From 7a4801a907332fa025616ff9a1240f447edd5a7d Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 12:18:21 +0000 Subject: [PATCH 01/13] Add an example Dotcom Chat prompt which could trigger symbol search --- .../using-github-copilot-chat-in-githubcom.md | 1 + 1 file changed, 1 insertion(+) diff --git a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/using-github-copilot-chat-in-githubcom.md b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/using-github-copilot-chat-in-githubcom.md index 7415886aef..ccc313fa05 100644 --- a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/using-github-copilot-chat-in-githubcom.md +++ b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/using-github-copilot-chat-in-githubcom.md @@ -104,6 +104,7 @@ You can choose a particular repository, file or symbol, and then ask a question - What is the main purpose of this repo? What problem does it solve or what functionality does it provide? - What web frameworks are used in this project? - Where is rate limiting implemented in our API? + - How does the WidgetFactory class work? - How is the code organized? Explain the project architecture. - Are there any specific environment requirements for working on this project? From a88dbf7295836aacfaf5b6dc1d4fff59c6c397b4 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 12:19:57 +0000 Subject: [PATCH 02/13] Mention in the Dotcom Chat transparency note that the model can gather additional context --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index 9f6f20e8b0..ec9a726113 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -1,6 +1,8 @@ ### Input processing -The input prompt from the user is pre-processed by the {% data variables.product.prodname_copilot_chat_short %} system and sent to a large language model to get a response based on the context and prompt. User input can take the form of code snippets or plain language. The system is only intended to respond to coding-related questions. +The input prompt from the user is pre-processed by the {% data variables.product.prodname_copilot_chat_short %} system, combined with contextual information (for example, the current date and time and the name of the repository the user is currently viewing), and sent to a large language model. User input can take the form of code snippets or plain language. + +The large language model will take the prompt, gather additional context (for example repository data stored on GitHub or search results from Bing), and provide a response based on the prompt. The system is only intended to respond to coding-related questions. ### Language model analysis @@ -8,7 +10,7 @@ The pre-processed prompt is then passed through the {% data variables.product.pr ### Response generation -The language model generates a response based on its analysis of the input prompt and the context provided to it. This response can take the form of generated code, code suggestions, or explanations of existing code. +The language model generates a response based on its analysis of the input prompt and the context provided to it. The language model can gather additional context (for example repository data stored on GitHub or search results from Bing), and provide a response based on the prompt. This response can take the form of generated code, code suggestions, or explanations of existing code. ### Output formatting From a73e89b9fd61c7d5a16d98d543d71fde82d00c86 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 12:20:18 +0000 Subject: [PATCH 03/13] Add Bing search results as a kind of citation in Dotcom Chat --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index ec9a726113..57473bdaa8 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -14,7 +14,7 @@ The language model generates a response based on its analysis of the input promp ### Output formatting -The response generated by {% data variables.product.prodname_copilot_chat_short %} is formatted and presented to the user. {% data variables.product.prodname_copilot_chat_short %} may use syntax highlighting, indentation, and other formatting features to add clarity to the generated response. Depending upon the type of question from the user, links to context that the model used when generating a response, such as source code files or documentation, may also be provided. +The response generated by {% data variables.product.prodname_copilot_chat_short %} is formatted and presented to the user. {% data variables.product.prodname_copilot_chat_short %} may use syntax highlighting, indentation, and other formatting features to add clarity to the generated response. Depending upon the type of question from the user, links to context that the model used when generating a response, such as source code files, Bing search results or documentation, may also be provided. {% data variables.product.prodname_copilot_chat_short %} is intended to provide you with the most relevant answer to your question. However, it may not always provide the answer you are looking for. Users of {% data variables.product.prodname_copilot_chat_short %} are responsible for reviewing and validating responses generated by the system to ensure they are accurate and appropriate. {% data variables.product.prodname_copilot_chat_short %} is also designed to learn from your feedback and improve over time. For more information on improving the performance of {% data variables.product.prodname_copilot_chat_short %}, see "[Improving performance for {% data variables.product.prodname_copilot_chat_short %}](#improving-performance-for-copilot-chat)." From e2ffb78182419941fa6b18b31cc8a0efa64c71f0 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 12:20:35 +0000 Subject: [PATCH 04/13] Mention Bing search results as a kind of context used in Dotcom Chat --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index 