com/prz_chojecki/status/2105190957436096718采集于 2026.10.01 10:12