Latest

Building an autonomous alpha research system that uses Claude Code to generate factor hypotheses, evolve strategies through mutation and crossover, and subject everything to a gauntlet of statistical tests designed to catch false discoveries.

How Recursive Self-Improvement turns LLMs from static prediction machines into trading systems that get better on their own -- learning from news, research reports, and price data through evolutionary search, self-critique, and memory-based refinement loops.

How I built an evolutionary factor mining system that uses Claude Code to autonomously discover, backtest, and evolve commodity futures trading factors — and what it found.

How to build a multi-agent trading firm with OpenClaw — specialized analyst agents running in parallel, adversarial bull/bear debate, dedicated risk management gates, sandboxed execution, and persistent memory that compounds institutional knowledge over time.

How to turn OpenClaw into a full-stack AI investment analyst — parsing sell-side research PDFs, building code-based financial models, running 24/7 market monitoring with heartbeat alerts, and conducting deep research with parallel subagents.