Live data from Hacker News

AI financial advice is surprisingly good, especially if you ask right questions

mitsloan.mit.edu

101–110 of 443 posts

Re: AI financial advice is surprisingly good, especially if you ask right questions

#101

Earlier quoted context omitted.

Lol. You don't even need AI for that 99% boiler plate. Save 6-12 months of expenses in cash, DCA the rest into total market stock index funds. But people still pay expensive advisors to get worse results.

I mean, never DCA anything that's terrible advice. But still better than what most people do.

If you only have a fixed amount of money to put aside every month, DCA makes sense. That applies to 99% of people. Not terrible at all.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#102

I wonder if telling (or somehow architecturally coaxing) the LLM it has 'skin in the game' will make it more risk-averse? I imagine it does. This makes me wonder too about the entire premise and worthiness of these evals. They orient themselves around normal one-shot interactions with a likely non-sys-prompted model with no built up context or memory of the person. I doubt the mentioned 'job loss' scenario is even co…

The problem I see with this approach is threefold. First, from a technical standpoint the required context window would be massive if you're looking at a person's career/life holistically. Probably solvable, but definitely something to be aware of. Second, privacy goes completely out the window since you're sharing everything. You don't know what's relevant and what's not up front so you need to provide everything. T…

> First, from a technical standpoint the required context window would be massive if you're looking at a person's career/life holistically. Probably solvable, but definitely something to be aware of.

Why would it be massive? The application layer typically compacts a profile of information about the users financial situation when offered. I doubt many of us have financial situations that would exceed the context window.

> Third, you would need a training dataset of all those input variables and their outcomes to be able to provide any sort of useful output. The first set of people to share everything wouldn't be able to derive any value from the tool, and I think you'd be hard pressed to convince enough people to do it to get a useful dataset.

Would you 'need' a training dataset of input variables and their outcomes for an LLM? Certainly for traditional ML, but the LLM toolcalling can simulate what an astute user should statistically do in their situation based on information on the internet and reason about the different constraints.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#103

Earlier quoted context omitted.

Lol. You don't even need AI for that 99% boiler plate. Save 6-12 months of expenses in cash, DCA the rest into total market stock index funds. But people still pay expensive advisors to get worse results.

I mean, never DCA anything that's terrible advice. But still better than what most people do.

DCA is not unreasonable advice given that most people's greatest enemy is themselves. DCA helps avoid the very emotionally upsetting feeling of you throwing money into a fund and it dropping 5% the next day. This emotional volatility can push people to make bad decisions (pull all their money out, try to time the market, stop investing, etc.). Scheduling your investment into smaller sums lets you diffuse the highs and lows in order to keep you steadfast.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#104

People in this thread are massively underestimating the level of financial illiteracy in the general population. We've had multiple people try to convince us to set up bank accounts for our kids, so that they could accumulate interest over 18 years. More that tried to convince me to gamble on random pump and dump shitcoins. More still that talked about "investing" in random collectables like Funko Pops or Pokemon car…

What’s wrong with bank accounts for your kids? Sorry, this one doesn’t seem to fit with your other examples.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#105

I wonder if telling (or somehow architecturally coaxing) the LLM it has 'skin in the game' will make it more risk-averse? I imagine it does. This makes me wonder too about the entire premise and worthiness of these evals. They orient themselves around normal one-shot interactions with a likely non-sys-prompted model with no built up context or memory of the person. I doubt the mentioned 'job loss' scenario is even co…

You wouldn't need history. You can probably build a flowchart choose-your-own-adventure that gives good financial advice, and then have an LLM hold the user's hand through that flowchart.

Like, do you have $1,000 in an emergency fund? No? Start there.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#106

Earlier quoted context omitted.

I don't know why you're being downvoted here. A huge amount of 'financial advice' boils down to 'stop being poor,' which is to say it's about what to do with your economic surplus rather than what to do if you don't have one and aren't long on avocado toast.

I didn't downvote them, but I am genuinely curious to hear from people who "can't save money", and try to understand why that's the case. My assumption is that a large percent of them are spending way more than they need to, but that could easily be an incorrect stereotype.

No offense, but: you need to get out of the house more. It'll answer your question very quickly.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#107
post #104

People in this thread are massively underestimating the level of financial illiteracy in the general population. We've had multiple people try to convince us to set up bank accounts for our kids, so that they could accumulate interest over 18 years. More that tried to convince me to gamble on random pump and dump shitcoins. More still that talked about "investing" in random collectables like Funko Pops or Pokemon car…

What’s wrong with bank accounts for your kids? Sorry, this one doesn’t seem to fit with your other examples.

Bank account interest is pretty much always less than inflation. So, money sitting in a bank account for 18 years is just losing value.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#108
post #104

People in this thread are massively underestimating the level of financial illiteracy in the general population. We've had multiple people try to convince us to set up bank accounts for our kids, so that they could accumulate interest over 18 years. More that tried to convince me to gamble on random pump and dump shitcoins. More still that talked about "investing" in random collectables like Funko Pops or Pokemon car…

What’s wrong with bank accounts for your kids? Sorry, this one doesn’t seem to fit with your other examples.

The interest rate is very low.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#109

People in this thread are massively underestimating the level of financial illiteracy in the general population. We've had multiple people try to convince us to set up bank accounts for our kids, so that they could accumulate interest over 18 years. More that tried to convince me to gamble on random pump and dump shitcoins. More still that talked about "investing" in random collectables like Funko Pops or Pokemon car…

“Pay your bills on time and fully”

“Do what you can to eliminate addictive vices or never get them”

“Max your Roth and 401k contributions before even thinking about anything else”

“Try to budget”

“Don’t live beyond your means. Monthly payment need to be considered carefully”

If you can even TRY to do these things it puts you SO far ahead of the average person.

It sucks because I get it, if you’re behind waiting years for things to stabilize sucks, if you even can. So these get rich quick by just doing X scams are enticing but only set you farther behind.

God I still remember when a friend showed up on his 18th birthday with a pack of cigarettes to show how “mature” he was. I always think about how much that one decision cost him over the years.

Re: AI financial advice is surprisingly good, especially if you ask right questions

#110
post #104

People in this thread are massively underestimating the level of financial illiteracy in the general population. We've had multiple people try to convince us to set up bank accounts for our kids, so that they could accumulate interest over 18 years. More that tried to convince me to gamble on random pump and dump shitcoins. More still that talked about "investing" in random collectables like Funko Pops or Pokemon car…

What’s wrong with bank accounts for your kids? Sorry, this one doesn’t seem to fit with your other examples.

If all you're doing with a bunch of cash over 18 years (!) is holding it in a bank account to collect interest, you're just losing money to inflation. Bank interest is almost nothing. Better to hold stocks, or at the very least bonds if you're extremely risk-averse.

Though this needs to be put in context - maybe you actually intend for the child to be permitted to spend the cash, in which case a bank account makes plenty of sense.

Post reply on HN