57473bdaa8..5421f77c0f 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -26,7 +26,7 @@ The response generated by {% data variables.product.prodname_copilot_chat_short You can ask {% data variables.product.prodname_copilot_chat_short %} for help or clarification on specific coding problems and receive responses in natural language format or in code snippet format. -The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, code in your repositories and Markdown documentation in your knowledge bases to answer your questions. +The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, search results from Bing, code in your repositories and Markdown documentation in your knowledge bases to answer your questions. This can be a useful tool for programmers, as it can provide guidance and support for common coding tasks and challenges. From 720e6f6fe42329ffbf271993d737f2b2bfdc7200 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 12:20:58 +0000 Subject: [PATCH 05/13] Flag that Bing search results may introduce biases to Dotcom Chat --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index 5421f77c0f..014ea6c686 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -78,7 +78,7 @@ Depending on factors such as your codebase and input data, you may experience di ### Potential biases -{% data variables.product.prodname_copilot_short %}'s training data is drawn from existing code repositories, which may contain biases and errors that can be perpetuated by the tool. Additionally, {% data variables.product.prodname_copilot_chat_short %} may be biased towards certain programming languages or coding styles, which can lead to suboptimal or incomplete code suggestions. +{% data variables.product.prodname_copilot_short %}'s training data (drawn from existing code repositories) and context gathered by the large language model (for example Bing search results) may contain biases and errors that can be perpetuated by the tool. Additionally, {% data variables.product.prodname_copilot_chat_short %} may be biased towards certain programming languages or coding styles, which can lead to suboptimal or incomplete code suggestions. ### Security risks From f667888d61613c71e016b189ac94b3cfb4f264b2 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 15:26:49 +0000 Subject: [PATCH 06/13] Update data/reusables/rai/copilot/about-copilot-dotcom-chat.md Co-authored-by: hubwriter --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index 014ea6c686..31bad86d7a 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -2,7 +2,7 @@ The input prompt from the user is pre-processed by the {% data variables.product.prodname_copilot_chat_short %} system, combined with contextual information (for example, the current date and time and the name of the repository the user is currently viewing), and sent to a large language model. User input can take the form of code snippets or plain language. -The large language model will take the prompt, gather additional context (for example repository data stored on GitHub or search results from Bing), and provide a response based on the prompt. The system is only intended to respond to coding-related questions. +The large language model will take the prompt, gather additional context (for example repository data stored on {% data variables.product.prodname_dotcom %} or search results from Bing), and provide a response based on the prompt. The system is only intended to respond to coding-related questions. ### Language model analysis From 0531935b0d2837be4918289eb4c574aa6fd7e9d5 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Fri, 23 Feb 2024 15:26:57 +0000 Subject: [PATCH 07/13] Update data/reusables/rai/copilot/about-copilot-dotcom-chat.md Co-authored-by: hubwriter --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index 31bad86d7a..2f4d06bfb8 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -10,7 +10,7 @@ The pre-processed prompt is then passed through the {% data variables.product.pr ### Response generation -The language model generates a response based on its analysis of the input prompt and the context provided to it. The language model can gather additional context (for example repository data stored on GitHub or search results from Bing), and provide a response based on the prompt. This response can take the form of generated code, code suggestions, or explanations of existing code. +The language model generates a response based on its analysis of the input prompt and the context provided to it. The language model can gather additional context (for example repository data stored on {% data variables.product.prodname_dotcom %} or search results from Bing), and provide a response based on the prompt. This response can take the form of generated code, code suggestions, or explanations of existing code. ### Output formatting From ab0335730766b2963d1d49ab5f5bf7714ccbaac7 Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Mon, 26 Feb 2024 13:06:28 +0000 Subject: [PATCH 08/13] Add comma --- data/reusables/rai/copilot/about-copilot-dotcom-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md index 2f4d06bfb8..606d0233f0 100644 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md @@ -26,7 +26,7 @@ The response generated by {% data variables.product.prodname_copilot_chat_short You can ask {% data variables.product.prodname_copilot_chat_short %} for help or clarification on specific coding problems and receive responses in natural language format or in code snippet format. -The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, search results from Bing, code in your repositories and Markdown documentation in your knowledge bases to answer your questions. +The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, search results from Bing, code in your repositories , and Markdown documentation in your knowledge bases