logoalt Hacker News

linsomniactoday at 1:40 AM3 repliesview on HN

It depends on how easily testable the Excel is. If Claude has the ability to run both the Excel and the Python with different inputs, and check the outputs, it's stunningly likely to be able to one-shot it.


Replies

AlotOfReadingtoday at 1:48 AM

Something being simultaneously described as a "30 sheet, mind-numbingly complex Excel model" and "testable" seems somewhat unlikely, even before we get into whether Claude will be able to test such a thing before it runs into context length issues. I've seen Claude hallucinate running test suites before.

show 1 reply
martinaldtoday at 1:43 AM

That's exactly what it did (author here).

show 1 reply
datsci_est_2015today at 3:14 AM

And also - who understands the system now? Does anyone know Python at this shop? Is it someone’s implicit duty to now learn Python, or is the LLM now the de facto interface for modifying the system?

When shit hits the fan and execs need answers yesterday, will they jump to using the LLM to probabilistically make modifications to the system, or will they admit it was a mistake and pull Excel back up to deterministically make modifications the way they know how?