WHAT NEW IN X11.08 SUN

X 上的 AI 合集档案 · 25 个合集 · 73,815 条

gpt-6IMAGE

让 GPT-6 Astra 与 Opus 5.5 写代码打星际争霸

测试者允许两个模型写代码后让它们在星际争霸中对战,发现两者接近但能力衰减很快,差距可能比 Intelligence Index 显示的更大。

kai
@kaimcpheeters2026.09.27收录原推发布于 2026.09.27
让 GPT-6 Astra 与 Opus 5.5 写代码打星际争霸
kai @kaimcpheeters原推发布于 2026.09.27
在 X 上打开原推

GPT-6 Astra and Claude Opus 5.5 can be competitive in StarCraft once they are allowed to write code. However, the field falls off fast - suggesting bigger differences in capabilities than other benchmarks like @ArtificialAnlys Intelligence Index might suggest

x.com/kaimcpheeters/status/2103880194930966869采集于 2026.09.27 10:07