Comment by baq
5 days 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)
5 days 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)
> 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.
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.
> the layman won't even know there was a calculator implemented.
That's on company making the agentic harness. Hiding details of what computer does from the user is the original sin of this industry, and subsequent generations of developers and software companies keeps doubling down on it.
(Case in point - I just downloaded the Codex app for Windows, and in the options I see it has two UI modes of operating, one of which is meant for "non coding" and apparently this means hiding the details of what the agent is doing. This is precisely where the layman is betrayed by the tool.)
Yeah, good luck trusting the output!
2 replies →
If your prompt was more complex than "do my taxes", then this is irrelevant.
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.
If you can assume "a sufficiently smart piece of technology" that doesn't exist now, a lot of problems become trivial
2 replies →
> 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).
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.