diff --git a/brainsteam/content/replies/2022/11/23/1669236944.md b/brainsteam/content/replies/2022/11/23/1669236944.md
new file mode 100644
index 0000000..830d4d7
--- /dev/null
+++ b/brainsteam/content/replies/2022/11/23/1669236944.md
@@ -0,0 +1,68 @@
+---
+date: '2022-11-23T20:55:44'
+hypothesis-meta:
+  created: '2022-11-23T20:55:44.414977+00:00'
+  document:
+    title:
+    - 2022.naacl-main.167.pdf
+  flagged: false
+  group: __world__
+  hidden: false
+  id: MrGLumtxEe21b1OADBLmyg
+  links:
+    html: https://hypothes.is/a/MrGLumtxEe21b1OADBLmyg
+    incontext: https://hyp.is/MrGLumtxEe21b1OADBLmyg/aclanthology.org/2022.naacl-main.167.pdf
+    json: https://hypothes.is/api/annotations/MrGLumtxEe21b1OADBLmyg
+  permissions:
+    admin:
+    - acct:ravenscroftj@hypothes.is
+    delete:
+    - acct:ravenscroftj@hypothes.is
+    read:
+    - group:__world__
+    update:
+    - acct:ravenscroftj@hypothes.is
+  tags:
+  - prompt-models
+  - NLProc
+  target:
+  - selector:
+    - end: 20146
+      start: 19539
+      type: TextPositionSelector
+    - exact: Misleading Templates There is no consistent re-lation between the performance
+        of models trainedwith templates that are moderately misleading (e.g.{premise}
+        Can that be paraphrasedas "{hypothesis}"?) vs. templates that areextremely
+        misleading (e.g., {premise} Isthis a sports news? {hypothesis}).T0 (both 3B
+        and 11B) perform better givenmisleading-moderate (Figure 3), ALBERT andT5
+        3B perform better given misleading-extreme(Appendices E and G.4), whereas
+        T5 11B andGPT-3 perform comparably on both sets (Figure 2;also see Table 2
+        for a summary of statisticalsignificances.) Despite a lack of pattern between
+      prefix: structiveand misleading-extreme.
+      suffix: 4 8 16 32 64 128 2560.50.550.60.
+      type: TextQuoteSelector
+    source: https://aclanthology.org/2022.naacl-main.167.pdf
+  text: "Their misleading templates really are misleading \n\n{premise} Can that be\
+    \ paraphrased as \"{hypothesis}\" \n\n{premise} Is this a sports news? {hypothesis}"
+  updated: '2022-11-23T20:55:44.414977+00:00'
+  uri: https://aclanthology.org/2022.naacl-main.167.pdf
+  user: acct:ravenscroftj@hypothes.is
+  user_info:
+    display_name: James Ravenscroft
+in-reply-to: https://aclanthology.org/2022.naacl-main.167.pdf
+tags:
+- prompt-models
+- NLProc
+- hypothesis
+type: reply
+url: /replies/2022/11/23/1669236944
+
+---
+
+
+
+ <blockquote>Misleading Templates There is no consistent re-lation between the performance of models trainedwith templates that are moderately misleading (e.g.{premise} Can that be paraphrasedas "{hypothesis}"?) vs. templates that areextremely misleading (e.g., {premise} Isthis a sports news? {hypothesis}).T0 (both 3B and 11B) perform better givenmisleading-moderate (Figure 3), ALBERT andT5 3B perform better given misleading-extreme(Appendices E and G.4), whereas T5 11B andGPT-3 perform comparably on both sets (Figure 2;also see Table 2 for a summary of statisticalsignificances.) Despite a lack of pattern between</blockquote>Their misleading templates really are misleading 
+
+{premise} Can that be paraphrased as "{hypothesis}" 
+
+{premise} Is this a sports news? {hypothesis}
\ No newline at end of file