diff --git a/README.md b/README.md index 16925c3f6..1611156f8 100644 --- a/README.md +++ b/README.md @@ -70,10 +70,13 @@ So you can bounce back and forth between aider and your editor, to collaborative ## State of the art -Aider has the highest score on the challenging SWE Bench benchmark. +Aider has the highest score on the challenging +[SWE Bench benchmark](https://aider.chat/2024/06/02/main-swe-bench.html).

- aider swe bench + + aider swe bench +

diff --git a/website/_posts/2024-03-08-claude-3.md b/website/_posts/2024-03-08-claude-3.md index 1254dcc91..1c80ecd9f 100644 --- a/website/_posts/2024-03-08-claude-3.md +++ b/website/_posts/2024-03-08-claude-3.md @@ -4,6 +4,10 @@ excerpt: Claude 3 Opus outperforms all of OpenAI's models on Aider's code editin highlight_image: /assets/2024-03-07-claude-3.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Claude 3 beats GPT-4 on Aider's code editing benchmark [![benchmark results](/assets/2024-03-07-claude-3.svg)](https://aider.chat/assets/2024-03-07-claude-3.svg) diff --git a/website/_posts/2024-04-09-gpt-4-turbo.md b/website/_posts/2024-04-09-gpt-4-turbo.md index eb4d07afe..abdfb753c 100644 --- a/website/_posts/2024-04-09-gpt-4-turbo.md +++ b/website/_posts/2024-04-09-gpt-4-turbo.md @@ -4,6 +4,10 @@ excerpt: OpenAI's GPT-4 Turbo with Vision model scores worse on aider's code edi highlight_image: /assets/2024-04-09-gpt-4-turbo-laziness.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # GPT-4 Turbo with Vision is a step backwards for coding [OpenAI just released GPT-4 Turbo with Vision](https://twitter.com/OpenAIDevs/status/1777769463258988634) diff --git a/website/_posts/2024-05-02-browser.md b/website/_posts/2024-05-02-browser.md index 4111d66e6..683cd603f 100644 --- a/website/_posts/2024-05-02-browser.md +++ b/website/_posts/2024-05-02-browser.md @@ -4,6 +4,10 @@ excerpt: Aider has an experimental browser UI, allowing you to collaborate with highlight_image: /assets/browser.jpg nav_order: 800 --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Aider in your browser
diff --git a/website/_posts/2024-05-13-models-over-time.md b/website/_posts/2024-05-13-models-over-time.md index d9397fa41..a30a538c2 100644 --- a/website/_posts/2024-05-13-models-over-time.md +++ b/website/_posts/2024-05-13-models-over-time.md @@ -4,6 +4,9 @@ excerpt: Use GPT-4o to draw graphs with matplotlib, including adjusting styles a highlight_image: /assets/models-over-time.png nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} ![LLM coding skill over time](/assets/models-over-time.svg) diff --git a/website/_posts/2024-05-22-draft.md b/website/_posts/2024-05-22-draft.md index 22b74579c..729b638a5 100644 --- a/website/_posts/2024-05-22-draft.md +++ b/website/_posts/2024-05-22-draft.md @@ -5,6 +5,9 @@ highlight_image: /assets/linting.jpg draft: true nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} # A draft post diff --git a/website/_posts/2024-05-22-linting.md b/website/_posts/2024-05-22-linting.md index e6640ec2e..04a0a131f 100644 --- a/website/_posts/2024-05-22-linting.md +++ b/website/_posts/2024-05-22-linting.md @@ -4,6 +4,9 @@ excerpt: Aider now lints code after every LLM edit and automatically fixes error highlight_image: /assets/linting.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} [![Linting code](/assets/linting.jpg)](https://aider.chat/assets/linting.jpg) diff --git a/website/_posts/2024-05-22-swe-bench-lite.md b/website/_posts/2024-05-22-swe-bench-lite.md index 92e9ef67f..0317fbfbf 100644 --- a/website/_posts/2024-05-22-swe-bench-lite.md +++ b/website/_posts/2024-05-22-swe-bench-lite.md @@ -4,6 +4,9 @@ excerpt: Aider achieved this result mainly through its existing features that fo highlight_image: /assets/swe_bench_lite.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} # How aider scored SOTA 26.3% on SWE Bench Lite diff --git a/website/_posts/2024-05-24-self-assembly.md b/website/_posts/2024-05-24-self-assembly.md index a79c1e59c..2b0f5366a 100644 --- a/website/_posts/2024-05-24-self-assembly.md +++ b/website/_posts/2024-05-24-self-assembly.md @@ -4,6 +4,9 @@ excerpt: Aider has written 7% of its own code, via 600+ commits that inserted 4. highlight_image: /assets/self-assembly.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} # Aider has written 7% of its own code diff --git a/website/_posts/2024-06-02-main-swe-bench.md b/website/_posts/2024-06-02-main-swe-bench.md index d70830354..239093b2f 100644 --- a/website/_posts/2024-06-02-main-swe-bench.md +++ b/website/_posts/2024-06-02-main-swe-bench.md @@ -4,6 +4,9 @@ excerpt: Aider sets SOTA for the main SWE Bench, after recently setting SOTA for highlight_image: /assets/swe_bench.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} # Aider is SOTA for both SWE Bench and SWE Bench Lite diff --git a/website/docs/benchmarks-0125.md b/website/docs/benchmarks-0125.md index 256d85d8d..0de49c947 100644 --- a/website/docs/benchmarks-0125.md +++ b/website/docs/benchmarks-0125.md @@ -4,6 +4,10 @@ excerpt: The new `gpt-4-0125-preview` model is quantiatively lazier at coding th highlight_image: /assets/benchmarks-0125.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # The January GPT-4 Turbo is lazier than the last version [![benchmark results](/assets/benchmarks-0125.svg)](https://aider.chat/assets/benchmarks-0125.svg) diff --git a/website/docs/benchmarks-1106.md b/website/docs/benchmarks-1106.md index 8d2a2220e..600642bc9 100644 --- a/website/docs/benchmarks-1106.md +++ b/website/docs/benchmarks-1106.md @@ -4,6 +4,10 @@ excerpt: A quantitative comparison of the code editing capabilities of the new G highlight_image: /assets/benchmarks-1106.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Code editing benchmarks for OpenAI's "1106" models [![benchmark results](/assets/benchmarks-1106.svg)](https://aider.chat/assets/benchmarks-1106.svg) diff --git a/website/docs/benchmarks-speed-1106.md b/website/docs/benchmarks-speed-1106.md index 6d7d7cde9..59c70cd8d 100644 --- a/website/docs/benchmarks-speed-1106.md +++ b/website/docs/benchmarks-speed-1106.md @@ -5,6 +5,10 @@ canonical_url: https://aider.chat/2023/11/06/benchmarks-speed-1106.html highlight_image: /assets/benchmarks-speed-1106.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Speed benchmarks of GPT-4 Turbo and gpt-3.5-turbo-1106

