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 it
Edit: 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.
Show HN is meant for people that build a thing. It's not meant for incremental features. However, I'd say this counts as a 'new thing', not an incremental feature, so I think it should be allowed. At any rate, I'm happy to see it, and I think it meets the bar as compared to most Show HN's I've seen in the past.
Welp, sorry it got taken down in the end. At any rate I feel it's significant enough effort to earn a space on HN one way or another -- maybe worth submitting through the 'main channel' if people really don't feel it belongs in Show HN.
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?
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.
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.
> 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?
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.
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.
- First is to actually evaluate whether these LLMs have any intelligence around investing. If you actually give them all the data, can they do well? Can they beat the market? I'm not sure, we're testing that.
- My thesis is that they will actually beat the market (I know a lot of you will disagree). If that's the case, how can we invest a lot of resources in building the best harness, tool calling, etc to enable these models to invest.
What does "all the data" mean here? I see you mentioned SEC posts. What about news articles, twitter / blog / other posts, general info on the industries, etc?
I assume these are simulated trades, not real trades being executed. How accurately do you take into account trading fees, time from order-decision to order-placement, and things like this?
I would be interested to see the same test run on some prediction market (kalshi / polymarket / etc). In the stock market, a rising tide lifts all boats, so it's easy to deceive yourself about how well you've done, vs how important initial timing was. I suspect that prediction markets will eliminate that source of noise, since it's truly a 0 sum game. That said, it also adds lots of complication, insider trading will eat into your performance more, etc.
- We've built a local vector database with every SEC filing over the last few years. And we've built a tool call on top of that to allow these LLMs to read and query sec filings.
- Have done the same for a lot of other data sources, just giving the LLM access to them and allowing it to spend some time to actually research.
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 it
Edit: 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!
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.
Thankyou!! Will unflag
It's an account with no activity here except for self promotion. Everyone should be flagging it. It's an advertisement.
Show HN is meant for people that build a thing. It's not meant for incremental features. However, I'd say this counts as a 'new thing', not an incremental feature, so I think it should be allowed. At any rate, I'm happy to see it, and I think it meets the bar as compared to most Show HN's I've seen in the past.
Cruel. Was having a good day! I know it's my own thing, but it's free, and it was a lot of work.
Welp, sorry it got taken down in the end. At any rate I feel it's significant enough effort to earn a space on HN one way or another -- maybe worth submitting through the 'main channel' if people really don't feel it belongs in Show HN.
Thanks, I flagged. OP, you need more activity than just submitting your own articles.
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?
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.
is the leaderboard based on returns since november 24 ?
correct.
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.
> 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?
How difficult would it be to do the same for the crypto world? I love the concept.
Not difficult at all.
Nof1 has actually been doing that.
Glad I didn't put my money on Qwen. -35% ouch
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.
How are you different from all the other quant funds?
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.
The default page load hides plots for all models with negative returns? That's sketch.
I was under the impression ML-driven trading was already widespread.
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.
Whats the goal of this though?
Two goals.
- First is to actually evaluate whether these LLMs have any intelligence around investing. If you actually give them all the data, can they do well? Can they beat the market? I'm not sure, we're testing that.
- My thesis is that they will actually beat the market (I know a lot of you will disagree). If that's the case, how can we invest a lot of resources in building the best harness, tool calling, etc to enable these models to invest.
> If you actually give them all the data
What does "all the data" mean here? I see you mentioned SEC posts. What about news articles, twitter / blog / other posts, general info on the industries, etc?
I assume these are simulated trades, not real trades being executed. How accurately do you take into account trading fees, time from order-decision to order-placement, and things like this?
I would be interested to see the same test run on some prediction market (kalshi / polymarket / etc). In the stock market, a rising tide lifts all boats, so it's easy to deceive yourself about how well you've done, vs how important initial timing was. I suspect that prediction markets will eliminate that source of noise, since it's truly a 0 sum game. That said, it also adds lots of complication, insider trading will eat into your performance more, etc.
What the goal of this?
Are you hedging against the AI bubble?
The AI models are. Somewhat.
[dead]
[flagged]
I agree. A couple of things.
- We've built a local vector database with every SEC filing over the last few years. And we've built a tool call on top of that to allow these LLMs to read and query sec filings. - Have done the same for a lot of other data sources, just giving the LLM access to them and allowing it to spend some time to actually research.
10-Ks are going to be written by LLMs increasingly soon. I wonder how this will impact LLMs reading them.