diff --git a/brainsteam/content/annotations/2023/01/29/1674989272.md b/brainsteam/content/annotations/2023/01/29/1674989272.md
new file mode 100644
index 0000000..37a06d4
--- /dev/null
+++ b/brainsteam/content/annotations/2023/01/29/1674989272.md
@@ -0,0 +1,59 @@
+---
+date: '2023-01-29T10:47:52'
+hypothesis-meta:
+  created: '2023-01-29T10:47:52.638117+00:00'
+  document:
+    title:
+    - 2301.11305.pdf
+  flagged: false
+  group: __world__
+  hidden: false
+  id: YYCjTJ_CEe2thKdVH4ie0A
+  links:
+    html: https://hypothes.is/a/YYCjTJ_CEe2thKdVH4ie0A
+    incontext: https://hyp.is/YYCjTJ_CEe2thKdVH4ie0A/arxiv.org/pdf/2301.11305.pdf
+    json: https://hypothes.is/api/annotations/YYCjTJ_CEe2thKdVH4ie0A
+  permissions:
+    admin:
+    - acct:ravenscroftj@hypothes.is
+    delete:
+    - acct:ravenscroftj@hypothes.is
+    read:
+    - group:__world__
+    update:
+    - acct:ravenscroftj@hypothes.is
+  tags:
+  - chatgpt
+  - detecting gpt
+  target:
+  - selector:
+    - end: 30225
+      start: 30062
+      type: TextPositionSelector
+    - exact: We simulate human re-vision by replacing 5 word spans of the text with
+        samplesfrom T5-3B until r% of the text has been replaced, andreport performance
+        as r varies.
+      prefix: 'n increasingly heavily revised. '
+      suffix: ' Figure 5 shows that De-tectGPT '
+      type: TextQuoteSelector
+    source: https://arxiv.org/pdf/2301.11305.pdf
+  text: I question the trustworthiness of this simulation - human edits are probably
+    going to be more sporadic and random.
+  updated: '2023-01-29T10:47:52.638117+00:00'
+  uri: https://arxiv.org/pdf/2301.11305.pdf
+  user: acct:ravenscroftj@hypothes.is
+  user_info:
+    display_name: James Ravenscroft
+in-reply-to: https://arxiv.org/pdf/2301.11305.pdf
+tags:
+- chatgpt
+- detecting gpt
+- hypothesis
+type: annotation
+url: /annotations/2023/01/29/1674989272
+
+---
+
+
+
+ <blockquote>We simulate human re-vision by replacing 5 word spans of the text with samplesfrom T5-3B until r% of the text has been replaced, andreport performance as r varies.</blockquote>I question the trustworthiness of this simulation - human edits are probably going to be more sporadic and random.
\ No newline at end of file