Comment by lordnacho
16 days ago
I was chatting to a friend in the space. This guy is both experienced in trading and LLMs, and has gone all-in on using LLMs to get his day-to-day coding done. Now he's working on the model to end all models, which is a fairly ambitious way to put it, but it throws off some interesting conversations.
You need domain knowledge to get this to work. Things like "we fed the model the market data" are actually non-obvious. There might be more than one way to pre-process the data, and what the model sees will greatly affect what actions it comes up with. You also have to think about corner cases, eg when AlphaZero was applied to StarCraft, they had to give it some restrictions on the action rate, that kind of thing. Otherwise the model gets stuck in an imaginary money fountain.
But yeah, the AI thing hasn't passed by the quant trading community. A lot of things going on with AI trading teams being hired in various shops.
You can vibe code in this space as an individual because practically everything you are going to write is already in the training data.
The big Quant hedge funds have been using machine learning for decades. I took the coursera RL in finance class years ago.
The idea you are going to beat Two Sigma at their own game with tokens is just an absurdity.
Personally, I think any individual on their own that claims they are doing anything in the algorithmic / ML high frequency space is full of shit.
I could talk like I am too and sound really impressive to someone outside the space. That is much different though than actually making money on what you claim you are doing.
It reminds me of an artist friend when I was younger. She was an artist and I quite liked her paintings. She would tell everyone she is an artist. She was also an encyclopedia when it came to anything art related. She wasn't actually selling much art though. She lived off the $10k a month allowance her rich father gave her. She wasn't even being dishonest but when you didn't know the full picture a person would just assume she was living off her art sales.
> The idea you are going to beat Two Sigma at their own game with tokens is just an absurdity.
Individual quant traders aren't competing with Two Sigma. If you're an individual quant trader and you find a signal with $500k/yr capacity, that's awesome. If you're Two Sigma you won't give a single cahoot if it's not a $50M/yr signal. Two completely different ball games. I doubt Two Sigma is even trading on Hyperliquid either.
> Personally, I think any individual on their own that claims they are doing anything in the algorithmic / ML high frequency space is full of shit.
Well I'm in the space, but I've come across more than one guy who discovered a money making algo, all on their own, with all the right ideas but without the industry standard terms for them.
All logic would suggest this shouldn't be possible, but what I've seen is what I've seen.
>> Personally, I think any individual on their own that claims they are doing anything in the algorithmic / ML high frequency space is full of shit. <<
do you want to have a chat by Whatsapp then I can show you quite the opposite! :-) And in my case: Nobody knows, only one friend who is also deep in the stuff; people doing this are usually more quiet, since nobody is interested at all. I have some contacts in academia and shared my ideas with them - none of them said: "this wont work"
(Disclaimer: 25+y IT experience, 15 of them in finance)
>The idea you are going to beat Two Sigma at their own game with tokens is just an absurdity.
The idea isn't to beat them. It's to pick up the scraps. Same as every small trading operation.
I've seen the books of a guy who makes money hand over fist trading options. He'll be the first one to tell you what he does won't scale.
These kinds of tests to me are not complete until they resolve the concept to full solution:
-Start just as they have here
-Keep improving the prompts in a huge variety of ways to see what improvements can be made
-start getting more and more code generated to complete more and more percentage of the work instead of textual prompting
-start fixing the worst parts with real human knowledge code/tools
-finally show fully working solution that does well, with full analysis of what kind of human intervention was necessary, and even explore what kind of prompting could lead to these human intuition-ed tooling going to whatever incredible lengths necessary to hand-hold the models in the right direction
otherwise... i don't get the points of stopping and saying "doesn't do great"
> There might be more than one way to pre-process the data
I'm honestly more hopeful about AI replacing this process than the core algorithmic component, at least directly. (AI could help write the latter. But it's immediately useful for the former.)
[dead]