Skip to content

Commit a08ee0f

Browse files
committed
Refactor the README to emphasize context control and list Qwen among the supported chatbots
1 parent 21e836c commit a08ee0f

1 file changed

Lines changed: 3 additions & 3 deletions

File tree

‎README.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,9 +4,9 @@
44

55
Unlimited AI coding in free chatbots for VS Code, Cursor and Windsurf. The best privacy, accuracy and speed.
66

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!_
88

9-
✅ **Initializes chatbots**—ChatGPT, Claude, Gemini, AI Studio, and 10+ more \
9+
✅ **Initializes chatbots**—ChatGPT, Claude, Gemini, AI Studio, Qwen, and 10+ more \
1010
✅ **Applies responses**—multi-file changes integration with easy rollback \
1111
✅ **Batteries included**—code completions, commit messages, and more
1212

@@ -23,7 +23,7 @@ Code Web Chat only starts new conversations. This idea is borrowed from [Firefox
2323
> [!NOTE]
2424
> 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.
2525
26-
🤓 **Control over "agency"**
26+
🧠 **Control the context, guide the model**
2727

2828
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.
2929

0 commit comments

Comments
 (0)