to answer your questions. This can be a useful tool for programmers, as it can provide guidance and support for common coding tasks and challenges. From 6c5160ecb74a29192d27457a77606b66d88cd5f8 Mon Sep 17 00:00:00 2001 From: hubwriter Date: Mon, 26 Feb 2024 14:48:08 +0000 Subject: [PATCH 09/13] Remove unused reusable file --- .../rai/copilot/about-copilot-dotcom-chat.md | 97 ------------------- 1 file changed, 97 deletions(-) delete mode 100644 data/reusables/rai/copilot/about-copilot-dotcom-chat.md diff --git a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md b/data/reusables/rai/copilot/about-copilot-dotcom-chat.md deleted file mode 100644 index 606d0233f0..0000000000 --- a/data/reusables/rai/copilot/about-copilot-dotcom-chat.md +++ /dev/null @@ -1,97 +0,0 @@ -### Input processing - -The input prompt from the user is pre-processed by the {% data variables.product.prodname_copilot_chat_short %} system, combined with contextual information (for example, the current date and time and the name of the repository the user is currently viewing), and sent to a large language model. User input can take the form of code snippets or plain language. - -The large language model will take the prompt, gather additional context (for example repository data stored on {% data variables.product.prodname_dotcom %} or search results from Bing), and provide a response based on the prompt. The system is only intended to respond to coding-related questions. - -### Language model analysis - -The pre-processed prompt is then passed through the {% data variables.product.prodname_copilot_chat_short %} language model, which is a neural network that has been trained on a large body of text data. The language model analyzes the input prompt. - -### Response generation - -The language model generates a response based on its analysis of the input prompt and the context provided to it. The language model can gather additional context (for example repository data stored on {% data variables.product.prodname_dotcom %} or search results from Bing), and provide a response based on the prompt. This response can take the form of generated code, code suggestions, or explanations of existing code. - -### Output formatting - -The response generated by {% data variables.product.prodname_copilot_chat_short %} is formatted and presented to the user. {% data variables.product.prodname_copilot_chat_short %} may use syntax highlighting, indentation, and other formatting features to add clarity to the generated response. Depending upon the type of question from the user, links to context that the model used when generating a response, such as source code files, Bing search results or documentation, may also be provided. - -{% data variables.product.prodname_copilot_chat_short %} is intended to provide you with the most relevant answer to your question. However, it may not always provide the answer you are looking for. Users of {% data variables.product.prodname_copilot_chat_short %} are responsible for reviewing and validating responses generated by the system to ensure they are accurate and appropriate. {% data variables.product.prodname_copilot_chat_short %} is also designed to learn from your feedback and improve over time. For more information on improving the performance of {% data variables.product.prodname_copilot_chat_short %}, see "[Improving performance for {% data variables.product.prodname_copilot_chat_short %}](#improving-performance-for-copilot-chat)." - -## Use cases for {% data variables.product.prodname_copilot_chat_short %} - -{% data variables.product.prodname_copilot_chat_short %} can provide coding assistance in a variety of scenarios. - -### Answering coding questions - -You can ask {% data variables.product.prodname_copilot_chat_short %} for help or clarification on specific coding problems and receive responses in natural language format or in code snippet format. - -The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, search results from Bing, code in your repositories , and Markdown documentation in your knowledge bases to answer your questions. - -This can be a useful tool for programmers, as it can provide guidance and support for common coding tasks and challenges. - -### Explaining code and suggesting improvements - -{% data variables.product.prodname_copilot_chat_short %} can help explain selected code by generating natural language descriptions of the code's functionality and purpose. This can be useful if you want to understand the code's behavior or for non-technical stakeholders who need to understand how the code works. For example, if you select a function or code block in the code editor, {% data variables.product.prodname_copilot_chat_short %} can generate a natural language description of what the code does and how it fits into the overall system. This can include information such as the function's input and output parameters, its dependencies, and its purpose in the larger application. - -{% data variables.product.prodname_copilot_chat_short %} can also suggest potential improvements to selected code, such as improved handling of errors and edge cases, or changes to the logical flow to make the code more readable. - -By generating explanations and suggesting related documentation, {% data variables.product.prodname_copilot_chat_short %} may help you to understand the selected code, leading to improved collaboration and more effective software development. However, it's important to note that the generated explanations and documentation may not always be accurate or complete, so you'll need to review, and occasionally correct, {% data variables.product.prodname_copilot_chat_short %}'s output. - -### Proposing code fixes - -{% data variables.product.prodname_copilot_chat_short %} can propose a fix for bugs in your