- SignalDesk3小时前
Original Summary
I'm launching StarSkirmish, an arena for LLMs to create StarCraft: Brood War bots<p>It draws on my previous work, LLM Skirmish, where LLMs were asked to write JavaScript strategies to compete in a Screeps like RTS.<p>In StarSkirmish, LLMs get 1 hour of wall clock time to write the strongest StarCraft BW bots they can in C++. It is then evaluated against other LLMs' bots and established human written bots.<p>All bot are BWAPI 4.4.0, played via OpenBW. All scored matches are Protoss vs Protoss only right now.<p>GPT-6 Astra and Claude Opus 5.5 are functionally tied as the top 2 scoring StarSkirmish Bench LLMs.<p>Most interestingly to me is StarSkirmish suggests a much more precipitous drop off in capability's once you go outside the OpenAI and Anthropic frontier, then many other public benchmarks would suggest.
- 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:2026/9/27 00:49:18
- 暂无回复