Remix.run Logo
baq 7 hours ago

> Or at "do my taxes"?

codex did my taxes this year (well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough)

William_BB 6 hours ago | parent | next [-]

> well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough

You can't seriously believe laymen will try to implement their own tax calculators.

baq 6 hours ago | parent [-]

of course not.

what I believe is that laymen will put all their tax docs into codex and tell it to 'do their taxes' and the tool will decide to implement the calculator, do the taxes and present only the final numbers. the layman won't even know there was a calculator implemented.

William_BB 6 hours ago | parent [-]

Yeah, good luck trusting the output!

baq 5 hours ago | parent [-]

check back in a couple of years!

William_BB 5 hours ago | parent [-]

Ah right! Reminds me of AGI by 2025 :D

tsimionescu 6 hours ago | parent | prev | next [-]

If your prompt was more complex than "do my taxes", then this is irrelevant.

baq 6 hours ago | parent [-]

it was many hours of working with codex, guidance and comparing to known-good outputs from previous years, but a sufficiently smart model would be able to just do it without any steering; it'd still take hours, but my input wouldn't be necessary. a harness for getting this done probably exists today, gastown perhaps or something that the frontier labs are sitting on.

troupo 5 hours ago | parent [-]

> but a sufficiently smart model would be able to just do it without any steering;

Yeah, yeah, we've heard "our models will be doing everything" for close to three years now.

> a harness for getting this done probably exists today, gastown perhaps

That got a chuckle and a facepalm out of me. I would at least consider you half-serious if you said "openclaw", at least those people pretend to be attempting to automate their lives through LLMs (with zero tangible results, and with zero results available to non-tech people).

ravenstine 5 hours ago | parent | prev [-]

Sounds fascinating! If you wrote an article on this I bet it'd have a good shot at making it to the home page of HN.