code by suggesting code snippets and solutions based on the context of the error or issue. This can be useful if you are struggling to identify the root cause of a bug or you need guidance on the best way to fix it. For example, if your code produces an error message or warning, {% data variables.product.prodname_copilot_chat_short %} can suggest possible fixes based on the error message, the code's syntax, and the surrounding code. - -{% data variables.product.prodname_copilot_chat_short %} can suggest changes to variables, control structures, or function calls that might resolve the issue and generate code snippets that can be incorporated into the codebase. However, it's important to note that the suggested fixes may not always be optimal or complete, so you'll need to review and test the suggestions. - -## Improving performance for {% data variables.product.prodname_copilot_chat_short %} - -{% data variables.product.prodname_copilot_chat_short %} can support a wide range of practical applications like Q&A, code generation, code analysis, and code fixes, each with different performance metrics and mitigation strategies. To enhance performance and address some of the the limitations of {% data variables.product.prodname_copilot_chat_short %}, there are various measures that you can adopt. For more information on the limitations of {% data variables.product.prodname_copilot_chat_short %}, see "[Limitations of {% data variables.product.prodname_copilot_chat %}](#limitations-of-github-copilot-chat)." - -### Keep your prompts on topic - -{% data variables.product.prodname_copilot_chat_short %} is intended to address queries related to coding exclusively. Therefore, limiting the prompt to coding questions or tasks can enhance the model's output quality. - -### Use {% data variables.product.prodname_copilot_chat_short %} as a tool, not a replacement - -While {% data variables.product.prodname_copilot_chat_short %} can be a powerful tool for generating code, it is important to use it as a tool rather than a replacement for human programming. You should always review and test the code generated by {% data variables.product.prodname_copilot_chat_short %} to ensure that it meets your requirements and is free of errors or security concerns. - -### Use secure coding and code review practices - -While {% data variables.product.prodname_copilot_chat_short %} can generate syntactically correct code, it may not always be secure. You should always follow best practices for secure coding, such as avoiding hard-coded passwords or SQL injection vulnerabilities, as well as following code review best practices, to address {% data variables.product.prodname_copilot_chat_short %}'s limitations. - -### Provide feedback - -If you encounter any issues or limitations with {% data variables.product.prodname_copilot_chat_short %}, we recommend that you provide feedback through the **share feedback** link in the {% data variables.product.prodname_copilot_chat_short %} interface. This can help the developers to improve the tool and address any concerns or limitations. - -### Stay up to date - -{% data variables.product.prodname_copilot_chat_short %} is a new technology and is likely to evolve over time For {% data variables.product.prodname_copilot_chat_dotcom %} you will always have access to the latest product experience. You should stay up to date with any new security risks or best practices that may emerge. - -## Limitations of {% data variables.product.prodname_copilot_chat %} - -Depending on factors such as your codebase and input data, you may experience different levels of performance when using {% data variables.product.prodname_copilot_chat_short %}. The following information is designed to help you understand system limitations and key concepts about performance as they apply to {% data variables.product.prodname_copilot_chat_short %}. - -### Limited scope - -{% data variables.product.prodname_copilot_chat_short %} has been trained on a large body of code but still has a limited scope and may not be able to handle more complex code structures or obscure programming languages. For each language, the quality of suggestions you receive may depend on the volume and diversity of training data for that language. For example, JavaScript is well-represented in public repositories and is one of {% data variables.product.prodname_copilot %}'s best supported languages. Languages with less representation in public repositories may be more challenging for {% data variables.product.prodname_copilot_chat_short %} to provide assistance with. Additionally, {% data variables.product.prodname_copilot_chat_short %} can only suggest code based on the context of the code being written, so it may not be able to identify larger design or architectural issues. - -### Potential biases - -{% data variables.product.prodname_copilot_short %}'s training data (drawn from existing code repositories) and context gathered by the large language model (for example Bing search results) may contain biases and errors that can be perpetuated by the tool. Additionally, {% data variables.product.prodname_copilot_chat_short %} may be biased towards certain programming languages or coding styles, which can lead to suboptimal or incomplete code suggestions. - -### Security risks - -{% data variables.product.prodname_copilot_chat_short %} generates code based on the context of the code being written, which can potentially expose sensitive information or vulnerabilities if not used carefully. You should be careful when using {% data variables.product.prodname_copilot_chat_short %} to generate code for security-sensitive applications and always review and test the generated code thoroughly. - -### Matches with public code - -{% data variables.product.prodname_copilot_chat_short %} is