181–190 of 192 posts
I don’t understand this constant fascination with having language models trade stocks. Language models are very useful tools but not aligned at all with generating alpha.
The usual question: what's "aligned with generating alpha" that a human stock trader can do, but an ai can't?
Earlier quoted context omitted.
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").
Earlier quoted context omitted.
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!
Earlier quoted context omitted.
The only way to win is to not play. https://www.bogleheads.org/wiki/Getting_started
Bogleheads are still playing.
The results from dollar cost averaging into VT or a target date fund for the next 30-50 years is likely superior to gambling on single named securities or options, for the unsophisticated.
Earlier quoted context omitted.
Bogleheads are still playing.
Bogleheads is maximizing potential economic gains from investing in the capital market while minimizing costs from the exposure attempt. The results from dollar cost averaging into VT or a target date fund for the next 30-50 years is likely superior to gambling on single named securities or options, for the unsophisticated.
Outside of FDIC insured cash accounts, the most anti-gambling way to play would be to buy nothing but TIPS. But even those have a (small) risk.
I'm trying to see how this could be net positive.
One lens to view PFOF is that it connects the most sophisticated traders (HFTs, etc.) with the least sophisticated traders (retail).
Inventing a new, even less sophisticated class of traders seems like exactly the kind of thing that makes sense for their business model.