trading

A backtest of the RSI<30 oversold strategy on BTC shows it was profitable (+12.44%) despite a 51.85% win rate, but with marginal risk-adjusted metrics, highlighting that payoff structure matters more than indicator accuracy. Promotes Horizon's backtesting platform.

A trader on Polymarket earned $3,324.98 in two weeks by buying weather forecast contracts at low prices when predictions are nearly certain, highlighting a niche opportunity in weather prediction markets.

AAOI has surged nearly 6x YTD driven by AI data center demand for optical transceivers and potential US policy restricting Chinese imports; the post discusses trading strategies and promotes Bitget's tokenized rAAOI for 24/7 trading.

The article opens with a trading scene about liquidity and clearing trades, then focuses on Leopold Aschenbrenner's Situational Awareness LP fund's concentrated bets on AI hardware and chip stocks, noting recent market volatility.

Five months ago, Claude agents were given a $50,000 portfolio to beat the S&P 500; they are up 19.04% vs the S&P's 12.24%, with $27 million now copying the trades.

The author open-sourced the risk/authorization layer from their live trading system as a standalone fail-closed policy engine that evaluates agent actions before execution, and is seeking agent builders to pilot it.

Kirk Borne highlights the 3rd edition of 'Machine Learning for Trading' by Stefan Jansen, a comprehensive 826-page book on building AI-driven trading systems, and announces an accompanying live workshop on August 15.

TradingView's open-source lightweight front-end charting library lightweight-charts is only about 35KB, based on HTML5 Canvas, with extremely high performance, supports multiple chart types, and has a built-in AI Agent Skill.

Suhail recommends a book on hedge fund trading behavior, while Grok reports that fund Situational Awareness sold its public stock book after heavy losses on AI infrastructure names and short positions, with Citadel buying the bulk.

TradingAgents is an open-source multi-agent LLM framework for financial market analysis, routing market data through specialized agents for research.

Magents is an open-source Python framework for simulating and backtesting multiple trading strategies in one system, with isolated strategy pods, an event-driven engine, and central risk controls.

A discussion on why the 'agent economy' is empty, arguing that AI agents lack a native way to earn money, with trading proposed as the only viable first job for autonomous agents.

A report on a 3-week live test of an AI trading agent that is structurally unable to withdraw funds, detailing each guardrail's effectiveness and a discovered failure mode that none of them catch.

A study from Northwestern shows a 3-state Hidden Markov Model that detects market regimes to outperform traditional factor investing in S&P 500 trading, delivering 2% annual alpha and avoiding major crashes.

A curated list of 10 free GitHub repositories for algorithmic trading and quantitative finance, covering tools for backtesting, data analysis, portfolio optimization, and AI-driven trading strategies.

A guide on using the TradingView MCP with Claude Code to create custom trading indicators in Pine Script without needing technical skills.

Bitget's Stocks 2.0 introduces rTokens representing US stocks that are 1:1 backed and usable as margin for futures trading, offering capital efficiency and pre-IPO access.

Testing 7 frontier models on live prediction markets found only 2 made money; a forecaster tool built on the Limitless API flags markets where models have a real edge.

Auriko is a trading desk platform for making calls to large language models, providing a marketplace for LLM API usage.

ArkhasFlow, a professional trading platform, announces it is becoming fully open source, releasing all components including backend, frontend, and core infrastructure, allowing self-hosting with no dependency on the company.