1st Anniversary Update: The GPT Investor

Today marks the first anniversary of The GPT Investor, and we are excited to share the most important update since we began this journey.

Exactly one year ago, on May 16th, 2023, we started investing in the stock market using LLM-powered autonomous agents, which we named The GPT Investor. These investments were real, made with actual cash in the NYSE and NASDAQ, not just paper trading.

Our goal was to determine if autonomous agents powered by Large Language Models, such as GPT-4, could "beat the market."

"Beating the market" refers to achieving investment returns that exceed the performance of a benchmark index, such as the S&P 500. It implies that an investor's portfolio has generated a higher return compared to the average market return over a specified period. This concept is often used to evaluate the success of investment strategies or the skill of portfolio managers. We outlined our experiment in the very first article we published titled "Can GPT Investors beat index funds like $SPY?"

We wanted the GPT Investor to compete against the SPDR S&P 500 ETF Trust, also known as $SPY, an exchange-traded fund (ETF) that aims to track the performance of the S&P 500 Index. This index includes 500 of the largest publicly traded companies in the U.S., making $SPY a popular investment vehicle for those seeking broad exposure to the U.S. stock market.

$SPY is a formidable opponent because, over the last 10 years, fewer than 10% of active U.S. stock funds have managed to outperform index funds like $SPY. (Source)

If The GPT Investor could beat $SPY, it would mean it outperforms 90% of professional fund managers.

Methodology:

We experimented with various methods and technology stacks to generate stock recommendations, meticulously documenting and reporting the results to our subscribers. The common thread among these methods was:

• Using OpenAI's LLMs (GPT-3.5 and GPT-4.0)
• Enabling the LLMs to autonomously search the web
• Generating stock recommendations for specific durations, such as three months

We utilized platforms like ChatGPT, Godmode, and BabyAGI UI to generate the stock recommendations. Each of these platforms can perform multi-step reasoning, a crucial attribute of autonomous agents. For example, based on a prompt, the agent can create its own to-do list and independently execute the steps to arrive at a result.

We conducted 19 experiments, investing CAD $300 in each, for a total of CAD $5,700 invested. We used a Wealthsimple brokerage account to execute the trades. Since each stock recommendation had a specific duration, we closed the positions at the end of each duration and compiled the returns as part of The GPT Investor portfolio.

For every experiment we ran, we published the entire methodology (tech stack, prompt, LLM, etc.) and results on this platform—The GPT Investor.

Results:

• Total Invested: CAD 5,700
• Number of Experiments: 19
• Shortest Experiment Duration: 7 days
• Longest Experiment Duration: 1 year
• Number of Stocks Recommended by The GPT Investor: 31

Subscriber Only: To view all stocks recommended by The GPT Investor and their performance since they were recommended, click below:

Total Return:

• The GPT Investor: 11.54% (CAD $658.20)
• $SPY: 8.89% (CAD $507.10)

Overall, The GPT Investor Portfolio return was approximately 29.78% better than the $SPY's return.

Number of experiments by LLM

• GPT-4: 11 experiments
• GPT-3.5: 8 experiments

The average return for the two LLMs used by the GPT Investor is as follows:

• GPT-4: 15.54% (with a corresponding average $SPY return of 9.74%)
• GPT-3.5: 6.05% (with a corresponding average $SPY return of 7.74%)

GPT-4's return was approximately 156.86% better than GPT-3.5's return.

The results raise the exciting possibility that as LLMs become more powerful, the returns of The GPT Investor should improve even further.

We publish the real-time status of The GPT Investor on our website.

When we started The GPT Investor, we didn't expect to beat the market as comprehensively as we did in our first year. Our success in the first year of operation, combined with the rapid evolution of LLMs and autonomous technology, has made us even more bullish about using AI as part of the investing toolbox. If GPT-4 can beat the market so comprehensively, how much better could GPT-4o do? What about when GPT-5 comes out? What other strategies, prompts, and technologies can we use to generate even better stock recommendations? These are exciting questions, and we will continue to explore and answer them here at The GPT Investor.