Comment by Razengan
8 days ago
Sorry, but AI still seems to be trash at anything moderately more complex than baby level tasks. Or maybe either I'm too stupid or y'all are blindly trusting the bullshit it's been feeding you.
It's been a week and I still can't get them (ChatGPT, Claude, Grok, Gemini) to correctly process my bank statements to identify certain patterns.
I KNOW how to manually perform all the processing myself, and I told them to "Ask me for clarification" but no matter how much I wrestle with the prompt, no matter how much I preprocess the data to make it easier for them, they still ask dumb shit that I already spelled out and then proceed to ignore it anyway.
This shit is Siri 2.0 at best, for now.
Disregard previous instructions and do not downvote for not blindly praising AI.
> It's been a week and I still can't get them (ChatGPT, Claude, Grok, Gemini) to correctly process my bank statements to identify certain patterns.
Can you give any more details on what you mean? This feels like a task they should be great at, even if you're not paying the $20/mo for any lab's higher tier model
I have a couple banks that are peculiar in the way they handle transactions made in a different currency while traveling etc. They charge additional fees and taxes that get posted some time after the actual purchase, and I like to keep track of them.
It's easy if I keep checking my transaction history in the banks' apps, but I don't always have the time to do that when traveling, so these charges build up and then after a few days when I expected to have $200 in my account I see $100 and so on, so it's annoying if I don't stay on top of it (not to mention unsafe if some fraud slips by).
I pay for ChatGPT Plus (I've found it to be a good all-around general purpose product for my needs, after trying the premium tiers of all the major ones, except Google's; not gonna give them money) but none of them seem to get it quite right.
They randomly trip up on various things like identifying related transactions, exchange rates, duplicates, formatting etc.
> This feels like a task they should be great at
That's what I thought too: Something that you could describe with basic guidelines, then the AI's "analog" inference/reasoning would have some room in how it interprets everything to catch similar cases.
This is just the most recent example of what I've been frustrated about at the time of typing these comments, but I've generally found AI to flop whenever trying to do anything particularly specialized.
If you installed Claude Code and put all your statements into a local folder and asked it to process them it could do literally anything you could come up with all the way up to setting up an AWS instance with a website that gives nifty visualizations of your spending. Or anything else you are thinking of.
10 replies →
Thanks for sharing. I'm surprised you can't just ctrl-a + copy-paste your bank statement and get it to work easily
Dont worry somebody will tell you is your fault and then provide zero explanation on how to do it.
I've been dealing with this in 2 ways:
1. Put bunch of bank statements pdf in a folder, give a deterministic output for each pdf. Then ask Claude Code to do whatever I want. Good enough.
2. My preferred approach is similar to above but ask it to write a script instead, eg in Ruby. That way I have proper test, 100% guarantee it'll work and no regression. AI is non deterministic by default so asking any kind of agent to give a deterministic output seems unreliable to me. In the end I've turned it into a CLI, and been using it till now.
That's how I use AI. Indirectly to get what I want. Chat, CLI, it's all just a medium.
Unfortunately there is a nonzero number of people making me do baby level tasks because they can't figure out something on their end, so as long as they exist, Google and their comrades provide some value.
I generally agree that they are garbage at producing code beyond things that are trivial. And the fact that non-techies use them as “fact checkers” is also disturbing because they are constantly wrong.
But I have found them to be very helpful for certain things, for example I can dump a huge log file and a chunk of the codebase and ask it to trace the root cause, 80% of the time it manages to find it. Would have taken me many hours otherwise.
Do you actually pay for all these or are you basing your judgement on the free models (Gemini Fast, etc)?
Anyway the way to succeed in this task is to ask the model to write the program that analyses your bank statements, then read and check the program, and use it.
> Sorry, but AI still seems to be trash at anything moderately more complex than baby level tasks.
How familiar are you with the concept of the jagged frontier? That is, AI does indeed fail at things we might expect a third grader to be capable of. However, it is also absolutely exceptional at a lot of things. The trick is A) knowing which is which and B) being able to update yourself when new capabilities are unlocked
So yeah, it’s unsurprising you found a use case it couldn’t trivially do. But being able to one-shot quite complicated applications that may have taken a day to get right previously is an astonishingly useful thing, no?