OpenAI withholds benchmark solutions; community proposes publishing hashes for verification
teortaxesTex · x · 2026-09-22
Rohit Krishnan 转发 OpenAI 相关消息并惊呼「This is insane！」——OpenAI 似乎完成了某项重磅任务但目前尚未披露解法。teortaxesTex 建议一个双赢做法：OpenAI 可以先公开无歧义的问题描述和答案的哈希值，让外界在官方解法公开前自行尝试复现，验证结果又不必剧透。
该建议呼应了基准测试公开、可验证的社区惯例，也侧面说明这次结果若属实分量不小。
Related event: OpenAI's Navier-Stokes Claim Draws Widespread Backlash from Mathematicians(16 posts)→
More from Models
- shadcn: Opus's 'taste' can't be benchmarked overnight, it takes real product building — shadcn · 2026-11-04
- Users say Claude's Ultrafast mode burns limits 8x faster — a 'flex' speed tier would make more sense — Lucky_Creme_5208 · 2026-11-04
- OpenAI quietly reverses its reverse engineering ban, diverging from Anthropic's stricter stance — AccBalanced · 2026-11-04
- Built with Claude Haiku 5.5, not Opus: pixel-art animation shows small models often suffice — Lazar988 · 2026-11-04
- Mistral Large 4 tested on real Django CVE: 133 agents find, prove and patch the bug — MistralAI · 2026-11-04
- Google and Mercor's PLE benchmark: all frontier agents score below 50% on 85 real engineering tasks — teortaxesTex · 2026-11-04