Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Multi-Agents LLM Financial Trading Framework

github.com

Post reply on HN
Print view View original

11–20 of 91 posts

Re: Multi-Agents LLM Financial Trading Framework

#11

Post by audinalexandre »

hacker_9 wrote: post #8

Having 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…

As local contexts/skills get better at depicting what's to be expected and what an agent can work with and work to get better at, having more and more little specialized agents working as a swarm get you, with a field-skilled human as a supervisor, really good results even in highly niche and technical fields

Re: Multi-Agents LLM Financial Trading Framework

#12

Post by looofooo0 »

hacker_9 wrote: post #8

Having 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…

Given what a know about the 2008 financial crisis, wouldn't an AI analysis in the years before that crisis of the real state funds helped to understand the risk of them better and avoid the big exposure.

Re: Multi-Agents LLM Financial Trading Framework

#15

Post by mechazawa »

politelemon wrote: post #4

103K stars, so clearly it's popular. Has anyone here used it, and what are the outcomes like, and importantly, who is the target audience for this? I can see the intention behind crawling social media and news feeds to determine some 'evidence', but am not sure if that's the best approach or even if an LLM is the best way to get an assessment, or whether having so many input sources is a good idea.

I feel like a lot of the stars for repos like this are from people who are riding the AI hype train and not actually interested in using the software

Re: Multi-Agents LLM Financial Trading Framework

#17

Post by testaccount121 »

politelemon wrote: post #4

103K stars, so clearly it's popular. Has anyone here used it, and what are the outcomes like, and importantly, who is the target audience for this? I can see the intention behind crawling social media and news feeds to determine some 'evidence', but am not sure if that's the best approach or even if an LLM is the best way to get an assessment, or whether having so many input sources is a good idea.

103K stars in a few months, smells of purchased stars IMO.

Re: Multi-Agents LLM Financial Trading Framework

#18

Post by _pdp_ »

If 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 all the chat logs to HF as well for research.

You can run your own trading agents that communicate over a message buss in your own terms by downloading the CBK platform and running it locally with your own models. I have also shared my trading blueprint if you want to give it a go. https://chatbotkit.com/hub/blueprints/trader

Re: Multi-Agents LLM Financial Trading Framework

#19

Post by hacker_9 »

looofooo0 wrote: post #12
hacker_9 wrote: post #8

Having 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…

Given what a know about the 2008 financial crisis, wouldn't an AI analysis in the years before that crisis of the real state funds helped to understand the risk of them better and avoid the big exposure.

The problem wasn't the analysis, given it was found out before it happened. The problem was politics, and as usual pushing the system to its limits and beyond.

Re: Multi-Agents LLM Financial Trading Framework

#20

Post by whazor »

_pdp_ wrote: post #18

If 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…

It would be more interesting to compare trading agents with index tracking ETFs. The better version of an ETF could maybe be a model where you zoom in on the companies and add/remove to your portfolio on the company related news, but keeping a broader portfolio.

Maybe agentic trading still performs worse than ETFs. But alternatively, if it were meaningfully better then it would be okay to opensource, similarly how ETFs are publishing their portfolios.

Post reply on HN