rallies

I get this a lot.

1) I think as agents get better, the probability that this happens becomes low. 2) I hate saying this tbh, but Robinhood is very clear that any mistake in the account is user's responsibility.

The only thing I can do on our end as we build this is make sure all context is there for the model to not make such decisions, there are software based safeguards, etc.

It'll take some time but I think as long as there's good context and guardrails, you can really prevent a lot of bad stuff from happening.

I'm very bullish on LLMs being able to invest in the market well, as long as proper safeguards are there.

Robinhood agentic accounts is an amazing idea but you can't really automate stuff that can run on its own. Different companies have different ways for setting up automation which most retail traders are not aware of.

Agency fixes a lot of this. It's a Mac OS app that keeps your account on your device, and lets you build agents that can run on their own every day to manage a sleeve of your cash.

Software engineer, trying to get into fintech. This is an open source tool I built to test out a bunch of portfolios I'm building with AI.

Unfortunately we already have a product we're building. Probably can't find any extra time.

this is such a great answer, thanks! printing them out and reading them today

Not difficult at all.

Nof1 has actually been doing that.

Cruel. Was having a good day! I know it's my own thing, but it's free, and it was a lot of work.

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.

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.

correct.

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.

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.