Show HN: I built an AI agent that helps me invest

Re:Show HN: I built an AI agent that helps me invest by kqr on Monday July 21, 2025 @10:09AM (#44635292)

I'm going to assume this project is at best a few years old, so return over index is more likely to be an indicator of overbetting (taking on too much risk) than a performance indicator.

Backtesting would be more useful. Of course, LLMs cannot be backtested since they know the past.

This system is impossible to test. I would be hesitant to trust it.

[ Parent | on HN ]

Re:Show HN: I built an AI agent that helps me invest by tmaly on Monday July 21, 2025 @12:01PM (#44636793)

it looks like the code was committed a week ago. I do not see an iterative history on the code

[ Parent | on HN ]

Re:Show HN: I built an AI agent that helps me invest by TuringNYC on Monday July 21, 2025 @10:15AM (#44635367)

>> I'm going to assume this project is at best a few years old, so return over index is more likely to be an indicator of overbetting (taking on too much risk) than a performance indicator.

Best metric here would be a Sharpe Ratio and drawdown details. https://en.wikipedia.org/wiki/Sharpe_ratio

> This system is impossible to test. I would be hesitant to trust it.

Disagree. Best test would be a paper test going forward, audited by a common platform.

[ Parent | on HN ]

Re:Show HN: I built an AI agent that helps me invest by kqr on Monday July 21, 2025 @10:32AM (#44635567)

Any forward test depends on market assumptions. I'm not a practitioner, and as a layperson I wouldn't know whose assumptions to trust.

[ Parent | on HN ]