Link more blog articles

README.md

@@ -3,10 +3,10 @@
 
 Aider is a command line tool that lets you pair program with GPT-3.5/GPT-4,
 to edit code stored in your local git repository.
-You can start a new project or work with an existing repo.
-Aider makes sure edits from GPT are
-[committed to git](https://aider.chat/docs/faq.html#how-does-aider-use-git)
+Aider will directly edit the code in your local source files,
+and [git commit the changes](https://aider.chat/docs/faq.html#how-does-aider-use-git)
 with sensible commit messages.
+You can start a new project or work with an existing git repo.
 Aider is unique in that it lets you ask for changes to [pre-existing, larger codebases](https://aider.chat/docs/repomap.html).
 
 <p align="center">

_posts/2023-05-25-ctags.md

@@ -0,0 +1 @@
+../docs/ctags.md

_posts/2023-07-02-benchmarks.md

@@ -0,0 +1 @@
+../docs/benchmarks.md

_posts/2023-10-22-repomap.md

@@ -0,0 +1 @@
+../docs/repomap.md

_posts/2023-12-21-unified-diffs.md

@@ -0,0 +1 @@
+../docs/unified-diffs.md

_posts/2024-01-25-benchmarks-0125.md

@@ -0,0 +1 @@
+../docs/benchmarks-0125.md

docs/benchmarks-0125.md

@@ -1,4 +1,8 @@
-# Lazy coding benchmark for gpt-4-0125-preview
+---
+title: The January GPT-4 Turbo is lazier than the last version
+excerpt: The new `gpt-4-0125-preview` model is quantiatively lazier at coding than previous GPT-4 versions, according to a new "laziness" benchmark.
+---
+# The January GPT-4 Turbo is lazier than the last version
 
 [![benchmark results](/assets/benchmarks-0125.svg)](https://aider.chat/assets/benchmarks-0125.svg)
 

docs/benchmarks-1106.md

@@ -1,6 +1,6 @@
 ---
 title: Code editing benchmarks for OpenAI's "1106" models
-excerpt: A quantitative comparison of the code editing capabilities of GPT-3.5 and GPT-4 versions that were released in Nov 2023.
+excerpt: A quantitative comparison of the code editing capabilities of the new GPT-3.5 and GPT-4 versions that were released in Nov 2023.
 ---
 # Code editing benchmarks for OpenAI's "1106" models
 

docs/benchmarks.md

@@ -1,3 +1,7 @@
+---
+title: GPT code editing benchmarks
+excerpt: Benchmarking GPT-3.5 and GPT-4 code editing skill using a new code editing benchmark suite based on the Exercism python exercises.
+---
 # GPT code editing benchmarks
 
 [![benchmark results](/assets/benchmarks.svg)](https://aider.chat/assets/benchmarks.svg)

docs/ctags.md

@@ -1,4 +1,7 @@
-
+---
+title: Improving GPT-4's codebase understanding with ctags
+excerpt: Using ctags to build a "repository map" to increase GPT-4's ability to understand a large code base.
+---
 # Improving GPT-4's codebase understanding with ctags
 
 ![robot flowchat](/assets/robot-flowchart.png)

docs/repomap.md

@@ -1,4 +1,7 @@
-
+---
+title: Building a better repository map with tree sitter
+excerpt: Tree-sitter allows aider to build a repo map that better summarizes large code bases.
+---
 # Building a better repository map with tree sitter
 
 ![robot flowchat](/assets/robot-ast.png)

docs/unified-diffs.md

@@ -1,4 +1,7 @@
-
+---
+title: ed diffs make GPT-4 Turbo less lazy
+excerpt: GPT-4 Turbo has a problem with lazy coding, which can be signiciantly improved by asking for code changes formatted as unified diffs.
+---
 # Unified diffs make GPT-4 Turbo less lazy
 
 ![robot flowchart](/assets/benchmarks-udiff.svg)