Discussion
How well can AI invest?
gambutin: Are you hedging against the AI bubble?
rallies: The AI models are. Somewhat.
pinkmuffinere: The link doesn’t let me read the post without downloading the app?? I’m not 100%, but I bet that’s against HN rules, and at least against the spirit. I’m flagging itEdit: I don’t want you to feel excessively bad, but you should feel bad for hijacking a user forum that _in good faith_ entertains new ideas like yours! This kind of behavior destroys the ecosystem you’re benefiting from.Edit2: It’s fixed! Thanks @rallies!
rallies: I'm fixing it. Give me a minute, apologies.Edit (reply on your edit lol): you're right.Second edit: fixed now. No more walls anywhere.
htrp: How are you different from all the other quant funds?
rallies: there is no human in the loop, there is no high frequency trading. We're trying to have AI mimic what fund managers do:- lots of research - longer time horizons - zero humans in the loop, but explain every single thing you do.
Kye: I was under the impression ML-driven trading was already widespread.
rallies: ML driven is. LLM driven is still nascent, especially the idea that as large language models get more advanced, can they research and invest like a fund manager.
mrbluecoat: Glad I didn't put my money on Qwen. -35% ouch
rallies: haha lol.I actually think it's doing better now. It was just too stubborn to exit its position for the first few months. It did that, and put some money into MSFT/JPM recently.
rallies: In case it's not clear.This is an experiment to see how well can LLMs invest in the market through a lot of research. We give them tool calls to access every financial dataset that exists online, and also some money to manage. And we then see how well they do.The experiment started in November 2024.
vicchenai: The LLM vs traditional ML distinction is real. Quant funds have used ML for signal generation for years, but the premise here is different: can an LLM do the reasoning-heavy parts like reading 10-Ks, understanding macro context, and making judgment calls about position sizing? Curious what data sources the models are actually using most and whether SEC filings are in the mix.
charliememe99: Whats the goal of this though?
pinkmuffinere: Thankyou!! Will unflag
add-sub-mul-div: It's an account with no activity here except for self promotion. Everyone should be flagging it. It's an advertisement.
charliememe99: What the goal of this?
rallies: Founder here: YC actually had an "AI hedge fund" idea in one of their recent "request for startups" post. We've been working on evaluating the capabilities of frontier models in investing money in the stock market. Results are encouraging and we're not doubling down on it.Happy to answer any questions.
Kuyawa: How difficult would it be to do the same for the crypto world? I love the concept.
rallies: Not difficult at all.Nof1 has actually been doing that.
rallies: Cruel. Was having a good day! I know it's my own thing, but it's free, and it was a lot of work.
joshstrange: Are there multiple instances of each model running? Or at least more than 1? I'd be fascinated to see what multiple Claude instances would fare, would they all be up, or did this instance just get lucky?
RhysU: The default page load hides plots for all models with negative returns? That's sketch.
pinkmuffinere: > Results are encouraging and we're not doubling down on it.Personally I believe LLM-assisted trading is destined to underperform passive indices, so I also would have moved on from this. But you say results were promising, so I'm interested to hear why you're not pursuing it further. Is it just that you have other things to focus on? Is there something else that's making you move on?
