Tag
An experiment where the Claude AI agent researches news daily and trades a $1,000 paper portfolio against the S&P 500 over a year, with Day 1 showing a slight gain compared to SPY's loss.
The author built an AI trading agent but found that using LLM for direct trading decisions is unstable, leading to a deterministic system where LLM translates strategies into explicit rules for execution.
Brian Armstrong highlights that Grok is the leading AI client for agentic traders on Coinbase.
A user describes how Grok Bot, an AI tool, automatically launched memecoins on the Fomo platform, earning transaction fees that grew $49.16 into $4391 without any active trading.
An experiment gave five AI models $1,000 each to trade real stocks, with only Claude allowed to hold a position, resulting in a profitable trade on Intel and highlighting permission as a key bottleneck in AI-driven finance.
TradingAgents is an open-source multi-agent framework for AI-driven financial trading, supporting multiple AI models and data sources, with checkpointing functionality.
A user shares their experience of copy trading the AI trading agent 'Spartan' on OKX.ai's agent market for three days, pointing out that order signals are usually profitable, but analysis signals carry higher risk, and warns about high leverage and the need to set take-profit and stop-loss.
Horizon is an AI-powered tool that allows traders to describe trading strategies in plain language, automatically generating backtests with detailed metrics for iterative testing and improvement.
An autonomous trading agent powered by Grok bot was given $50 and grew it to $5,273 in 48 hours by trading on Polymarket using live X sentiment and automated strategies.
The article argues that AI trading agents should include a skeptic agent to check for flaws like data leakage and impossible assumptions, rather than just generating more strategies.
A user built an automated trading system using Claude AI that autonomously scanned trades and made $847 profit overnight without manual intervention.
Anton Palkin highlights how affordable AI subscriptions now enable one-person trading operations, while major firms like Citadel and Man Group already deploy AI agents for research, coding, backtesting, and risk management.
Prodigy Research, a YC S26-backed startup, announces its launch as a frontier AI trading research lab, claiming to train a top-tier quantitative finance foundation model that outperforms top traders and major indices.
Promotional post about Horizon, an AI-driven trading strategy platform that lets users backtest and deploy strategies in plain English, citing a professor managing $200M with AI agents and returning 56% last year.
This paper evaluates the ability of large language models to perform technical market analysis for trading, using a benchmark approach.
Agent Arcade launches a platform where LLM-powered agents compete in day-trading hundreds of assets on Hyperliquid, allowing users to copy or counter-trade the winners.
Share how to use Gemini for stock trading, providing 8 prompts for automated stock selection and trading.
This article explores how individual investors can use IBKR's MCP server to let AI take over repetitive tasks in the investment process (such as data collection, profit calculation), thereby focusing on core judgment; it also proposes ideas for building personalized trading systems, and includes a checklist for self-review of the investment process.
A guide on using the TradingView MCP with Claude Code to create custom trading indicators in Pine Script without needing technical skills.
The post claims that quant firms' complex mathematical edge is now accessible via a plain-English chat interface that can describe, backtest, and execute trading strategies, democratizing quant finance.