“Following the recent discussion, we have strengthened our safeguards,” [OKA's] Zimmerman told me. “We are now rolling out a second, independent LLM review step. Translators must run the completed draft through a separate model using a dedicated comparison prompt designed to identify potential discrepancies, omissions, or inaccuracies relative to the source text. Initial findings suggest this is highly effective at detecting potential issues.”
Ah yes; when LLMs don't work, just add more LLMs. Genius.
They say it's been “highly effective” but somehow, I doubt that.

Also reading through the post linked at the end that has more details, this proposal actually seems pretty well-designed. Most importantly, it's very easy to use, and that's important for accessibility features (otherwise no one will put these attributes on their websites).
Looking forward to being able to use this, but it's probably going to take a while for it to be accepted and implemented across browsers. Not sure what the process for that actually looks like.