Someone let AI fully-control their stock portfolio: here's how it did

Switzer

Yesterday

Nathan Smith isn’t your typical investor. For one, he’s 17. For another, he wasn’t trying to get rich, he was trying to test a theory. Can AI run its own portfolio? What would happen if you gave a ...

Source Link

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.

Most Discussed

{"basename":"","ssrTDKData":{"titleTemplate":"%s - Tiger Brokers","title":"Tiger Brokers | Global Stocks, Options & Futures Trading App","description":"Tiger Brokers, one-stop investment in US stocks, SGX stocks, HK stocks, A-shares & other global assets. One of the best stock trading platforms in Singapore.","keywords":"tiger brokers,tiger trade,tiger brokers singapore,broker online,stock trading in singapore,share trading singapore,brokerage firm singapore,trading app,stock broker singapore,stock trading platforms,trading account","social":{"ogDescription":"Tiger Brokers, one-stop investment in US stocks, SGX stocks, HK stocks, A-shares & other global assets. One of the best stock trading platforms in Singapore.","ogImage":"https://c1.itigergrowtha.com/portal5/static/media/og-logo.be62fbe1.png","ogUrl":"https://www-web.itiger.com/news/2565578186"},"companyName":"Tiger Brokers"},"pageData":{"isMobile":false,"isTiger":false,"isTTM":true,"region":"SGP","license":"TBSG","edition":"fundamental"},"isCrawlerRequest":true,"__swrFallback__":{"@#url:\"https://stock-news.skytigris.cn/v3/news\",params:#id:\"2565578186\",edition:\"fundamental\",auth_exemption:1,,,undefined,":{"share":"https://ttm.financial/m/news/2565578186?lang=en_US&edition=fundamental","thumbnail":"https://switzer.com.au/wp-content/uploads/robot-ai-emilipothese-unsplash.jpg","is_english":true,"pubTime":"2025-09-08 06:58","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2565578186","market":"nz","top_or_hot":-1,"title":"Someone let AI fully-control their stock portfolio: here's how it did","media":"Switzer","content":"<div>\n<p>Nathan Smith isn’t your typical investor. For one, he’s 17. For another, he wasn’t trying to get rich, he was trying to test a theory. Can AI run its own portfolio?\nWhat would happen if you gave a ...</p>\n\n<a href=\"https://switzer.com.au/the-experts/luke-hopewell/someone-let-ai-fully-control-their-stock-portfolio-heres-how-it-did/\">Source Link</a>\n\n</div>\n","source":"switzer_stock","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>Someone let AI fully-control their stock portfolio: here's how it did</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\nSomeone let AI fully-control their stock portfolio: here's how it did\n</h2>\n\n<h4 class=\"meta\">\n\n\n2025-09-08 06:58 GMT+8&nbsp;&nbsp;&nbsp;<a href=https://switzer.com.au/the-experts/luke-hopewell/someone-let-ai-fully-control-their-stock-portfolio-heres-how-it-did/><strong>Switzer</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>Nathan Smith isn’t your typical investor. For one, he’s 17. For another, he wasn’t trying to get rich, he was trying to test a theory. Can AI run its own portfolio?\nWhat would happen if you gave a ...</p>\n\n<a href=\"https://switzer.com.au/the-experts/luke-hopewell/someone-let-ai-fully-control-their-stock-portfolio-heres-how-it-did/\">Source Link</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"ABEO","symbol_name":"Abeona Therapeutics Inc","start_time":0,"source_url":"https://switzer.com.au/the-experts/luke-hopewell/someone-let-ai-fully-control-their-stock-portfolio-heres-how-it-did/","article_id":"2565578186","we_media_id":null,"thumbnails":["https://switzer.com.au/wp-content/uploads/robot-ai-emilipothese-unsplash.jpg"],"rights":{"source":"switzer_stock","url":"https://switzer.com.au/the-experts/luke-hopewell/someone-let-ai-fully-control-their-stock-portfolio-heres-how-it-did/","rn_cache_url":null,"directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2565578186","pubTimestamp":1757285883,"columns":[],"sourceInfo":{"source_id":"switzer_stock","name":"Switzer"},"weMediaInfo":null,"summary":"Nathan Smith isn’t your typical investor. For one, he’s 17. For another, he wasn’t trying to get rich, he was trying to test a theory. Can AI run its own portfolio?","collect":0,"end_time":0,"defaultTopTitle":"switzer.com.au","property":[],"viewcount":null,"language":"en","relate_stocks":{"ABEO":"Abeona Therapeutics Inc","FDMT":"4D Molecular Therapeutics","ATYR":"ATYR PHARMA INC","CADL":"Candel Therapeutics, Inc.","BK4539":"次新股","CPSH":"CPS Technologies Corp","BK4082":"医疗保健设备","BK4139":"生物科技","BK4148":"电子元件","AXGN":"AxoGen Inc.","FBIO":"Fortress Biotech Inc.","MYO":"Myomo Inc."},"translate_title":"有人让人工智能完全控制他们的股票投资组合：事情是这样的","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"ABEO":1,"ATYR":1,"AXGN":1,"CADL":1,"CPSH":1,"FBIO":1,"FDMT":1,"MYO":1},"content_text":"Nathan Smith isn’t your typical investor. For one, he’s 17. For another, he wasn’t trying to get rich, he was trying to test a theory. Can AI run its own portfolio?\nWhat would happen if you gave a generative AI model full control over a real-money stock portfolio?\nIn June 2025, Nathan launched what he called a “real-money experiment” using just $100 and a free version of ChatGPT-4o, a large language model developed by OpenAI. The rules were strict: the AI could only invest in U.S.