-[TODO—
- * Given that sex-category information is _in fact_ being transfered, the "Pronouns are Ryphnol" lady has a point
- * To relate this to Yudkowsky's specialty And preferred pronouns have the same function as the typographic attacks in the multimodal-neurons paper
- * the people aligning language models should understand this
-]
+[TODO: Kerr suggests misgendering as an exercise]
+
+[TODO: Contrary to Yudkowskys' claims about lies, Kerr _isn't_ claiming that pronouns can be "lies"; the article is _very_ explicit about this; Yudkowsky is obviously completely unfamiliar with his opponents' arguments]
+
+[TODO: let's related this to Yudkowsky's specialty multimodal neurons— both CLIP and biological neurons respond to text/images; typographic attacks are the same thing as pronoun badges; you would expect the people aligning language models to be able to think these thoughts]
+
+Given this multitude of reasons why the _existing_ meanings of gendered pronouns are relevant to the question of pronoun reform, what is Yudkowsky's response?
+
+Apparently, to play dumb. [TODO: flesh out the original "Oliver" example] In the comments of the Facebook post, Yudkowsky claims:
+
+> I do not know what it feels like from the inside to feel like a pronoun is attached to something in your head much more firmly than "doesn't look like an Oliver" is attached to something in your head.