Building a $60,000-a-day stock research pipeline with Kimi K3 and GPT-6 Astra
The author splits research into a five-stage funnel: plain code for math, rule-based screening, Kimi K3 reading filings, GPT-6 Astra running bull-versus-bear debates, and human confirmation, at a cost of about $450.
This AI analyst does $60,000 a day of research for about $450 Kimi K3 + GPT-6 Astra, but the real trick is a funnel, not one giant model: signal → plain code → Kimi K3 → GPT-6 Astra → human → sourced report step 1 → plain code does the math first, zero LLM cost step 2 → rules and a light classifier cut 10,000 stocks to 150 step 3 → Kimi K3 reads eight quarters at once and keeps the 40 that don't add up step 4 → GPT-6 Astra argues bull vs bear, every claim needs a source step 5 → a human confirms anything that executes the result: no BUY, no predictions, just what changed and what contradicts it save this setup, watch the terminal above - then read the full architecture with formulas ↓
This post quotes another post: x.com/leopardracer/status/2101982527871131955