-listed micro-cap stocks (companies worth less than $300 million), had to work with whole-share positions (no fractional investing), and the portfolio would be judged over a six-month period, ending in December.\nThis wasn’t a paper-trading simulation. Nathan hooked the AI’s decisions into his brokerage account and manually executed the trades ChatGPT recommended. He treated the experiment as seriously as any professional backtest.\n“I wanted to see if an LLM could generate real alpha,” Nathan wrote in the project’s first post. “Not in theory, but with actual money, under real-world constraints.”\nThe project quickly picked up attention online—not just because of the novelty, but because it was working.\nOver the first ten weeks, the AI-powered portfolio soared over 32%, massively outperforming the S&P 500’s return of about 4.5% over the same period .\nBut how did it actually work? What exactly did the AI do—and how much of this was luck?\nTo the untrained eye, Nathan Smith’s trading setup might have looked like magic. But under the hood, it was a tightly scoped system powered by automation, discipline, and prompt engineering—not blind faith in AI.\nThe rules\nNathan set strict guardrails for the project:\n\n\nThe AI could only pick U.S.-listed micro-cap stocks (market cap under $300 million).\n\n\nThe portfolio was limited to $100 in total, and only whole-share purchases were allowed.\n\n\nThe timeframe was fixed: 6 months, from June 23 to December 23, 2025.\n\n\nThe AI had complete discretion over what to buy, when to sell, and how to manage risk, including stop losses and position sizing.\n\n\nNathan acted purely as the executor. He provided daily market data to ChatGPT, implemented the trades it chose, and asked for updated instructions.\n\n\n“I will only reach out to provide data and get decisions, nothing else,” he wrote. “You have full control… Your decisions must be based on deep, verifiable research.”\nThe build\nNathan used ChatGPT-4o, one of OpenAI’s publicly accessible models, and augmented it with a specific structure for how it received and responded to data. He created a consistent pipeline where each day’s closing prices, position sizes, and any pending news were sent into the model. Once a week, it was also allowed to use what Nathan called “Deep Research”—a prompt that told the AI to step back, review the portfolio from scratch, and make strategic decisions like a human fund manager might at a Monday investment meeting.\nThe AI would then:\n\n\nEvaluate its current holdings.\n\n\nSuggest trades.\n\n\nJustify each move—whether tactical (short-term catalyst) or strategic (long-term value).\n\n\nSet specific entry prices and stop-loss levels.\n\n\nDocument all changes in clear, reproducible steps.\n\n\nNathan coded basic tracking tools in Python to calculate returns, log trades, track benchmark comparisons (initially to the Russell 2000 and XBI, later to the S&P 500), and even calculate performance metrics like Sharpe Ratio, Sortino Ratio, Beta, and Alpha .\nKeeping track\nEarly on, the experiment attracted some criticism for being unclear or anecdotal. Rather than brush it off, Nathan responded by making the entire process radically transparent.\nHe committed to:\n\n\nPublishing full logs of prompts and AI responses.\n\n\nPosting raw performance data.\n\n\nAdding risk-adjusted metrics.\n\n\nDocumenting every single mistake he’d made in tracking or execution.\n\n\n“I want this to be judged by the same standards as anyone else,” he said. “I take this seriously and want the work to stand on its own—not be excused because of my age.”\nThat mindset set this project apart: it wasn’t a hype machine or a meme bet. It was a methodical test of whether a publicly available AI could act like a real-life hedge fund analyst, making decisions under constraints, in a high-risk part of the market.\nSo what did it actually buy?\nWith the system in place, ChatGPT was given its mission: build the strongest possible stock portfolio using only micro-cap U.S. equities and a $100 budget.\nMicro-caps are volatile, often illiquid stocks with market capitalisations under $300 million. They’re risky, sensitive to hype, and difficult to analyse—but for a nimble trader or an enterprising AI, they can offer massive upside.\nEarly picks and adjustments\nIn its first week of “deep research,” the AI settled on three small companies:\n\n\nMyomo Inc. (MYO) – A medtech company developing wearable robotics to help people with neuromuscular disorders. Chosen for its Medicare-driven growth and improving revenue.\n\n\nCandel Therapeutics (CADL) – A biotech firm working on cancer treatments, with positive Phase 3 results in the pipeline.\n\n\nCPS Technologies (CPSH) – An industrial turnaround play with defense contracts and actual profitability, rare in micro-cap land .\n\n\nEach decision was justified in writing, and orders were placed with limit prices and position sizes designed to balance the budget—roughly $30–$40 each.\n“I think the AI won’t find totally hidden gems,” Nathan said early on, “but it’s making rational, verifiable decisions about companies with data behind them.”\nAs weeks went on, ChatGPT began to shift its strategy. It leaned more heavily into biotech names with binary catalysts—events like FDA approval decisions or clinical trial results that could make or break a stock overnight.