Paper uses Kimi K3 to find anomalies and GPT-6 Astra to argue bull vs bear
A three-stage pipeline has code find anomalies, Kimi K3 read financial reports, and Astra run bull-versus-bear debates only on surviving targets, at about $450 a day.
this paper is actually insane for three years every LLM market analyst has done the same thing: read everything, guess BUY or SELL the paper's whole argument: by the time your model finishes reading, the signal is already priced in. prediction was never the right target what they built instead - three stages, one job each: code finds the anomaly, free Kimi K3 reads eight quarters in one window, ~$153/day GPT-6 Astra argues bull vs bear, only on what survives - ~$240/day 10,000 companies in. 8 arbitrations out. $450 a day instead of $60,000 37% precision on what gets flagged, against a 15-20% base rate no call, no score - just the contradiction, sourced read it ↓
This post quotes another post: x.com/gyome1_/status/2098057823930155319