{{ page.date | date: "%b %-d, %Y" }}

diff --git a/website/docs/benchmarks.md b/website/docs/benchmarks.md index f21f5557c..b7d68af96 100644 --- a/website/docs/benchmarks.md +++ b/website/docs/benchmarks.md @@ -4,6 +4,10 @@ excerpt: Benchmarking GPT-3.5 and GPT-4 code editing skill using a new code edit highlight_image: /assets/benchmarks.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # GPT code editing benchmarks [![benchmark results](/assets/benchmarks.svg)](https://aider.chat/assets/benchmarks.svg) diff --git a/website/docs/ctags.md b/website/docs/ctags.md index 80ec1ad0c..b53c921cf 100644 --- a/website/docs/ctags.md +++ b/website/docs/ctags.md @@ -4,6 +4,10 @@ excerpt: Using ctags to build a "repository map" to increase GPT-4's ability to highlight_image: /assets/robot-flowchart.png nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Improving GPT-4's codebase understanding with ctags ![robot flowchat](/assets/robot-flowchart.png) diff --git a/website/docs/repomap.md b/website/docs/repomap.md index ecadc6d6d..8046680d8 100644 --- a/website/docs/repomap.md +++ b/website/docs/repomap.md @@ -4,6 +4,10 @@ excerpt: Tree-sitter allows aider to build a repo map that better summarizes lar highlight_image: /assets/robot-ast.png nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Building a better repository map with tree sitter ![robot flowchat](/assets/robot-ast.png) diff --git a/website/docs/unified-diffs.md b/website/docs/unified-diffs.md index bc6001182..5e0ecc3a3 100644 --- a/website/docs/unified-diffs.md +++ b/website/docs/unified-diffs.md @@ -4,6 +4,10 @@ excerpt: GPT-4 Turbo has a problem with lazy coding, which can be signiciantly i highlight_image: /assets/benchmarks-udiff.jpg nav_exclude: true --- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + # Unified diffs make GPT-4 Turbo 3X less lazy ![robot flowchart](/assets/benchmarks-udiff.svg) diff --git a/website/index.md b/website/index.md index 429c98684..dede50409 100644 --- a/website/index.md +++ b/website/index.md @@ -74,10 +74,13 @@ So you can bounce back and forth between aider and your editor, to collaborative ## State of the art -Aider has the highest score on the challenging SWE Bench benchmark. +Aider has the highest score on the challenging +[SWE Bench benchmark](https://aider.chat/2024/06/02/main-swe-bench.html).

- aider swe bench + + aider swe bench +