\nBy week 9, the portfolio was up over 32%, led by a heavy bet on aTyr Pharma (ATYR), which alone made up 50% of the total portfolio. Other holdings included:\n\n\nAbeona Therapeutics (ABEO) – transitioning to commercial stage with a funded runway.\n\n\nFortress Biotech (FBIO) – picked for its upcoming FDA decision.\n\n\n4D Molecular Therapeutics (FDMT) – a tactical buy following positive trial data .\n\n\nEach move included entry prices, stop-loss limits, and clear reasoning based on news flow, earnings catalysts, or technical setups. For instance, it exited a position in Axogen (AXGN) after an FDA decision was delayed, rebalancing into stocks with nearer-term events.\nRisk Management and Metrics\nDespite the risky nature of the stocks, the portfolio showed signs of structured risk control:\n\n\nStop-losses were enforced and adjusted over time.\n\n\nSharpe and Sortino Ratios (measures of risk-adjusted return) were calculated and posted.\n\n\nNathan even measured Alpha and Beta vs the S&P 500, though he acknowledged the sample size was too small to draw real statistical conclusions .\n\n\nPerformance as of week 10:\n\n\nTotal Return: +32.6%\n\n\nMax Drawdown: −7.1%\n\n\nSharpe Ratio (annualised): 2.96\n\n\nSortino Ratio (annualised): 5.26\n\n\nAlpha vs S&P500: 182.96%\n\n\nThese are exceptional numbers, particularly for a portfolio made up entirely of volatile micro-caps. Even professional funds rarely achieve this level of alpha in such a short timeframe.\nAI's biggest weakness\nNathan did point out one emerging flaw. As the portfolio evolved, ChatGPT started to fixate on high-risk, low-probability biotech events—drifting from diversification toward a concentrated “lottery ticket” approach. While this had paid off so far, it made the strategy more fragile.\n“With only four holdings, leaning too heavily into binary outcomes turns the portfolio into more of a lottery ticket than a repeatable strategy,” Nathan warned .\nStill, the AI’s ability to justify trades, manage risk, and adapt to news was far more sophisticated than many expected from a public model working under tight constraints.\nShutting it down\nAfter 10 weeks of trading, a 32% return, and hundreds of AI prompts, Nathan—still just 17 years old—decided to pull the plug on his experiment.\nIt wasn’t because the portfolio failed. In fact, it had dramatically outperformed the broader market, with results many professional traders would envy. But as the project grew, its original purpose was becoming less clear.\n“It had become a bit of a meme portfolio,” he said. “People loved the returns, but I felt like I was becoming more of an entertainer than an experimenter.”\nThe project had started as a genuine test: Can an AI build and manage a real-money portfolio using logical reasoning and open financial data? But as his social media following grew—largely thanks to screenshots of 10% weekly gains and AI-generated stock picks—expectations began to shift.\nFollowers began requesting daily updates, asking ChatGPT for new tickers, and meme-trading some of the AI’s selections. One of the stocks even pumped over 10% intraday after it was posted publicly—an echo of the “SPAC stack” or WallStreetBets frenzy.\nNathan didn’t want to fuel that kind of speculation.\n“It felt like we were slipping into hype and influencer territory,” he said. “That’s not what I built this for.”\nDespite shutting it down, Nathan came away with real insights:\n\n\nAI can do a lot more than people expect, but it needs well-defined constraints and constant human oversight.\n\n\nRisk management is the hardest part, especially with volatile assets. ChatGPT handled this surprisingly well, using stop-losses and adaptive sizing.\n\n\nGarbage in = garbage out. The biggest determinant of success wasn’t the AI’s brain, but the clarity of the prompt and rules Nathan used to guide it.\n\n\nHe also recognised the AI’s natural bias: when left unchecked, it would often chase catalysts and fixate on short-term wins over long-term fundamentals.\n“It could read earnings calls, find FDA dates, do sentiment checks—it was brilliant. But it wasn’t thinking in decades. It thought in weeks.”\nNathan isn’t done building.\nHe’s already working on a new project—a web-based app that uses AI to summarise earnings calls, pick up anomalies in trading volumes, and suggest potential breakout stocks before they trend.\nHe also wants to revisit the trading bot idea with a more robust stack:\n\n\nAPI-connected execution (rather than human input of orders)\n\n\nReal-time data ingestion\n\n\nMultiple LLMs working in tandem—one for sentiment, one for valuation, one for strategy\n\n\nEventually, he hopes to build a fully autonomous research assistant, not just a trading tool. Something that could read, digest, and recommend across 10,000 listed companies without bias—or hype.\nFor now, though, the experiment is paused. But the question lingers:\nIf a 17-year-old with $100, a laptop, and ChatGPT can do this… what happens when institutional capital tries the same?","kind":"highlight","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":0,"need_auth":false,"code":"91000000","status":"200"}}}