Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research • Hacker News Board

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#31

Post by RuiWang0811 » Wed, Aug 05, 2026, 3:29 PM UTC

hmokiguess wrote: post #30

Mzzzzz wrote: post #19

Earlier quoted context omitted.

Quant trading is an extremely high margin business itself. Quant shops are printing billions and have on average much higher profits per employee than tech companies. So it is definitely a business worth doing. On the other hand, you could also view quant research as some very hard research problems, so training LLMs on these problems could also enhance their general research capabilities.

Right, that's quant trading, that's not this business. Enhancing their research seems like they are your customer and you would be eating from their margin. How would you sell to them, you would deliver what? Faster time to decision? Wouldn't quants be your competition, given their work is building tools like this one?

No we sell our own research to AI labs as RL envs. Realistic RL envs grows in demand as labs seek better data train better models.

It’s a complimentary business. Simply put: we sell envs to labs, labs make better models, firms buy these models to make more profit. Everybody wins.

Yeah a competitor for us would be fellow quants doing the same thing. But even then every quant firm trades differently (and good ones all make money) so envs can still be sufficiently different.

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#32

Post by RuiWang0811 » Wed, Aug 05, 2026, 3:32 PM UTC

modgate wrote: post #27

Strong agree that static evals saturate — the decay property of markets is the genuinely useful part: historically, quant alpha decays on the order of 30-50% per year as capital crowds in, so a live market eval is self-difficultating, exactly what model comparison needs once benchmarks plateau. The hard part I'd flag is comparability: market paths are stochastic, so two runs of the same model can land on wildly diffe…

We use real historical market data for the environments. There is no parametric modelling involved.

The decay property refers to alpha that we give the agent for trade in the env - they are generated as tools.

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#33

Post by RuiWang0811 » Wed, Aug 05, 2026, 3:34 PM UTC

balanbong wrote: post #28

Curious as to whether you guys have shown that post-training has actually improved performance of agents in your environments.

We have experiments showing that agents at least can learn from the environment by overfitting on train. But we do not yet have full post train runs, mainly due to time. But follow our blog/X where we’ll regularly update our research

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#34

Post by hmokiguess » Wed, Aug 05, 2026, 3:47 PM UTC

RuiWang0811 wrote: post #31

hmokiguess wrote: post #30

Earlier quoted context omitted.

Right, that's quant trading, that's not this business. Enhancing their research seems like they are your customer and you would be eating from their margin. How would you sell to them, you would deliver what? Faster time to decision? Wouldn't quants be your competition, given their work is building tools like this one?

No we sell our own research to AI labs as RL envs. Realistic RL envs grows in demand as labs seek better data train better models. It’s a complimentary business. Simply put: we sell envs to labs, labs make better models, firms buy these models to make more profit. Everybody wins. Yeah a competitor for us would be fellow quants doing the same thing. But even then every quant firm trades differently (and good ones all…

So what's an example today of "envs" like yours that these firms buy and how you differ from them? Why you?

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#35

Post by jjallen » Wed, Aug 05, 2026, 3:54 PM UTC

RuiWang0811 wrote: post #10

jjallen wrote: post #8

Earlier quoted context omitted.

I looked through the transcript/output of the model/run linked but didn't find anything that showed much, if any, alpha. Maybe I missed it?

not sure about your background, the trace shows the feature engineering the LLMs did

The comment in the parent said "kind alphas the agent found". It linked to a job then a trial. All of the comments I read there except for one said things like "The final alpha check is still fitting; the prior lagged backtest’s exact zero metrics make clear that model was not acceptable economically". One said "successful backtest’s" but did not expound on what that means or anything. I was looking for the alpha it found and not the feature engineering.

My backgroud is in finance but do not look at things so quantitatively.

Here is another comment/output: "correlation −0.007 and directional accuracy 0.498". Wouldn't directional accuracy have to be greater than .50 to be profitable?

Forgive my ignorance I am interested in this though. I have asked Claude/ChatGPT to show me where the alpha is that the model found as well so I can learn.

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#36

Post by jjallen » Wed, Aug 05, 2026, 3:59 PM UTC

jjallen wrote: post #35

RuiWang0811 wrote: post #10

Earlier quoted context omitted.

not sure about your background, the trace shows the feature engineering the LLMs did

The comment in the parent said "kind alphas the agent found". It linked to a job then a trial. All of the comments I read there except for one said things like "The final alpha check is still fitting; the prior lagged backtest’s exact zero metrics make clear that model was not acceptable economically". One said "successful backtest’s" but did not expound on what that means or anything. I was looking for the alpha it…

Spent more time looking at this because I was still interested in the alpha it found and found this:

"cumulative_after_cost_return": -0.004003033519454746"

https://hub.harborframework.com/jobs/af0299f9-a3bb-44ea-8ced...

¯\(ツ)/¯

Re: Launch HN: EdotEnv (YC S26) – Quant Trading RL Envs to Teach LLMs Research

#37

Post by RuiWang0811 » Wed, Aug 05, 2026, 4:58 PM UTC

hmokiguess wrote: post #34

RuiWang0811 wrote: post #31

Earlier quoted context omitted.

No we sell our own research to AI labs as RL envs. Realistic RL envs grows in demand as labs seek better data train better models. It’s a complimentary business. Simply put: we sell envs to labs, labs make better models, firms buy these models to make more profit. Everybody wins. Yeah a competitor for us would be fellow quants doing the same thing. But even then every quant firm trades differently (and good ones all…

So what's an example today of "envs" like yours that these firms buy and how you differ from them? Why you?

there are loads of env businesses for coding tasks, enterprise tasks, computer use etc etc. we offer different envs from a niche industry, which just so happens to be a very hard data science task & where the data doesn't saturate. In order to build these you'd need niche expert knowledge.