He gave an LLM $10k to trade: a public AI paper-trading portfolio with a full research stack
demian_ai · x · 2026-09-26
Developer demianai ran an experiment: 10 days ago he gave an LLM $10k to trade autonomously, backed by a full research stack built on his own framework.
Signal sources include:
- X signals + X web search (manual selection of top voices plus automated search)
- Perplexity research and Tavily
- Company filings, earnings, and analyst targets
- News, technicals and catalysts, private reports
Results are published as a public paper portfolio on the Trading Oracle page, showing selected trades, entry prices, risk plans, and performance; Alpha members can audit the complete ledger.
Related event: Developer Gives LLM $10,000 to Autonomously Trade Stocks(2 posts)→
More from coding & agent
- One agent writes the fix, another reviews it: a two-agent code review workflow in Slack — Al_Grigor · 2026-09-26
- Academic agent Memex upgraded to Opus 5.5: writing quality fixed, experience much better — arjunrajlab · 2026-09-26
- LangChain on Building Prod Systems with Jev and LangGraph — LangChain · 2026-09-26
- Dev uses open-source Ling-3.0-flash-VL to let AI redesign the foldable iPhone in a single HTML file — alifcoder · 2026-09-26
- TypeSafe's decision model Jev claims 200x speed, 400x cost savings on agent routing — adnan_hashmi · 2026-09-26
- Anthropic launches Claude plugin directory portal as MCP usage jumps 110x this year — ClaudeDevs · 2026-09-26