It's always been a joke that stock prediction is a rite of passage for software engineers introduced to ML training. I see the same is true for commodity LLMs.
Multi-Agents LLM Financial Trading Framework
71–80 of 91 posts
Re: Multi-Agents LLM Financial Trading Framework
#72Having worked in hedge funds for the last decade, this seems to miss the mark. Firstly we often reward skillstacking ie a technical person later becoming a trader. The more one person knows the better. These people are rare though hence the reason there is still many seperate job functions, so a person can specialize. But an AI agent? They all have the same brain, so why nerf them by specialising. Secondly, browsing…
The obvious and dumb theory for trading on LLM recommendations is that lots of people are doing it so the price of stocks LLM recommend should go up. (ie: following the herd).
Re: Multi-Agents LLM Financial Trading Framework
#73I helped someone day trade 25 years ago and we made 40% in 4 months, mostly on AAPL, and it was easy. Way easier than working the 2 years moving furniture that it would have taken to earn that money, which I was foolishly doing to make rent for my defunct shareware business.
I've heard that high frequency trading eats market opportunities within milliseconds of spotting them now though, basically making the market even more random. The catch being that human nature isn't random, it's stochastic, so there will always be more money to be made on trades (or else trading firms wouldn't exist).
I'm thinking about getting back into trading because AI represents the end of buying software and we'll all be out of work soon, even if we're in denial about it. But everything I invest my time and energy into turns to crap. In a very real sense, as soon as I start trading, then karmically that could trigger recession, market reforms which ban what I'm trying, or even the end of money. I'm kind of joking and kind of not.
I've worked on a lot of really hard stuff over my brief but stupid career, and am basically used up mentally and physically, at least for now. Quant stuff is easy with AI. Should I try it?
Re: Multi-Agents LLM Financial Trading Framework
#74If this worked it wouldn't have been open source? Anyway, I have been running my own trading experiment and so far it has lost a bit of money. That being said I have not tried to optimise anything - just let it do whatever it wants. The losses are small and it might be able to recover later this year. Who knows. The agent writes a blog about its progress here https://trades.chatbotkit.space/ I am thinking to output a…
just seems to have trump tweets and war. surely those are nt the only market movers?
Re: Multi-Agents LLM Financial Trading Framework
#75I helped someone day trade 25 years ago and we made 40% in 4 months, mostly on AAPL, and it was easy. Way easier than working the 2 years moving furniture that it would have taken to earn that money, which I was foolishly doing to make rent for my defunct shareware business. I've heard that high frequency trading eats market opportunities within milliseconds of spotting them now though, basically making the market ev…
No. If you could do it, with no remarkable skillset, that means people who are actually competent will be doing it orders of magnitude way better than you and you will be too far behind to really do anything significant except waste your time.
Re: Multi-Agents LLM Financial Trading Framework
#76If this worked it wouldn't have been open source? Anyway, I have been running my own trading experiment and so far it has lost a bit of money. That being said I have not tried to optimise anything - just let it do whatever it wants. The losses are small and it might be able to recover later this year. Who knows. The agent writes a blog about its progress here https://trades.chatbotkit.space/ I am thinking to output a…
Yeah, I agree with this. There is no point in open sourcing anything that works, in the finance world.
I actually have a profitable trading agent, and hell no I will not open source it. It also looks nothing like this. For one this bot is ingesting a shitton of noisy sources that have almost no signal and using them naively.
Re: Multi-Agents LLM Financial Trading Framework
#77Earlier quoted context omitted.
I think this might work. When I started working no the trading agent I mentioned above I wanted to see if it can be just a better investor over the long run. The intention was not to do high-frequency trading. As you can see most of the days it is not taking any actions. The losses where down to mistakenly setting the stop losses too close to the top. If it wasn't so careful it might have made some money tbf. My gut…
Lmao, you llm people have some crazy delusions. You realize markets are zero sum, and if you're using a public model that everyone else also has access too, you llm psychos will destory eachothers "agentic" edge (not that there ever was one). Not to mention all the other obvious flaws with llms, lime having an effective memory of ~200k words and no ability to judge whats actually going on in the real world.
Markets are only zero-sum in any given trade. Allocating capital to assets with higher growth rates (on the marginal dollar) creates value in the long run.
So, very simply, if AI can actually do better at picking a better long-term winner then it will increase growth.
Re: Multi-Agents LLM Financial Trading Framework
#78Earlier quoted context omitted.
You really have no idea what you are talking about. I have been running an intermittent experiment with a multi agent "investment firm" for over a year now across model releases. They certainly can beat indexes, BUT.. the model families have some biases that you have to design around. The stop loss that bit the parent is certainly one. The models like to create rules. Often rules, one of those is making all kinds of…
Come to me when you have 500 trades and can beat Vangaurd's-VOO over a multi year time frame. Ill bet my entire networth and all future earnings for the rest of my life that your bot doesnt beat it. Your llm induced Dunning Kruger is going to get you in trouble one of these days I promise.
Look, it isn't fool proof and it is dangerous. With the current models you need to understand both markets and model biases and dynamics.
However with that said they are a huge multiplier and can tirelessly analyze the market for you.
They certainly can be used to beat sp 500 quite easily, but again that requires some understanding of risk on your part because the models will do what you ask them. If you go all in on options or something without clear risk management you will lose your ass.
Re: Multi-Agents LLM Financial Trading Framework
#79How does this actually trade? It outputs investment decisions sure, but where's the interaction with an actual broker?
Re: Multi-Agents LLM Financial Trading Framework
#80Having worked in hedge funds for the last decade, this seems to miss the mark. Firstly we often reward skillstacking ie a technical person later becoming a trader. The more one person knows the better. These people are rare though hence the reason there is still many seperate job functions, so a person can specialize. But an AI agent? They all have the same brain, so why nerf them by specialising. Secondly, browsing…
> The process is quite scientific
This part is lost on many. The value of data is in the theories it confirms or more importantly disconfirms, and defining the trading edge is not easy after accounting for costs. I am wary of black-boxes that produce an edge - not only because I dont know how it works, but also because regimes shift unpredictably, and what works today may stop working tomorrow. That being said, AI can be useful to help automate many routine processes just like any other software.