capable of generating new code, which it does in a probabilistic way. While the probability that it may produce code that matches code in the training set is low, a {% data variables.product.prodname_copilot_chat_short %} suggestion may contain some code snippets that match code in the training set. {% data variables.product.prodname_copilot_chat_short %} utilizes filters that block matches with public code on {% data variables.product.prodname_dotcom %} repositories, but you should always take the same precautions as you would with any code you write that uses material you did not independently originate, including precautions to ensure its suitability. These include rigorous testing, IP scanning, and checking for security vulnerabilities. - -### Inaccurate code - -One of the limitations of {% data variables.product.prodname_copilot_chat_short %} is that it may generate code that appears to be valid but may not actually be semantically or syntactically correct or may not accurately reflect the intent of the developer. To mitigate the risk of inaccurate code, you should carefully review and test the generated code, particularly when dealing with critical or sensitive applications. You should also ensure that the generated code adheres to best practices and design patterns and fits within the overall architecture and style of the codebase. - -### Inaccurate responses to non-coding topics - -{% data variables.product.prodname_copilot_chat_short %} is not designed to answer non-coding questions, and therefore its responses may not always be accurate or helpful in these contexts. If a user asks {% data variables.product.prodname_copilot_chat_short %} a non-coding question, it may generate an answer that is irrelevant or nonsensical, or it may simply indicate that it is unable to provide a useful response. From def0096013e09d903e622209062a3f9e9a7bf81e Mon Sep 17 00:00:00 2001 From: hubwriter Date: Mon, 26 Feb 2024 20:14:51 +0000 Subject: [PATCH 10/13] Update content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md --- .../about-github-copilot-chat-in-githubcom.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md index e4e78fcbdf..907bfa4334 100644 --- a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md +++ b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md @@ -64,7 +64,7 @@ The response generated by {% data variables.product.prodname_copilot_chat_short You can ask {% data variables.product.prodname_copilot_chat_short %} for help or clarification on specific coding problems and receive responses in natural language format or in code snippet format. -The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, search results from Bing,code in your repositories, and Markdown documentation in your knowledge bases to answer your questions. +The response generated by {% data variables.product.prodname_copilot_chat_short %} may use the model's training data set, search results from Bing, code in your repositories, and Markdown documentation in your knowledge bases to answer your questions. This can be a useful tool for programmers, as it can provide guidance and support for common coding tasks and challenges. From c2e3e5a768408ad9f6fc7a92c0de7a440f782fe1 Mon Sep 17 00:00:00 2001 From: hubwriter Date: Mon, 26 Feb 2024 20:15:31 +0000 Subject: [PATCH 11/13] Update content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md --- .../about-github-copilot-chat-in-githubcom.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md index 907bfa4334..920f492981 100644 --- a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md +++ b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md @@ -116,7 +116,7 @@ Depending on factors such as your codebase and input data, you may experience di ### Potential biases -{% data variables.product.prodname_copilot_short %}'s training data (drawn from existing code repositories) and context gathered by the large language model (for example Bing search results) may contain biases and errors that can be perpetuated by the tool. Additionally, {% data variables.product.prodname_copilot_chat_short %} may be biased towards certain programming languages or coding styles, which can lead to suboptimal or incomplete code suggestions. +{% data variables.product.prodname_copilot_short %}'s training data (drawn from existing code repositories) and context gathered by the large language model (for example, Bing search results) may contain biases and errors that can be perpetuated by the tool. Additionally, {% data variables.product.prodname_copilot_chat_short %} may be biased towards certain programming languages or coding styles, which can lead to suboptimal or incomplete code suggestions. ### Security risks From 2a1a3bf1e8349641708e2aa1a9aabbc8dce9dfb9 Mon Sep 17 00:00:00 2001 From: Jules <19994093+jules-p@users.noreply.github.com> Date: Tue, 27 Feb 2024 11:11:58 +0100 Subject: [PATCH 12/13] Update content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md --- .../about-github-copilot-chat-in-githubcom.