Hacker News new | ask | show | jobs
by kratom_sandwich 753 days ago
Form a quick glance at your websites the results only show performance and no volatility, which is only half the story.

Also, GPT seems to be mostly picking tech stocks; considering the fact that average performance of AAPL alone has been higher than SPY for the last 1/3/5/10 years, this result seems to be pretty much what one would expect …
1 comments
jcrash 753 days ago
Lol what more do you want? The experiment was to beat the S&P 500. You are dismissing the results because ... it chose stocks that would do that?
link
kratom_sandwich 753 days ago
I think it‘s only fair to be critical since there is a product attached to this experiment
link
dialup_sounds 753 days ago
You don't really need an LLM to beat SPY by choosing the largest four holdings of SPY. Plenty of passive funds already do something like that. It's a fun experiment, but don't misinterpret it to mean the LLM had a unique insight.

To frame it another way: When the best returns were from investing in the company that makes the GPUs that run the LLM that you're asking for stock picks from, did you really need the LLM?

link