I spent a year and $5,700 to see if ChatGPT can beat the market (S&P 500)

Re:I spent a year and $5,700 to see if ChatGPT can beat the ... by mechagodzilla on Monday May 27, 2024 @06:47PM (#40495511)

The 1-year return on $SPY is 26%, or 67% better than your GPT-4 return (https://www.google.com/finance/quote/SPY:NYSEARCA?window=1Y). I think you've been fooled by randomness over very short intervals.

[ Parent | on HN ]

Re:I spent a year and $5,700 to see if ChatGPT can beat the ... by ishtiaqrahman on Monday May 27, 2024 @10:02PM (#40496670)

You misunderstood my research, I think my wording wasn't clear enough. Let me clarify.

I am comparing SPY's return with the GPT return for the exact timeframe during which a particular position was recommended by the GPT Investor. For example, some positions were held for only 7 days, while others were held for 3 months, etc. I generated 19 different sets of recommendations with varied timeframes and at different points in the last year. This link, where I track everything, should clarify any confusion: https://www.gptinvestor.co/the-gpt-investor/

[ Parent | on HN ]

Re:I spent a year and $5,700 to see if ChatGPT can beat the ... by mechagodzilla on Tuesday May 28, 2024 @04:29PM (#40505257)

This is basically tea-leaf reading on your part - a dart board might give similar (or better!) results if tested in such a fashion, and it doesn't change the overall result that just putting your money in $SPY over the whole duration of the experiment was still a much better strategy.

[ Parent | on HN ]