Merge branch 'main' into read-write-changes

_layouts/default.html

@@ -6,10 +6,11 @@
     {% seo %}
     {% if page.highlight_image %}
     <meta property="og:image" content="{{ site.url }}{{ page.highlight_image }}">
+    <meta property="twitter:image" content="{{ site.url }}{{ page.highlight_image }}">
     {% else %}
     <meta property="og:image" content="{{ site.url }}/assets/aider.jpg">
+    <meta property="twitter:image" content="{{ site.url }}/assets/aider-square.jpg">
     {% endif %}
-<meta property="twitter:image" content="{{ site.url }}/assets/aider-square.jpg">
     <link rel="preconnect" href="https://fonts.gstatic.com">
     <link rel="preload" href="https://fonts.googleapis.com/css?family=Open+Sans:400,700&display=swap" as="style" type="text/css" crossorigin>
     <meta name="viewport" content="width=device-width, initial-scale=1">

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

@@ -1,7 +1,7 @@
 ---
 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.svg
+highlight_image: /assets/2024-03-07-claude-3.jpg
 ---
 # Claude 3 beats GPT-4 on Aider's code editing benchmark
 

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

@@ -1,7 +1,7 @@
 ---
 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.svg
+highlight_image: /assets/2024-04-09-gpt-4-turbo-laziness.jpg
 ---
 # GPT-4 Turbo with Vision is a step backwards for coding
 

docs/benchmarks-0125.md

@@ -1,7 +1,7 @@
 ---
 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.
-highlight_image: /assets/benchmarks-0125.svg
+highlight_image: /assets/benchmarks-0125.jpg
 ---
 # The January GPT-4 Turbo is lazier than the last version
 

docs/benchmarks-1106.md

@@ -1,7 +1,7 @@
 ---
 title: Code editing benchmarks for OpenAI's "1106" models
 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.
-highlight_image: /assets/benchmarks-1106.svg
+highlight_image: /assets/benchmarks-1106.jpg
 ---
 # Code editing benchmarks for OpenAI's "1106" models
 

docs/benchmarks-speed-1106.md

@@ -2,7 +2,7 @@
 title: Speed benchmarks of GPT-4 Turbo and gpt-3.5-turbo-1106
 excerpt: This report provides a detailed comparison of the speed of GPT-4 Turbo and gpt-3.5-turbo-1106 models based on the aider benchmarking suite.
 canonical_url: https://aider.chat/2023/11/06/benchmarks-speed-1106.html
-highlight_image: /assets/benchmarks-speed-1106.svg
+highlight_image: /assets/benchmarks-speed-1106.jpg
 ---
 # Speed benchmarks of GPT-4 Turbo and gpt-3.5-turbo-1106
 

docs/benchmarks.md

@@ -1,7 +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.
-highlight_image: /assets/benchmarks.svg
+highlight_image: /assets/benchmarks.jpg
 ---
 # GPT code editing benchmarks
 

docs/unified-diffs.md

@@ -1,7 +1,7 @@
 ---
 title: Unified diffs make GPT-4 Turbo 3X 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.
-highlight_image: /assets/benchmarks-udiff.svg
+highlight_image: /assets/benchmarks-udiff.jpg
 ---
 # Unified diffs make GPT-4 Turbo 3X less lazy