Comment by Biologist123 | Hacker News Reader

Comment by Biologist123 | Hacker News Reader

Parent Full thread

I run an operation which provides an open source loan tracking tool. I had a play with ChatGPT 4.0 to see if it could recreate its functionality using a natural language interface rather than our current UX.

I fed ChatGPT a bunch of dummy savings and loans transactions and then asked it to compile loan tables for named borrowers.

It worked and I was impressed. For me, this felt like a move from programming to curation. I give the AI the data, and it organizes it for me and outputs it according to what I ask for.

I appreciate there is higher order programming, but for simple needs like the one I described, maybe this is not the beginning of the end for programming, but at least the end of the beginning.

Did you verify each and every cell of data?

LLMs are concerned with mimicking language and appearance as best they can. You don't know if it's just packaging up a bunch of numbers and a table that looks pretty plausible or if it's actually using some sort of formatting scheme and applying it while strictly preserving the numbers.

And that's part of the inherent problems of AI. It's a black box. You don't know if it's calculating some final report that thinks you want with the numbers it thinks you want or if it's actually applying a constant process to all the numbers, cells and columns of the of the report.

I suppose perhaps if the LLM could provide some sort of processing chain information to you, maybe that would work to alleviate any concerns

No, didn’t do a thorough check. Will do it again and report back!

As the parent comment says, LLMs are very good at giving plausible answers. Without checking each cell, then the data you eventually output becomes suspect.

We've been trying to solve this problem at Leaptable (https://leaptable.co/). The crux is that while LLMs are still a black box, transparency in the way AI Agents interact with LLMs is key. For instance, seeing the outputs of each step in a chain-of-thought sequence helps debug common fallacies in the way the LLMs reason and built trust.

https://github.com/peterwnjenga/leaptable

Reply on news.ycombinator.com