Comment by grey-area
4 hours ago
Translating from one language/platform to another is something AI is very very good at, so this sounds like a good use of it, bonus points if they create a comprehensive test suite first.
Yes it will lead to new bugs, but the older code probably contains a ton of bugs already and is probably difficult to update (original writers long gone, docs out of date etc), so this is probably the best way out of that situation, as long as proper support is given afterwards so they don't end up in the same situation a year later (this is the hard bit).
The ra-ra commentary from the CEO is somewhat off-putting, but the idea is not all bad.
Problem with legacy code is that with time some of the bugs have become features without users even knowing it or remembering it.
Yeah you can not deploy this to customers with the hardware already in production if it mass fixes bugs and improves behavior because those are likely breaking changes.
They have to modernize the code while keeping all weird edge case behaviour. I think this can be done. And I suspect that is probably the request.
The issue is deciding what is weird edge case behavior and what are bugs. It can be a fine line.
https://lawsofsoftwareengineering.com/laws/hyrums-law/
Every bug is someone else's workflow: https://xkcd.com/1172/
Also, extensive commenting inside codebases is useful documentation, incl. these kinds of incidents. Good code documents the how, but not why. Comments shall also include the "why" where applicable.
As good as it is, we saw a lot of problems with these translations as the code was rewritten without understanding. I remember a security issue where a runtime went from single threaded to multithreaded for example.
Testing is still the long pull, even if you have an engineer with good expertise.
Yes sure, it's not a panacea, but this is a use-case for which AI is quite suited. I'm not a huge fan of using to write without human intervention, so personally I'd want a lot of human involvement...
"as the code was rewritten without understanding."
good thing they have unlimited token, now they would have 5 different model reviewing the work