__cayenne__

↗ HN profile [ 78.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 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

  2. 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…

  3. I'm launching StarSkirmish, an arena for LLMs to create StarCraft: Brood War bots It draws on my previous work, LLM Skirmish, where LLMs were asked to write JavaScript strategies to compete in a Screeps like RTS. In…

  4. I've liked all the projects that put LLMs into game environments. It's been a weird juxtaposition, though: frontier LLMs can one-shot full coding projects, and those same models struggle to get out of Pokémon Red's Mt.…

  5. My lobster lost $450k this weekend (pashpashpash.substack.com)
  6. Inspired by Screeps, LLM Skirmish is a RTS game you play with your preferred AI model

  7. I wanted to create an LLM game benchmark that put this generation of frontier LLMs' top skill, coding, on full display. Ten years ago, a team released a game called Screeps. It was described as an "MMO RTS sandbox for…

  8. What's New in Python 3.14 (docs.python.org)
  9. Snatched Party is a alien themed party game you can play for free in the browser with your friends or LLM powered game characters.

  10. /Llms.txt Directory (directory.llmstxt.cloud)
  11. Two weeks ago, I built a 3d browser based game that lets you speak into your mic and talk to LLM powered NPCs. You play as an alien tasked with abducting humans by luring them back to your ship. This is a playable early…

  12. I built a 3d browser based game that lets you speak into your mic and talk to LLM powered NPCs. You play as an alien tasked with abducting humans by luring them back to your ship. This is a playable early access / demo…