Comment by trollbridge
10 hours ago
Why not? Given a proper spec, you should absolutely be able to one-shot Excel, particularly if we put it at the level of complexity of, say, Excel 1.0 for Mac.
Current models aren't capable of that, but that doesn't mean it's not possible.
The issue is not the models, the issue is that this method ws tried before, and humans suck at writing what they want. Developing in small increments allowing feedback was an answer to this issue.
If you made models able to code to long spec, you would be left with the hard issue of having to write them.
An interesting question for me is "can the LLMs predict what humans want?".
Like if you show the LLM a page, can the LLM review the page and then spit out a review that is close to what a human would say about the page?
Yes, my current nightmare is I have a very long queue of specs to write and need to work with non technical staff to help them put in words what it is they actually want.
Software was always that way, though.
Seems like this would be a good time to use this famous quote:
> given the sufficiently smart compiler
For those unaware, this is a similar quote used by compiler proponents. The first full compiler was created in 1957 (+/- 70 years ago) and the "sufficiently smart compiler" never happened, hand written code from the best coders still is faster. Now, that doesn't mean that compilers didn't do the job well enough, we just accepted that 90-95% of the top speed was enough for almost everything.
To the LLM one shotting point, it took 30 (40?) years for compilers to be good enough for the mass market. Caveat early adopter and investor.
Plus what pyrale said.