> I'd argue back that LLMs likely have a better understanding of a11y conventions than I do as well.

To make the obvious counterargument, “then you shouldn’t be creating websites at all”.

I don’t actually believe this, but I know people who do. Some would add “shouldn’t be allowed to”.

I wonder what went so wrong that "if you don't understand [thing] you shouldn't be building [thing]" is now considered a controversial statement.

▲

mathgeek 3 hours ago | parent | next [-]

If you're building bridges, this shouldn't be a controversial statement. Same if you're building cryptography software.

It's debatable if the same should apply to the vast majority of software that is less critical.

▲

Filligree 2 hours ago | parent | prev | next [-]

Keep in mind these are two different things. Not all websites need to be accessible.

▲

kristianc 3 hours ago | parent | prev | next [-]

That's not what I said, I said I likely understand it less than a 635B parameter LLM, and that using the LLM as a shortcut to that knowledge is something I'd consider perfectly acceptable. I might even become better at it through using the LLM.

	▲	layer8 3 hours ago \| parent [-]
		You need a certain understanding to be able to judge whether the output is adequate. I think the argument is against people who lack that understanding.

▲

fwip 3 hours ago | parent | prev [-]

Well, there's degrees of understanding, as well as degrees of seriousness of the project. You can also learn a lot by building something.

Some people are writing the Netflix homepage (where an outage costs millions of dollars), and some people are writing a blog for three readers.