It will certainly help - but its an extremely high bar. Almost all formal verification of software today is "does this pass the typechecker"?.
Now this captures some errors, but it doesn't really capture high level ones (is this program guaranteed to not deadlock is a hard one), and it doesn't capture the one that is important for business purposes (does this do what the customer wants). That requirement is more important than correctness (vitness all the software that is described as "crap", but is nonetheless widely used).
I don't think this is a required key to unlocking vibe coding. That seems to be easy: does this provide business value? And there the answer seems roughly to be "yes".
But accessiblity on the frontend is to a large extend patterns - if it looks like a checkbox it should have the appropriate ARIA tag, and patterns are easy for an LLM.
It's just… a lot of people don't see this on their bottom line. Or any line. My awareness of accessibility issues is the Web Accessibility Initiative and the Apple Developer talks and docs, but I don't think I've ever once been asked to focus on them. If anything, I've had ideas shot down.
What AI does do is make it cheap to fill in gaps. 1500 junior developers for the price of one, if you know how to manage them. But still, even there, they'd only be filling in gaps as well as the nature of those gaps have been documented in text, not the lived experience of people with e.g. limited vision, or limited joint mobility whose fingers won't perform all the usual gestures.
Even without that issue, I'd expect any person with a disability to describe an AI-developed accessibility solution as "slop": because I've had to fix up a real codebase where nobody before me had noticed the FAQ was entirely Bob Ross quotes (the app wasn't about painting, or indeed in English), I absolutely anticipate that a vibe-coded accessibility solution will do something equally weird, perhaps having some equivalent to "As a large language model…" or to hard-code some example data that has nothing to do with the current real value of a widget.
Not only can we not just do that (you did not even define what you mean), but China is coming out with models that are good enough for this purpose - and they are, because they are open, everywhere.
I always travel with my GL.iNet GL-MT3000 (Beryl AX) and this is what I use it for:
- My wife and I travel with multiple devices (laptops, phones, Chromecast...) and when we get to a hotel/Airbnb, I simply connect my Beryl AX to their network (it deals with captive portals btw) and all of our devices automatically connect.
- I changed the `/etc/hosts` directly in the router, meaning I can test my local servers under custom domains easily on my other devices like phones/tablets without apps like SquidMan.
- I route specific domains through specific VPNs. Government websites, streaming websites, AWS services, etc.
- I can plug in a 4G USB modem into it and it can automatically fallback to it if the main connection drops.
Now this captures some errors, but it doesn't really capture high level ones (is this program guaranteed to not deadlock is a hard one), and it doesn't capture the one that is important for business purposes (does this do what the customer wants). That requirement is more important than correctness (vitness all the software that is described as "crap", but is nonetheless widely used).
I don't think this is a required key to unlocking vibe coding. That seems to be easy: does this provide business value? And there the answer seems roughly to be "yes".
reply