Hacker News Reader

Being able to weigh the benefits of different places to put money is important too. I had an ex who was big on Ramsey and really wanted to pay down our 1.8% rate mortgage and put "rainy day" money into a savings account that also yielded 1-2%.

I argued that the the first priority should be maintaining a consistent $5k in the main chequing account and calling that the the rainy day money, since doing so would cause us to have a $20/mo service fee waived and we'd avoid the semi-regular NSF feeds we were getting dinged with from preauth utility bill debits.

Monthly interest of 2% on $5k is only about $8 a month; our interest rate would have needed to be 5%+ before it was worth it earning that before first getting the account fee cleared (or, of course, just switching to a bank that offered fee-free chequing accounts).

Untrue - there isn't a personal finance solution that doesn't have mistakes. Not one. I've literally tried them all. Its mostly because the syncing with accounts is very very brittle and a lot of things like stock plans etc aren't supported well so your daily view will always be somewhat off.

There are insights to derive from the data - like how much do you really spend. But again its really hard to get there because the numbers are always off and most people don't actually want to know.

You are severely underestimating the average person's agency with their money.

I wanted to sync accounts some time ago and decided to not do it at all. I lost all track of where what is, how I managed to spend etc.

Writing it down yourself is still the best option for me at this point. I feel on top of things.

I use an app but I also have an excel sheet where I track everything very carefully every week or so.

Trust my excel sheet much much more.

Honestly for everyone I know this is how they do it. There is one guy who built his own app and his is perfect because he has solved for his specific bank accounts.

He knows every $ coming in and going out - its pretty impressive.

Thats awesome!

> hard to disrupt with AI for two reasons: (1) mistakes, hallucinations, etc., aren't acceptable

I think AI hallucination rate is already below my own hallucination rate, especially in a boring/unknown domain

And yet only one is unacceptable for humans reviewing their own expenditures.

I also dont trust an LLM with my finances. At least not for now

I think the lack of friction AI has is a real problem.

AI models output is always overly confident. And when you correct them they will almost always come up with something like "Ah, you're totally right" and switch around the output (unless there are safeguards / deep research involved).

AI doesn't push back, therefore you more often than not don't second guess your own thoughts. This is, in essence, the most valuable tool in discussions with other humans.

You can forgive your own mistakes, but you'll have zero tolerance for a bot making mistakes with your money / on your behalf.

I prefer to also just write it down myself (at least for now)

I don't know how much you can trust this though, given that you might not be able to catch hallucinations exactly in those boring/unknown domains.

There are some databases with spending habits, so you can compare your spending to folks with similar households, and some prudent guidelines. But it's not rocket science and a bit silly. You don't really need to remind sneakerheads they spend more than average on shoes, or pennypinchers that they spend (too?) little.

For most people just keeping tabs of spending helps them reign it in. Setting up auto savings and pension contributions also helps. The next step is using cash to pay for discretionary spending - not more automation.

I'd really like an AI tool with absolute security I can trust to trawl through my emails and reconcile invoices against my bank records.

I'd never trust it

Do you have to trust it? Have the AI built a list of all the invoices it can find in your email then a separate application reconciles that against your statements. The AI might miss something or invent something, but the mismatch list you get back should be short.

It wouldn't be perfect, but maybe it would be better than having to do it all manually.

So I’m doing something like this for a legal case I am dealing with for giggles. AI is absolutely giving me bogus answers that I have to fact check. Not sure I would trust it to reconcile items.

> and with integrity

Good advice except for this. In today’s society you’ll lose 10/10 times to somebody who’s working hard and doesn’t have any integrity. See Sam Altman, Larry Ellison, Elon Musk, Jeff Bezos, etc.

There are always outlier examples, but for most folks, sacrificing integrity too much will come back to bite them -- marital and family problems, divorce, or personal crises that end up eating through money or having ramifications that affect your career performance are the most common examples.

