Use sonnet by default; updated docs

HISTORY.md

@@ -6,6 +6,7 @@
 - Allow Claude 3.5 Sonnet to stream back >4k tokens!
   - It is the first model capable of writing such large coherent, useful code edits.
   - Do large refactors or generate multiple files of new code in one go.
+- Aider now uses `claude-3-5-sonnet-20240620` by default if `ANTHROPIC_API_KEY` is set in the environment.
 - Enabled [image support](https://aider.chat/docs/images-urls.html) for 3.5 Sonnet and for GPT-4o & 3.5 Sonnet via OpenRouter (by @yamitzky).
 - Added `--attribute-commit-message` to prefix aider's commit messages with "aider:".
 - Fixed regression in quality of one-line commit messages.

README.md

@@ -31,6 +31,7 @@ and works best with GPT-4o, Claude 3.5 Sonnet, Claude 3 Opus and DeepSeek Coder
 # Because this page is rendered by GitHub as the repo README
 cog.out(open("website/_includes/get-started.md").read())
 ]]]-->
+
 You can get started quickly like this:
 
 ```
@@ -43,14 +44,9 @@ $ cd /to/your/git/repo
 $ export OPENAI_API_KEY=your-key-goes-here
 $ aider 
 
-# Or, work with Anthropic's models
+# Work with Claude 3.5 Sonnet on your repo
 $ export ANTHROPIC_API_KEY=your-key-goes-here
-
-# Claude 3 Opus
-$ aider --opus
-
-# Claude 3.5 Sonnet
-$ aider --sonnet
+$ aider
 ```
 <!--[[[end]]]-->
 

aider/args.py

@@ -6,7 +6,7 @@ import sys
 
 import configargparse
 
-from aider import __version__, models
+from aider import __version__
 from aider.args_formatter import (
     DotEnvFormatter,
     MarkdownHelpFormatter,
@@ -44,12 +44,11 @@ def get_parser(default_config_files, git_root):
         env_var="ANTHROPIC_API_KEY",
         help="Specify the Anthropic API key",
     )
-    default_model = models.DEFAULT_MODEL_NAME
     group.add_argument(
         "--model",
         metavar="MODEL",
-        default=default_model,
-        help=f"Specify the model to use for the main chat (default: {default_model})",
+        default=None,
+        help="Specify the model to use for the main chat",
     )
     opus_model = "claude-3-opus-20240229"
     group.add_argument(

aider/main.py

@@ -403,6 +403,11 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
     register_models(git_root, args.model_settings_file, io)
     register_litellm_models(git_root, args.model_metadata_file, io)
 
+    if not args.model:
+        args.model = "gpt-4o"
+        if os.environ.get("ANTHROPIC_API_KEY"):
+            args.model = "claude-3-5-sonnet-20240620"
+
     main_model = models.Model(args.model, weak_model=args.weak_model)
 
     lint_cmds = parse_lint_cmds(args.lint_cmd, io)

website/HISTORY.md

@@ -17,6 +17,7 @@ cog.out(text)
 - Allow Claude 3.5 Sonnet to stream back >4k tokens!
   - It is the first model capable of writing such large coherent, useful code edits.
   - Do large refactors or generate multiple files of new code in one go.
+- Aider now uses `claude-3-5-sonnet-20240620` by default if `ANTHROPIC_API_KEY` is set in the environment.
 - Enabled [image support](https://aider.chat/docs/images-urls.html) for 3.5 Sonnet and for GPT-4o & 3.5 Sonnet via OpenRouter (by @yamitzky).
 - Added `--attribute-commit-message` to prefix aider's commit messages with "aider:".
 - Fixed regression in quality of one-line commit messages.

website/_includes/get-started.md

@@ -1,3 +1,4 @@
+
 You can get started quickly like this:
 
 ```
@@ -10,12 +11,7 @@ $ cd /to/your/git/repo
 $ export OPENAI_API_KEY=your-key-goes-here
 $ aider 
 
-# Or, work with Anthropic's models
+# Work with Claude 3.5 Sonnet on your repo
 $ export ANTHROPIC_API_KEY=your-key-goes-here
-
-# Claude 3 Opus
-$ aider --opus
-
-# Claude 3.5 Sonnet
-$ aider --sonnet
+$ aider
 ```

