https://aggr.aymericbeaumet.com/sources/starskirmish.com/ Browse aymeric's, an independent, searchable archive of readable snapshots from followed feeds, preserved in Git with aggr. en Fri, 16 Oct 2026 14:18:44 +0000 aggr https://aggr.aymericbeaumet.com/items/hnrss-org/2026-10-16-show-hn-gemini-4-argon-plays-starcraft/ urn:aggr:item:7a5f655f41b862b70ee817940c770fb65cda67a8 Fri, 16 Oct 2026 14:18:44 +0000 __cayenne__ I've refreshed StarSkirmish Bench, a benchmark where LLMs play StarCraft BW by writing code, with results from the flagship models of OpenAI, Anthropic, Google, and Muse Comments URL: https://news.ycombinator.com/item?id=50118688 Points:… <p>I've refreshed StarSkirmish Bench, a benchmark where LLMs play StarCraft BW by writing code, with results from the flagship models of OpenAI, Anthropic, Google, and Muse</p> <hr /> <p>Comments URL: <a target="_blank" rel="noopener noreferrer" href="https://news.ycombinator.com/item?id=50118688">https://news.ycombinator.com/item?id=50118688</a></p> <p>Points: 122</p> <p># Comments: 57</p> news