check in

[Ultimately_Untrue_Thought.git] / content / drafts / a-hill-of-validity-in-defense-of-meaning.md

diff --git a/content/drafts/a-hill-of-validity-in-defense-of-meaning.md b/content/drafts/a-hill-of-validity-in-defense-of-meaning.md
index fdc264f..9a92d5e 100644 (file)
--- a/content/drafts/a-hill-of-validity-in-defense-of-meaning.md
+++ b/content/drafts/a-hill-of-validity-in-defense-of-meaning.md
@@ -320,3 +320,9 @@ As far as I can tell, Professor, I'm just doing what _you_ taught me—carve rea
 > decision-theoretically, it's also not their fault. They were all following a strategy that was perfectly reasonable until they ran into someone with an anomalously high insistence that words should mean things
 
 Sure: everyone in a conflict thinks they're acting defensively against aggressors infringing on their rights, because in the cases where everyone agrees what the "actual" property rights are, there's no conflict.
+
+typographic attack: https://openai.com/blog/multimodal-neurons/
+
+https://distill.pub/2021/multimodal-neurons/
+> These neurons detect gender^10
+> Footnote: By this, we mean both that it responds to people presenting as this gender, as well as that it responds to concepts associated with that gender.