website/_posts/2024-07-01-sonnet-not-lazy.md

@@ -0,0 +1,93 @@
+---
+title: Sonnet is the opposite of lazy
+excerpt: Claude 3.5 Sonnet represents a step change in AI coding.
+#highlight_image: /assets/linting.jpg
+draft: true
+nav_exclude: true
+---
+{% if page.date %}
+<p class="post-date">{{ page.date | date: "%B %d, %Y" }}</p>
+{% endif %}
+
+
+# Sonnet is the opposite of lazy
+
+Claude 3.5 Sonnet represents a step change
+in AI coding.
+It is so industrious, diligent and hard working that
+it has caused multiple problems for aider.
+It's been worth the effort to adapt aider to work well
+with Sonnet,
+because the result is surprisingly powerful.
+
+Sonnet's amazing work ethic caused a few problems:
+
+1. Sonnet is capable of outputting a very large amount of correct,
+complete code in one response.
+So much that it can easily blow through the 4k output token limit
+on API responses, which truncates its coding in mid-stream.
+2. Similarly, Sonnet can specify large sequences of edits in one go, 
+like changing a majority of lines while refactoring a large file.
+Again, this regularly triggered the 4k output limit
+and resulted in a failed edits.
+3. Sonnet is not shy about quoting large chunks of an
+existing file to perform a SEARCH & REPLACE edit across
+a long span of lines.
+This can be wasteful and also trigger the 4k output limit.
+
+
+## Good problems
+
+Problems (1) and (2) are "good problems"
+in the sense that Sonnet is
+able to write more high quality code than any other model!
+
+Aider now allows Sonnet to return code in multiple 4k token
+responses.
+This gets all the upsides of Sonnet's prolific coding skills,
+without being constrained by the 4k output token limit.
+
+
+## Wasting tokens
+
+Problem (3) does cause some real downsides.
+
+Faced with a few small changes spread far apart in 
+a source file,
+Sonnet would often prefer to do one giant SEARCH/REPLACE
+operation of the ~entire file.
+This wastes a tremendous amount of tokens,
+time and money -- and risks hitting the 4k output limit.
+It would be far faster and less expensive to instead 
+do a few surgical edits.
+
+Aider now prompts Sonnet to discourage these long-winded
+SEARCH/REPLACE operations
+and promotes much more concise edits.
+
+
+## Aider with Sonnet
+
+[The latest release of aider](https://aider.chat/HISTORY.html#aider-v0410)
+has specialized support for Claude 3.5 Sonnet:
+
+- Aider allows Sonnet to produce as much code as it wants,
+by automatically and seamlessly spreading the response
+out over a sequence of 4k token API responses.
+- Aider carefully prompts Sonnet to be concise and
+return only changing sections of code.
+This reduces Sonnet's tendency to waste time, tokens and money
+returning large chunks of unchanging code.
+- Aider now uses `claude-3-5-sonnet-20240620` by default if `ANTHROPIC_API_KEY` is set in the environment.
+
+You can use aider with Sonnet like this:
+
+```
+pip install aider-chat
+
+export ANTHROPIC_API_KEY=<key> # Mac/Linux
+setx   ANTHROPIC_API_KEY <key> # Windows
+
+aider
+```
+

website/assets/sample.aider.conf.yml

@@ -19,8 +19,8 @@
 ## Specify the Anthropic API key
 #anthropic-api-key:
 
-## Specify the model to use for the main chat (default: gpt-4o)
-#model: gpt-4o
+## Specify the model to use for the main chat
+#model:
 
 ## Use claude-3-opus-20240229 model for the main chat
 #opus: false

website/assets/sample.env

@@ -27,8 +27,8 @@
 ## Specify the Anthropic API key
 #ANTHROPIC_API_KEY=
 
-## Specify the model to use for the main chat (default: gpt-4o)
-#AIDER_MODEL=gpt-4o
+## Specify the model to use for the main chat
+#AIDER_MODEL=
 
 ## Use claude-3-opus-20240229 model for the main chat
 #AIDER_OPUS=

website/docs/config/aider_conf.md

@@ -47,8 +47,8 @@ cog.outl("```")
 ## Specify the Anthropic API key
 #anthropic-api-key:
 
-## Specify the model to use for the main chat (default: gpt-4o)
-#model: gpt-4o
+## Specify the model to use for the main chat
+#model:
 
 ## Use claude-3-opus-20240229 model for the main chat
 #opus: false

website/docs/config/dotenv.md

@@ -60,8 +60,8 @@ cog.outl("```")
 ## Specify the Anthropic API key
 #ANTHROPIC_API_KEY=
 
-## Specify the model to use for the main chat (default: gpt-4o)
-#AIDER_MODEL=gpt-4o
+## Specify the model to use for the main chat
+#AIDER_MODEL=
 
 ## Use claude-3-opus-20240229 model for the main chat
 #AIDER_OPUS=

website/docs/config/options.md

@@ -72,8 +72,7 @@ Specify the Anthropic API key
 Environment variable: `ANTHROPIC_API_KEY`  
 
 ### `--model MODEL`
-Specify the model to use for the main chat (default: gpt-4o)  
-Default: gpt-4o  
+Specify the model to use for the main chat  
 Environment variable: `AIDER_MODEL`  
 
 ### `--opus`

website/docs/llms/anthropic.md

@@ -19,12 +19,12 @@ pip install aider-chat
 export ANTHROPIC_API_KEY=<key> # Mac/Linux
 setx   ANTHROPIC_API_KEY <key> # Windows
 
+# Aider uses Claude 3.5 Sonnet by default (or use --sonnet)
+aider
+
 # Claude 3 Opus
 aider --opus
 
-# Claude 3.5 Sonnet
-aider --sonnet
-
 # List models available from Anthropic
 aider --models anthropic/
 ```

website/docs/llms/openai.md

@@ -19,7 +19,7 @@ pip install aider-chat
 export OPENAI_API_KEY=<key> # Mac/Linux
 setx   OPENAI_API_KEY <key> # Windows
 
-# GPT-4o is the best model, used by default
+# Aider uses gpt-4o by default (or use --4o)
 aider
 
 # GPT-4 Turbo (1106)

website/index.md

@@ -45,6 +45,7 @@ and works best with GPT-4o, Claude 3.5 Sonnet, Claude 3 Opus and DeepSeek Coder
 # Because this page is rendered by GitHub as the repo README
 cog.out(open("website/_includes/get-started.md").read())
 -->
+
 You can get started quickly like this:
 
 ```
@@ -57,14 +58,9 @@ $ cd /to/your/git/repo
 $ export OPENAI_API_KEY=your-key-goes-here
 $ aider 
 
-# Or, work with Anthropic's models
+# Work with Claude 3.5 Sonnet on your repo
 $ export ANTHROPIC_API_KEY=your-key-goes-here
-
-# Claude 3 Opus
-$ aider --opus
-
-# Claude 3.5 Sonnet
-$ aider --sonnet
+$ aider
 ```
 <!-- NOOP -->