You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit d89b4b3
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: README.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,9 +4,9 @@
4
4
5
5
Unlimited AI coding in free chatbots for VS Code, Cursor and Windsurf. The best privacy, accuracy and speed.
6
6
7
-
Free and open-source. Join our [discord server](https://discord.gg/KJySXsrSX5) and get involed!
7
+
❤️ **Free and open-source.**_Join our [discord server](https://discord.gg/KJySXsrSX5) and get involed!_
8
8
9
-
✅ **Initializes chatbots**—ChatGPT, Claude, Gemini, AI Studio, and 10+ more \
9
+
✅ **Initializes chatbots**—ChatGPT, Claude, Gemini, AI Studio, Qwen, and 10+ more \
10
10
✅ **Applies responses**—multi-file changes integration with easy rollback \
11
11
✅ **Batteries included**—code completions, commit messages, and more
12
12
@@ -23,15 +23,15 @@ Code Web Chat only starts new conversations. This idea is borrowed from [Firefox
23
23
> [!NOTE]
24
24
> The _Apply response_ button placed under responses is not a means of automatic output extraction, it's an alias for the original _copy to clipboard_ button.
25
25
26
-
🤓**Control over "agency"**
26
+
🧠**Master model guidance through context ownership**
27
27
28
28
Large language models (LLMs) are trained on vast datasets targeting many use cases. For code generation, a model's training involves analyzing millions of simulated problem-solving flows, such as arriving at the accepted answer from a given StackOverflow question. For the purpose of agentic coding, models are trained on an additional layer of data that simulates gathering context and planning its next steps.
29
29
30
30
Because the model is only as smart as examples it has seen in its pre-training stage, the possible coverage of real-world scenarios when approached at a high level is fundamentally limited.
31
31
32
32
Therefore, CWC is designed to align with LLMs' true capabilities—that is, code generation in a controlled signal-to-noise ratio environment. Controlled by you, the engineer.
33
33
34
-
🤝 **Meet non-agentic workflow**
34
+
🤝 **Meet the non-agentic workflow**
35
35
36
36
Select folders and files for context, enter instructions, and send message via...
`Context exceeds threshold of ${threshold} tokens by ${percentage}%. Unreasonably large context may degrade response quality, hurt plan's usage allowance or incur significant costs.`,
0 commit comments