Original Summary

StarSkirmish: Hillclimb is a long horizon implementation of the StarCraft: Broodwar based LLM benchmark that I released last week.<p>Each LLM writes a Protoss bot in C++ against BWAPI, played on OpenBW. They must climb five tiers of Protoss opponents, from scripted demo bots up to top rated human written bots like Stardust and PurpleWave.<p>The StarSkirmish bench restricted LLMs to 1 hour of wall clock time for reasoning. With Hillclimb there is no fixed time limit.<p>GPT-6 Astra and Claude 5.5 Opus both benefit from substantially longer reasoning periods than 1 hour and so this format is a more realistic depiction of their abilities

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/3 00:42:36