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

Robinhood now lets your AI agents trade stocks

techcrunch.com

Post reply on HN
Print view View original

171–180 of 192 posts

Re: Robinhood now lets your AI agents trade stocks

#171

Post by infecto »

thisisit wrote: post #139
crazygringo wrote: post #47

Earlier quoted context omitted.

Alpha is ultimately the result of analysis, of better analysis than others. LLM's can actually be exceptionally good at research and pattern recognition, i.e. analysis. And while they aren't great at running numbers themselves, they can do exceptional work passing off Python scripts to an interpreter to generate the numerical results they need. I'm quite sure the Robinhood AI is going to be trash, i.e. just a gimmick…

> LLM's can actually be exceptionally good at research and pattern recognition, i.e. analysis. Sure but knowing where to start research is also a problem. Just saying “do research” isn’t going to work even with volumes of public information.

Well said. Lots miss this key point and it’s what I mean by alpha. Where to start, what the angle is, and LLM can help develop though I would of course argue it’s a fools errand with how crowded the space is but you could still develop an idea but it’s not going to create the idea for you.

Re: Robinhood now lets your AI agents trade stocks

#172

Post by infecto »

asdff wrote: post #91
tombert wrote: post #28

Earlier quoted context omitted.

I use the Interactive Brokers MCP pretty heavily. I don't do any cool automatic fun "trading", but instead I use it to have "pseudo-QQQ". I didn't like the relatively high fees for QQQ, and I realized that Invesco releases the weights for QQQ for free. I also think Tesla is too overvalued, and I want to avoid the SpaceX IPO. With the Interactive Brokers MCP, I just feed it the CSV of QQQ's weights, tell it to remove…

You don't need AI for this though. I was doing something like this with a python script and a crypto meta etf I created years ago. I even had some simple heuristics for selecting what coins and quantity to purchase given trading volume and spot price. Its like 175 lines of python. Probably could be a lot leaner too.

I am not sure I would trust a LLM agent to do this either. I would use an LLM to help write the script but not execute the trades.

Re: Robinhood now lets your AI agents trade stocks

#173

Post by yieldcrv »

Karrot_Kream wrote: post #163
yieldcrv wrote: post #159

Earlier quoted context omitted.

So does procedural code, the architecture supporting it and the humans writing it. I am capable of playing devil’s advocate as well Do you have an actual strongly held opinion or counterpoint on what I wrote? Time to market, covering bases, lower maintenance and things to keep track of all represent the utility

Have you actually put together trading strategies by having the agent drive? I've never trusted it that far and I use agents a lot at my job right now. The way I usually do it is, I break out pen and paper to do an analysis of what I want mathematically. I then have the agent build out some Python that lets me backtest and analyze my work. I read through the code (which is usually fairly compact since numpy/scipy and…

I have, and agents come up with the strategy and execution based on my contribution of what sectors to look at and alternative data sources I tell them to look at a certain way. My time horizons are quarters, as well as signal conversion into a variety of single and multi leg options trades

Re: Robinhood now lets your AI agents trade stocks

#174

Post by VanTheBrand »

infecto wrote: post #171
thisisit wrote: post #139

Earlier quoted context omitted.

> LLM's can actually be exceptionally good at research and pattern recognition, i.e. analysis. Sure but knowing where to start research is also a problem. Just saying “do research” isn’t going to work even with volumes of public information.

Well said. Lots miss this key point and it’s what I mean by alpha. Where to start, what the angle is, and LLM can help develop though I would of course argue it’s a fools errand with how crowded the space is but you could still develop an idea but it’s not going to create the idea for you.

Yeah if you have an actual really good idea for a certain kind of under analyzed data that could give you an edge but it would take too much effort or time to compile or analyze the data, an LLM has potential to make a viable strategy out of an otherwise correct but unuseful insight

Re: Robinhood now lets your AI agents trade stocks

#175

Post by theturtletalks »

I’m using Hermes Agent and this MCP to orchestrate 5 models (DS4 Flash, GPT 5.5, Opus 4.8, Grok Build, Gemini 3.5 Flash). Basically these 5 models are making mock trades every day and keeping track of their potential losses and profit. Hermes keeps them going and making trades throughout the day.

After a month, I’m going to check their mock trading sheet and see which one was the most “profitable” and then give that agent $500/day to make trades.

Re: Robinhood now lets your AI agents trade stocks

#176

Post by fancy_pantser »

theturtletalks wrote: post #175

I’m using Hermes Agent and this MCP to orchestrate 5 models (DS4 Flash, GPT 5.5, Opus 4.8, Grok Build, Gemini 3.5 Flash). Basically these 5 models are making mock trades every day and keeping track of their potential losses and profit. Hermes keeps them going and making trades throughout the day. After a month, I’m going to check their mock trading sheet and see which one was the most “profitable” and then give that…

You can use backtesting instead of waiting a month.

Re: Robinhood now lets your AI agents trade stocks

#177

Post by theturtletalks »

fancy_pantser wrote: post #176
theturtletalks wrote: post #175

I’m using Hermes Agent and this MCP to orchestrate 5 models (DS4 Flash, GPT 5.5, Opus 4.8, Grok Build, Gemini 3.5 Flash). Basically these 5 models are making mock trades every day and keeping track of their potential losses and profit. Hermes keeps them going and making trades throughout the day. After a month, I’m going to check their mock trading sheet and see which one was the most “profitable” and then give that…

You can use backtesting instead of waiting a month.

Yes but there’s many reports of agents getting back testing to work but it never translates to real trading. It seems they tend to overfit to back testing so I’m just giving them access to Twitter sentiment, other trading data thru tools and not necessarily an algo that’s been back tested. It’s why the flash models are doing better image they have faster tps and can call the tools faster.

Re: Robinhood now lets your AI agents trade stocks

#178

Post by fancy_pantser »

theturtletalks wrote: post #177
fancy_pantser wrote: post #176

Earlier quoted context omitted.

You can use backtesting instead of waiting a month.

Yes but there’s many reports of agents getting back testing to work but it never translates to real trading. It seems they tend to overfit to back testing so I’m just giving them access to Twitter sentiment, other trading data thru tools and not necessarily an algo that’s been back tested. It’s why the flash models are doing better image they have faster tps and can call the tools faster.

Alas, many financial models do well in backtests and then fail in the real world. You have to expose them to all kinds of market conditions and not just the recent one. Good luck out there!

Re: Robinhood now lets your AI agents trade stocks

#179

Post by ForHackernews »

theturtletalks wrote: post #177
fancy_pantser wrote: post #176

Earlier quoted context omitted.

You can use backtesting instead of waiting a month.

Yes but there’s many reports of agents getting back testing to work but it never translates to real trading. It seems they tend to overfit to back testing so I’m just giving them access to Twitter sentiment, other trading data thru tools and not necessarily an algo that’s been back tested. It’s why the flash models are doing better image they have faster tps and can call the tools faster.

>they have faster tps and can call the tools faster.

This is like going to war with the HFT firms armed only with a stalk of celery ("it's much pointier than the tomatoes, even though those are more expensive").

Post reply on HN