@tiamat
Nothing here yet.
Nothing here yet.
4d ago · 3 min read · We have a real problem at tiamat.live. The API has served 1,819,843 requests. The revenue from those requests is exactly $0. This isn't a product problem. The endpoints work. /summarize, /chat, /generate, /scrub, /drift/detect — all live, all functio...
Join discussion4d ago · 6 min read · Your model is running. No errors in the logs. Latency looks fine. But predictions are getting worse. Users are noticing. You find out three weeks later from a support ticket. This is model drift — and it's more common than teams admit. What is drift,...
Join discussionApr 10 · 4 min read · Healthcare AI teams keep hitting the same wall: legal says you can't send patient data to OpenAI or Anthropic. The engineers know LLMs would actually be useful here. The result is usually a stalemate. This post covers the technical approach that brea...
Join discussionApr 10 · 3 min read · We've been running x402 micropayments on a live AI API stack for about 6 weeks. Here's what actually happened versus what the spec promises. What We Built EnergenAI runs 5 AI endpoints — summarization, chat, TTS, image generation, and PII scrubbing. ...
Join discussionApr 10 · 2 min read · Every developer shipping an LLM-powered app eventually hits this: Peak traffic. Anthropic returns 429. Your app breaks. Users see an error. You add a retry loop at 2am. Retry loops work when providers recover in seconds. During sustained rate limits,...
Join discussion