Living with integrity doesn't mean you can't be highly competitive or make emotionally difficult decisions in a professional context. But it does mean avoiding the kind of personal debt that can detonate your life in a way that most people, unlike Musk or Altman, can't truly get away with.

Said differently, taking moral shortcuts in your career might seem to work in isolation, but doing so in all aspects of your life tends to accrue real consequences that compound over time. And most folks who take moral shortcuts aren't capable of constraining that behavior to a single domain of their life over time. It's like an infection that spreads and is hard to control. Add in any kind of latent substance use risk -- common throughout the adult US population in general -- and successful, talented people end up in the second half of their life nowhere near where their financial potential was.

it's the thing that would be easier to automate and use AI. your rationalization would apply to everything. heck the front page have a medical diagnosis slop.

the point is, seen critically, it's obvious that it's not even a replacement for a calculator. yet the hype pushes on with infinite exceptions "oh, its not the best for this that i know about, but everything else I'm not an expert I will clai AI is perfect"

I must admit that I disagree and believe that AI will only be used more as it improves. There is already a big difference between GPT-4 and GPT-5 in terms of hallucinations. If AI can do your tax accounting in 20 seconds with a 95% probability of accuracy (perhaps better than most accountants—after all, who can really understand tax legislation?) and with some clear checksums, who wouldn't use it instead of doing it themselves? In addition, AI is really excellent at inferring meaning from data (and see relations).

In the current AI = LLM world, why have a language model do taxes? Why not just have AI help you adapt your non AI tax planning platform to local tax laws by reading and comprehending them at scale, a language task, instead?

> perhaps

That perhaps is doing a lot of lifting.

Not really. After using GPT-5 extensively I'd easily trust it to do my taxes. I find the output to be very reliable, also my taxes are trivial.

I'm currently doing that. One problem is that it's interpretation of the tax law and instructions are not consistent. My taxes are not trivial.

> I'd easily trust it to do my taxes. I find the output to be very reliable, also my taxes are trivial.

Tax season in the US is in about six months - I look forward to hearing how your experiment goes!

Better idea: the U.S. could adopt the income tax practices of most other countries, where the revenue service tells you what you owe, instead of making you guess. No need for A.I. or Intuit.

That doesn't arbitrarily increase GDP through revenue-through-friction, though.

They will tell you how much you owe, but only if you file incorrectly :P

For Americans, if you didn't know, you can check your IRS transcripts at https://www.irs.gov/ to see exactly how much the IRS thinks you've earned.

Thank you, I didn't know about this and it's great information to have for reference!

Fwiw iirc Intuit has to offer a free version of their tool with the same capabilties but it is so hidden from everybody behind so much stuff that its hard for people to reach there.

Honestly, yes there shouldn't really even be a discussion about this. US should definitely do it. I think US and India are the only two major countries still stuck on something like this and I am not sure if there are really any advantages of it.

For the 95% of people who get all their income from W2/1099 compensation, bank accounts, and brokerage accounts and who either take the standard deduction or whose only itemised deductions are dependents, mortgage interest, and SALT, there's really no need for filing tax returns at all. But the tax accounting and tax software industries lobby to prevent it.

For most folks, filing your taxes is already mostly automated and requires a time investment of maybe 45 to 60 minutes per year. Would it be nice to reduce that down to 20 seconds? Sure, but it's not going to materially change anything in the financial life of most people. I'm all for it if it could be done reliably at scale. Outlier cases where taxation is complicated enough that it's possible to engineer substantial and meaningful financial outcomes often count more as business finance than personal finance. I'm sure artificial intelligence will indeed be more disruptive to business and corporate finance. For true personal finance, though, I suspect it may be more predatory than helpful by selling people into bad decisions that sound smart (which banks, etc., already try to do with so-called financial advisors).

Keep in mind a 5% failure rate would likely be >10 million incorrect tax filings per year solely due to AI errors, not inclusive of additional incorrect filings due to human error as well.

5% odds of screwing up my taxes and going to jail through no fault of my own is a horrible proposition.