Adapted content for just the docs

_posts/2024-03-08-claude-3.md

@@ -2,6 +2,7 @@
 title: Claude 3 beats GPT-4 on Aider's code editing benchmark
 excerpt: Claude 3 Opus outperforms all of OpenAI's models on Aider's code editing benchmark, making it the best available model for pair programming with AI.
 highlight_image: /assets/2024-03-07-claude-3.jpg
+nav_exclude: true
 ---
 # Claude 3 beats GPT-4 on Aider's code editing benchmark
 

_posts/2024-04-09-gpt-4-turbo.md

@@ -2,6 +2,7 @@
 title: GPT-4 Turbo with Vision is a step backwards for coding
 excerpt: OpenAI's GPT-4 Turbo with Vision model scores worse on aider's code editing benchmarks than all the previous GPT-4 models. In particular, it seems much more prone to "lazy coding" than the existing GPT-4 Turbo "preview" models.
 highlight_image: /assets/2024-04-09-gpt-4-turbo-laziness.jpg
+nav_exclude: true
 ---
 # GPT-4 Turbo with Vision is a step backwards for coding
 

_posts/2024-05-02-browser.md

@@ -2,6 +2,7 @@
 title: Aider in your browser
 excerpt: Aider has an experimental browser UI, allowing you to collaborate with LLMs on code in your local git repo.
 highlight_image: /assets/browser.jpg
+nav_order: 800
 ---
 # Aider in your browser
 

_posts/2024-05-13-models-over-time.md

@@ -2,6 +2,7 @@
 title: Drawing graphs with aider, GPT-4o and matplotlib
 excerpt: Use GPT-4o to draw graphs with matplotlib, including adjusting styles and making visual changes. You get the graph, but you also get the code in your repo.
 highlight_image: /assets/models-over-time.png
+nav_exclude: true
 ---
 
 ![LLM coding skill over time](/assets/models-over-time.svg)

_posts/2024-05-22-draft.md

@@ -3,6 +3,7 @@ title: A draft post.
 excerpt: With a draft summary.
 highlight_image: /assets/linting.jpg
 draft: true
+nav_exclude: true
 ---
 
 # A draft post

_posts/2024-05-22-linting.md

@@ -2,6 +2,7 @@
 title: Linting code for LLMs with tree-sitter
 excerpt: Aider now lints code after every LLM edit and automatically fixes errors, using tree-sitter and AST-aware code context.
 highlight_image: /assets/linting.jpg
+nav_exclude: true
 ---
 
 [![Linting code](/assets/linting.jpg)](https://aider.chat/assets/linting.jpg)

_posts/2024-05-22-swe-bench-lite.md

@@ -2,6 +2,7 @@
 title: How aider scored SOTA 26.3% on SWE Bench Lite
 excerpt: Aider achieved this result mainly through its existing features that focus on static code analysis, reliable LLM code editing, and pragmatic UX for AI pair programming.
 highlight_image: /assets/swe_bench_lite.jpg
+nav_exclude: true
 ---
 
 # How aider scored SOTA 26.3% on SWE Bench Lite

_posts/2024-05-24-self-assembly.md

@@ -2,6 +2,7 @@
 title: Aider has written 7% of its own code
 excerpt: Aider has written 7% of its own code, via 600+ commits that inserted 4.8K and deleted 1.5K lines of code.
 highlight_image: /assets/self-assembly.jpg
+nav_exclude: true
 ---
 
 # Aider has written 7% of its own code

_posts/2024-06-02-main-swe-bench.md

@@ -2,6 +2,7 @@
 title: Aider is SOTA for both SWE Bench and SWE Bench Lite
 excerpt: Aider sets SOTA for the main SWE Bench, after recently setting SOTA for the Lite version.
 highlight_image: /assets/swe_bench.jpg
+nav_exclude: true
 ---
 
 # Aider is SOTA for both SWE Bench and SWE Bench Lite