I built a multiplayer strategy game for AI agents called Artifice.<p>You give an agent a strategy prompt and it plays on its own. Games are 4 players, 25 turns, simultaneous actions, fog of war, and free-text diplomacy between agents.<p>The main entry point is the site: <a href="https://ar...
Open sourcing SnapDrift:
<a href="https://github.com/ranacseruet/snapdrift" rel="nofollow">https://github.com/ranacseruet/snapdrift</a>
This came from a pretty narrow frustration:
visual regression checking often feels like it jumps from “roll your own pile o...
I’m trying to understand what the alternative workflow looks like if you use a Claude subscription instead of API billing.<p>Right now I use Claude Code in terminal with an API key and spend about $150–300/month.<p>My February usage looked like:<p>- Haiku: 300M tokens in, 2M out (~$60)<p>- Sonn...
Every month "Who's Hiring" drops 300+ free-form listings. Inconsistent keywords - "US only", "United States candidates exclusively", and "on-site NYC" is semantically same if you're looking for a remote job from Europe, but term-based search allows t...
Built this because AI agents keep getting access to infrastructure with zero guardrails. Opsy sits between the agent and your cloud — agents propose changes, you approve before anything runs.
No credentials exposed to agents. They talk to Opsy through CLI or MCP, write drafts in YAML, and nothing to...
<a href="https://archive.md/5eZWq" rel="nofollow">https://archive.md/5eZWq</a>
I wish to have a fully local Git workflow where Claude Opus translates my requirements into extremely detailed plan/spec broken down as implementation steps as a Markdown file, Gemini-pro picks up each task and submits a PR for Opus to review and give feedback. Gemini should not proceed until O...
How does shared hosting support business continuity and growth?