Hacker News: cayenne

New comment by cayenne in "DeepClaude – Claude Code agent loop with DeepSeek V4 Pro"

__cayenne__ — Mon, 04 May 2026 02:59:52 +0000

The maintainer, Mario, sometimes declares the repo is on an “issue holiday” where issues are auto closed. This particular holiday is because there is a big refactor coming up. In non holiday periods issues can be reported as normal.

Zappa: An AI Powered Mitmproxy

__cayenne__ — Wed, 15 Apr 2026 23:33:13 +0000

Article URL: https://geohot.github.io//blog/jekyll/update/2026/04/15/zappa-mitmproxy.html

Comments URL: https://news.ycombinator.com/item?id=47786753

Points: 3

# Comments: 0

A 5x faster Maestro runner implemented in Go

__cayenne__ — Wed, 01 Apr 2026 20:08:28 +0000

Article URL: https://github.com/devicelab-dev/maestro-runner

Comments URL: https://news.ycombinator.com/item?id=47605879

Points: 2

# Comments: 0

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Thu, 26 Feb 2026 15:24:36 +0000

Didn't observe any cheating attempts at the JS level yet, the primary attack was LLMs trying to find local creds to access the other LLM's per round strategies from inside the harness (which ultimately was OpenCode running in Docker).

In the benchmark, in each round every LLM plays every opponent, and then we do that multiple times (an "epoch").

In the community ladder, when a player submits a strategy it plays a match against the latest strategy submitted by every player.

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Thu, 26 Feb 2026 01:30:41 +0000

There’s two levels of in game event level logs the LLMs have access to, one less token intensive than the other. Duplicate and uninteresting game state can be compressed and interrogated by the LLMs via tool use. All game state is available as text only state.

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Wed, 25 Feb 2026 19:58:40 +0000

okay leaderboard match making changes have gone live

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Wed, 25 Feb 2026 19:02:02 +0000

LLM Skirmish is all 1v1 right now, but agents can plan by reviewing previous match results

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Wed, 25 Feb 2026 16:07:05 +0000

Yes, I used Elevenlabs for the voice over audio - I couldn't get the voice stability I wanted with Elevenlabs v3 so had to use Elevenlabs v2.

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Wed, 25 Feb 2026 15:54:55 +0000

Tweaking the leaderboard match assignment logic now to prevent these bad incentives - definitely want people to iterate!

I had started with the Silicon Valley characters as a one off way to seed the board.

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Wed, 25 Feb 2026 15:43:57 +0000

Very interested in self-play training loops, but I do like codegen as an abstraction layer. I am planning to make it available as an RL environment at some point

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

__cayenne__ — Wed, 25 Feb 2026 15:18:52 +0000

funny you mention this… I have a new project that is going in this direction

Show HN: A real-time strategy game that AI agents can play

__cayenne__ — Wed, 25 Feb 2026 10:02:45 +0000

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. Moon.

Because of this, I wanted to create a game environment 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 programmers." The Screeps paradigm of writing code and having it executed in a real-time game environment is well suited to LLMs. Drawing on a version of the Screeps open source API, LLM Skirmish pits LLMs head-to-head in a series of 1v1 real-time strategy games.

In my testing I found that Claude Opus 4.5 was the most dominant model, but it showed weakness in round 1 as it was overly focused on its in-game economy. Meanwhile, I probably spent a third of all code on sandbox hardening because GPT 5.2 kept trying to cheat by pre-reading its opponent's strategies.

If there's interest, I'm planning on doing a round of testing with the latest generation of LLMs (Claude 4.6 Opus, GPT 5.3 Codex, etc.).

You can run local matches via CLI. I'm running a hosted match runner with Google Cloud Run that uses isolated-vm. The match playback visualizer is statically served from Cloudflare.

I've created a community ladder that you can submit strategies to via CLI, no auth required. I've found that the CLI plus the skill.md that's available has been enough for AI agents to immediately get started.

Website: https://llmskirmish.com

API docs: https://llmskirmish.com/docs

GitHub: https://github.com/llmskirmish/skirmish

A video of a match: https://www.youtube.com/watch?v=lnBPaZ1qamM

Comments URL: https://news.ycombinator.com/item?id=47149586

Points: 220

# Comments: 78

My lobster lost $450k this weekend

__cayenne__ — Tue, 24 Feb 2026 18:33:51 +0000

Article URL: https://pashpashpash.substack.com/p/my-lobster-lost-450000-this-weekend

Comments URL: https://news.ycombinator.com/item?id=47140773

Points: 59

# Comments: 28

Show HN: A real-time strategy game that AI agents can play

__cayenne__ — Wed, 18 Feb 2026 15:08:44 +0000

Article URL: https://llmskirmish.com/

Comments URL: https://news.ycombinator.com/item?id=47061773

Points: 4

# Comments: 1

Show HN: LLM Skirmish, an RTS game you play with LLMs

__cayenne__ — Wed, 04 Feb 2026 15:52:38 +0000

Inspired by Screeps, LLM Skirmish is a RTS game you play with your preferred AI model

Comments URL: https://news.ycombinator.com/item?id=46887350

Points: 1

# Comments: 0

Show HN: LLM Skirmish – a benchmark where LLMs play RTS games, by writing code

__cayenne__ — Wed, 04 Feb 2026 13:59:36 +0000

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 programmers." In Screeps, human players write javascript strategies that get executed in the game's environment.

The Screeps paradigm, writing code and having it execute in a real-time game environment, is well suited for an LLM benchmark. Drawing on a version of the Screeps open source API, LLM Skirmish pits LLMs head-to-head in a series of 1v1 real-time strategy games.

Comments URL: https://news.ycombinator.com/item?id=46885863

Points: 5

# Comments: 2

Apptron – Run Linux in the Browser

__cayenne__ — Fri, 02 Jan 2026 21:41:02 +0000

Article URL: https://github.com/tractordev/apptron

Comments URL: https://news.ycombinator.com/item?id=46469731

Points: 1

# Comments: 0

What's New in Python 3.14

__cayenne__ — Fri, 26 Sep 2025 19:53:59 +0000

Article URL: https://docs.python.org/3.14/whatsnew/3.14.html

Comments URL: https://news.ycombinator.com/item?id=45390400

Points: 14

# Comments: 1

Figma's S-1/A from their IPO today

__cayenne__ — Thu, 31 Jul 2025 19:39:43 +0000

Article URL: https://www.sec.gov/Archives/edgar/data/1579878/000162828025035381/figma-sx1a.htm

Hacker News: __cayenne__

New comment by __cayenne__ in "DeepClaude – Claude Code agent loop with DeepSeek V4 Pro"

Zappa: An AI Powered Mitmproxy

A 5x faster Maestro runner implemented in Go

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

New comment by __cayenne__ in "Show HN: A real-time strategy game that AI agents can play"

Show HN: A real-time strategy game that AI agents can play

My lobster lost $450k this weekend

Show HN: A real-time strategy game that AI agents can play

Show HN: LLM Skirmish, an RTS game you play with LLMs

Show HN: LLM Skirmish – a benchmark where LLMs play RTS games, by writing code

Apptron – Run Linux in the Browser

What's New in Python 3.14

Figma's S-1/A from their IPO today

What happened to the AI game? Lessons from experiments in AI game design

Hacker News: cayenne

New comment by cayenne in "DeepClaude – Claude Code agent loop with DeepSeek V4 Pro"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"

New comment by cayenne in "Show HN: A real-time strategy game that AI agents can play"