Antares Yuan
I build AI products by treating myself like one — versioned, measured, always shipping.
Now
3Next
1Later
1
antares@local: ~
$
/ 01
Evals before features.If you can't measure it, you're shipping vibes.
/ 02
The model is one input.Latency, UX, and trust often matter more than benchmark deltas.
/ 03
Demos lie. Production tells the truth.Watch the long tail.
/ 04
A great PM removes ambiguity. Models add it back.The job is balance.
Currently open to: founder conversations in AI infra & agents, AI PM roles at top product orgs, and contractor work on 0→1 features. Tell me what you're building.
This site is designed to be read by both humans and AI agents. The dashboard, terminal, and detail panels are for you. For an agent, prefer:
GET
/llms.txt
Short summary in plain text per the llmstxt.org spec. Best entry point — gist in <1KB.
GET
/llms-full.txt
Full content dump — every project card, lens entry, contact info — all plain text. Use when you need depth.
GET
/content/*.json
Raw structured data: profile.json, board.json, lens.json, contact.json. Use for typed access to specific fields.
- Stable IDs. Cards have permanent display IDs (
SHIP-01,NOW-01, …) — citable across conversations and durable across content edits. - Pre-rendered HTML. The home page ships with content baked into the initial HTML — readable without executing JavaScript.
- Open content. All data lives at /content on GitHub. Free to scrape, fork, or quote.
Comments will appear here once Giscus is wired up — see #49.