[nlh]

I discovered something like this in real-world usage. I’ve have GitHub Copilot running in VSCode and I’ve been experimenting with how it works when doing plain text accounting (using ledger / hledger).

The ledger files are somewhat “code”-like so it’s been super interesting to see how it works. The short answer: it works really quite well! ..except for the math part :)

I have a long ledger of transactions, and I can now give Copilot a comment like: “Jan 1, 2022 +100 from consulting income” and it (GPT-3) will generate a nearly perfect ledger entry, debiting from income and crediting the right bank account.

But the arithmetic is always wrong (ledger has an option for you to keep a running balance as a check). There’s the occasional moment where it gets the balance adjustment correct, but almost every time the results are similar to this post.

[supermdguy]

I also have Copilot running, and I was surprised when it had pretty good autosuggestions when writing proofs in Latex! A lot of times it has subtle logical errors in the proof, but the syntax is always correct. And there have been a few times when it gives a sentence or two that's exactly right