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md index 920f492981..f9e255bf7b 100644 --- a/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md +++ b/content/copilot/github-copilot-enterprise/copilot-chat-in-github/about-github-copilot-chat-in-githubcom.md @@ -54,7 +54,7 @@ The language model generates a response based on its analysis of the input promp The response generated by {% data variables.product.prodname_copilot_chat_short %} is formatted and presented to the user. {% data variables.product.prodname_copilot_chat_short %} may use syntax highlighting, indentation, and other formatting features to add clarity to the generated response. Depending upon the type of question from the user, links to context that the model used when generating a response, such as source code files, Bing search results or documentation, may also be provided. -{% data variables.product.prodname_copilot_chat_short %} is intended to provide you with the most relevant answer to your question. However, it may not always provide the answer you are looking for. Users of {% data variables.product.prodname_copilot_chat_short %} are responsible for reviewing and validating responses generated by the system to ensure they are accurate and appropriate. Additionally, as part of our product development process, we undertake red teaming to understand and improve the safety of {% data variables.product.prodname_copilot_chat_short %}. Input prompts and output completions are run through content filters. The content filtering system detects and prevents the output on specific categories of content including harmful, offensive, or off-topic content. {% data variables.product.prodname_copilot_chat_short %} is also designed to learn from your feedback and improve over time. For more information on improving the performance of {% data variables.product.prodname_copilot_chat_short %}, see "[Improving performance for {% data variables.product.prodname_copilot_chat_short %}](#improving-performance-for-copilot-chat)." +{% data variables.product.prodname_copilot_chat_short %} is intended to provide you with the most relevant answer to your question. However, it may not always provide the answer you are looking for. Users of {% data variables.product.prodname_copilot_chat_short %} are responsible for reviewing and validating responses generated by the system to ensure they are accurate and appropriate. Additionally, as part of our product development process, we undertake red teaming to understand and improve the safety of {% data variables.product.prodname_copilot_chat_short %}. Input prompts and output completions are run through content filters. The content filtering system detects and prevents the output on specific categories of content including harmful, offensive, or off-topic content. For more information on improving the performance of {% data variables.product.prodname_copilot_chat_short %}, see "[Improving performance for {% data variables.product.prodname_copilot_chat_short %}](#improving-performance-for-copilot-chat)." ## Use cases for {% data variables.product.prodname_copilot_chat_short %} From 27edefa43cd3b436178e7f57a4fabf824f46cc3d Mon Sep 17 00:00:00 2001 From: Jules Porter Date: Tue, 27 Feb 2024 11:15:44 +0100 Subject: [PATCH 13/13] remove improve over time line --- .../copilot/github-copilot-chat/about-github-copilot-chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/copilot/github-copilot-chat/about-github-copilot-chat.md b/content/copilot/github-copilot-chat/about-github-copilot-chat.md index 947b87bef9..2c0b97a94f 100644 --- a/content/copilot/github-copilot-chat/about-github-copilot-chat.md +++ b/content/copilot/github-copilot-chat/about-github-copilot-chat.md @@ -37,7 +37,7 @@ The language model generates a response based on its analysis of the input promp The response generated by {% data variables.product.prodname_copilot_chat_short %} is formatted and presented to the user. {% data variables.product.prodname_copilot_chat_short %} may use syntax highlighting, indentation, and other formatting features to add clarity to the generated response. Depending upon the type of question from the user, links to context that the model used when generating a response, such as source code files or documentation, may also be provided. -{% data variables.product.prodname_copilot_chat %} is intended to provide you with the most relevant answer to your question. However, it may not always provide the answer you are looking for. Users of {% data variables.product.prodname_copilot_chat_short %} are responsible for reviewing and validating responses generated by the system to ensure they are accurate and appropriate. Additionally, as part of our product development process, we undertake red teaming to understand and improve the safety of {% data variables.product.prodname_copilot_chat_short %}. Input prompts and output completions are run through content filters. The content filtering system detects and prevents the output on specific categories of content including harmful, offensive, or off-topic content. {% data variables.product.prodname_copilot_chat_short %} is also designed to learn from your feedback and improve over time. For more information on improving the performance of {% data variables.product.prodname_copilot_chat %}, see "[Improving performance for {% data variables.product.prodname_copilot_chat %}](/copilot/github-copilot-chat/about-github-copilot-chat#improving-performance-for-github-copilot-chat)." +{% data variables.product.prodname_copilot_chat %} is intended to provide you with the most relevant answer to your question. However, it may not always provide the answer you are looking for. Users of {% data variables.product.prodname_copilot_chat_short %} are responsible for reviewing and validating responses generated by the system to ensure they are accurate and appropriate. Additionally, as part of our product development process, we undertake red teaming to understand and improve the safety of {% data variables.product.prodname_copilot_chat_short %}. Input prompts and output completions are run through content filters. The content filtering system detects and prevents the output on specific categories of content including harmful, offensive, or off-topic content. For more information on improving the performance of {% data variables.product.prodname_copilot_chat %}, see "[Improving performance for {% data variables.product.prodname_copilot_chat %}](/copilot/github-copilot-chat/about-github-copilot-chat#improving-performance-for-github-copilot-chat)." ## Use cases for {% data variables.product.prodname_copilot_chat %}