I'm very bullish on LLMs being able to invest in the market well, as long as proper safeguards are there.
Robinhood agentic accounts is an amazing idea but you can't really automate stuff that can run on its own. Different companies have different ways for setting up automation which most retail traders are not aware of.
Agency fixes a lot of this. It's a Mac OS app that keeps your account on your device, and lets you build agents that can run on their own every day to manage a sleeve of your cash.
who is actually accountable when the agent misreads a filled order and closes the wrong position, the agent framework or the person who approved the trading permission
1) I think as agents get better, the probability that this happens becomes low.
2) I hate saying this tbh, but Robinhood is very clear that any mistake in the account is user's responsibility.
The only thing I can do on our end as we build this is make sure all context is there for the model to not make such decisions, there are software based safeguards, etc.
It'll take some time but I think as long as there's good context and guardrails, you can really prevent a lot of bad stuff from happening.
I'm very bullish on LLMs being able to invest in the market well, as long as proper safeguards are there.
Robinhood agentic accounts is an amazing idea but you can't really automate stuff that can run on its own. Different companies have different ways for setting up automation which most retail traders are not aware of.
Agency fixes a lot of this. It's a Mac OS app that keeps your account on your device, and lets you build agents that can run on their own every day to manage a sleeve of your cash.
who is actually accountable when the agent misreads a filled order and closes the wrong position, the agent framework or the person who approved the trading permission
I get this a lot.
1) I think as agents get better, the probability that this happens becomes low. 2) I hate saying this tbh, but Robinhood is very clear that any mistake in the account is user's responsibility.
The only thing I can do on our end as we build this is make sure all context is there for the model to not make such decisions, there are software based safeguards, etc.
It'll take some time but I think as long as there's good context and guardrails, you can really prevent a lot of bad stuff from happening.