diff --git a/README.md b/README.md
index cfbe2f2ba..60278b97c 100644
--- a/README.md
+++ b/README.md
@@ -35,7 +35,7 @@ Aider is unique in that it lets you ask for changes to [pre-existing, larger cod
 
 Aider supports OpenAI's new GPT-4 model that has the massive 128k context window.
 Benchmark results indicate that it is
-[very fast](https://aider.chat/docs/benchmarks-speed-1106.html),
+[very fast](https://aider.chat/2023/11/06/benchmarks-speed-1106.html),
 and a bit [better at coding](https://aider.chat/docs/benchmarks-1106.html) than previous GPT-4 models.
 
 Aider now supports a [unified diff editing format, which reduces GPT-4 Turbo's "lazy" coding](https://aider.chat/docs/unified-diffs.html).
diff --git a/docs/benchmarks-speed-1106.md b/_posts/2023-11-06-benchmarks-speed-1106.md
similarity index 94%
rename from docs/benchmarks-speed-1106.md
rename to _posts/2023-11-06-benchmarks-speed-1106.md
index d68ed6656..f349cbfac 100644
--- a/docs/benchmarks-speed-1106.md
+++ b/_posts/2023-11-06-benchmarks-speed-1106.md
@@ -1,3 +1,8 @@
+---
+title: Speed benchmarks of GPT-4 Turbo and gpt-3.5-turbo-1106
+redirect_from:
+  - /docs/benchmarks-speed-1106.md
+---
 # Speed benchmarks of GPT-4 Turbo and gpt-3.5-turbo-1106
 
 [![benchmark results](../assets/benchmarks-speed-1106.svg)](https://aider.chat/assets/benchmarks-speed-1106.svg)
diff --git a/_posts/2024-02-11-aider-20.md b/_posts/2024-02-11-aider-20.md
deleted file mode 100644
index a77d78091..000000000
--- a/_posts/2024-02-11-aider-20.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-title: Aider v0.20 title
-redirect_from:
-  - /docs/aider-20.html
----
-
-# Aider v0.20.0 is live
-
-Aider v0.20.0 is now available in pypi.
diff --git a/_posts/2024-02-11-hello-world.md b/_posts/2024-02-11-hello-world.md
deleted file mode 100644
index 1f4966bf7..000000000
--- a/_posts/2024-02-11-hello-world.md
+++ /dev/null
@@ -1,8 +0,0 @@
----
-layout: post
-title:  "Welcome to the aider blog"
----
-
-# Welcome
-
-**Hello world**, this is my first Aider blog post.
diff --git a/docs/benchmarks-1106.md b/docs/benchmarks-1106.md
index c8243ec1f..0859a4219 100644
--- a/docs/benchmarks-1106.md
+++ b/docs/benchmarks-1106.md
@@ -73,7 +73,7 @@ You can review the other reports
 for additional information:
 
 - [GPT code editing benchmarks](https://aider.chat/docs/benchmarks.html) evaluates the March and June versions of GPT-3.5 and GPT-4.
-- [Code editing speed benchmarks for OpenAI's "1106" models](https://aider.chat/docs/benchmarks-speed-1106.html) compares the performance of the new GPT models.
+- [Code editing speed benchmarks for OpenAI's "1106" models](https://aider.chat/2023/11/06/benchmarks-speed-1106.html) compares the performance of the new GPT models.
 
 
 ## Updates