iceman_w

Yeah, when you connect to robinhood, this platform gets access to your Agent account only, not your regular brokerage account.

We are planning to add crypto and prediction markets soon!

1. We get it from yahoo finance for paper trading and Robinhood for users who connect their robinhood account for real trading.

2. You can configure agents to run every 1, every 4 hours, every day or every 3 days.

3. There's a few presets we have. You can check the leaderboard to see how they are doing.

What you are observing is relativistic aberration. W does make your velocity increase in the forward direction.

RL constrains the space of possible output token sequences to what is likely to lead to the correct answer. So we are inherently making a trade-off to reduce variance. A non-RL model will have higher variance, so given enough attempts, it will come up with some correct answers that an RL model can't.

I always thought that the point of instruction tuning and ability to use prompts to get the model to do 0 shot tasks was that you don't have to collect tons of example data/samples. The method proposed here requires you to have tons of data. If you have that, why not just fine tune the underlying model?

Thanks! The data is collected by continuously scraping the startup's website and their YC page.

Nope. I didn't know about the Gnutella Network when I posted this. I've changed the name since but HN doesn't allow editing posts.