中文 English Français Русский Español العربية

Show HN: Gemini 4 Argon plays StarCraft

Hacker News New2026-10-16 22:180 views

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: 1

# Comments: 0

Source：https://starskirmish.com/bench/v0-2/

My favorites

PreviousAsk HN: macOS 27.x upgrade without Siri eating disk space?NextHow to make System 1 LLMs show System 2 competencies?

Copilot Fusion's Local Model Preview: Only One of Three Stages Runs on Your Machine

GitHub shipped an experimental preview on October 28, 2026 that lets Copilot Fusion add eligible local models to its sma

0dev.to AI

Meituan shipped LongCat-2.5

Meituan shipped LongCat-2.5. 1.6T params, ~48B active, native multimodal, aimed at long-horizon agents, trained start to

0dev.to AI

Standard bf16 Rounding Discards 99% of Your RL Policy Updates

If you run reinforcement learning post-training on language models using frameworks like verl, TRL, or OpenRLHF, your ro

0dev.to AI

Why Are Startups Choosing Coworking Space in Pune in 2026?

Why Are More Startups Choosing Coworking Spaces in Pune in 2026? Pune has become an attractive destination for startups,

0dev.to AI

What a 32GB GPU actually lets you run locally

The jump to 32GB of VRAM on consumer cards (hello, 5090) is a bigger deal for local AI than the gaming benchmarks sugges

0dev.to AI

LLM weak random number generator detection test

Originally published at sunny-chokshi.github.io . I ran an LLM weak random number generator detection test on four Pytho

0dev.to Security

Show HN: Gemini 4 Argon plays StarCraft

Related posts

Copilot Fusion's Local Model Preview: Only One of Three Stages Runs on Your Machine

Meituan shipped LongCat-2.5

Standard bf16 Rounding Discards 99% of Your RL Policy Updates

Why Are Startups Choosing Coworking Space in Pune in 2026?

What a 32GB GPU actually lets you run locally

LLM weak random number generator detection test