Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 55 min 1 sec ago

Steam Frame

Fri, 10/02/2026 - 12:55pm
Categories: Hacker News

Debian 13 as a dual WAN router

Fri, 10/02/2026 - 12:53pm
Categories: Hacker News

Dutch Computer Museums

Fri, 10/02/2026 - 12:52pm
Categories: Hacker News

OpenAI Deprecations

Fri, 10/02/2026 - 12:45pm
Categories: Hacker News

Show HN: GPT-6 Astra and Claude 5.5 Opus race to create the best StarCraft bot

Fri, 10/02/2026 - 12:42pm

StarSkirmish: Hillclimb is a long horizon implementation of the StarCraft: Broodwar based LLM benchmark that I released last week.

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.

The StarSkirmish bench restricted LLMs to 1 hour of wall clock time for reasoning. With Hillclimb there is no fixed time limit.

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

Comments URL: https://news.ycombinator.com/item?id=49935608

Points: 1

# Comments: 1

Categories: Hacker News

Show HN: Odd Essentials Agent Guild

Fri, 10/02/2026 - 12:40pm
Categories: Hacker News

Pages