From 6bca74d40d2f063f676461523e06a5a294a53bf3 Mon Sep 17 00:00:00 2001 From: Matthew Isabel Date: Wed, 2 Apr 2025 12:32:42 -0400 Subject: [PATCH] Update claude docs (#55105) --- .../ai-models/using-claude-sonnet-in-github-copilot.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/content/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot.md b/content/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot.md index 205a5da92e56..a11554204b41 100644 --- a/content/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot.md +++ b/content/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot.md @@ -29,9 +29,13 @@ redirect_from: * {% data variables.product.prodname_copilot_chat_short %} in {% data variables.product.prodname_vs %} 2022 version 17.12 or later * Immersive mode in {% data variables.product.prodname_copilot_chat_short %} in {% data variables.product.github %} -{% data variables.product.prodname_copilot %} uses {% data variables.copilot.copilot_claude_sonnet %} hosted on Amazon Web Services. When using {% data variables.copilot.copilot_claude_sonnet %}, prompts and metadata are sent to Amazon's Bedrock service, which makes the [following data commitments](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html): _Amazon Bedrock doesn't store or log your prompts and completions. Amazon Bedrock doesn't use your prompts and completions to train any AWS models and doesn't distribute them to third parties_. +{% data variables.copilot.copilot_claude_sonnet %} is hosted by Amazon Web Services, Anthropic PBC, and Google Cloud Platform when used in {% data variables.product.prodname_copilot %}. GitHub has provider agreements in place to ensure data is not used for training. Additional details for each provider are included below: -Beginning March 11th, 2025, {% data variables.copilot.copilot_claude_sonnet %} will additionally be hosted by Anthropic PBC and Google Cloud Platform when used in {% data variables.product.prodname_copilot %} to provide additional model capacity and reliability. +* Amazon Bedrock: Amazon makes the [following data commitments](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html): _Amazon Bedrock doesn't store or log your prompts and completions. Amazon Bedrock doesn't use your prompts and completions to train any AWS models and doesn't distribute them to third parties_. +* Anthropic PBC: GitHub maintains a [zero data retention agreement](https://privacy.anthropic.com/en/articles/8956058-i-have-a-zero-retention-agreement-with-anthropic-what-products-does-it-apply-to) with Anthropic. +* Google Cloud: [Google commits to not training on GitHub data as part of their service terms](https://cloud.google.com/vertex-ai/generative-ai/docs/data-governance). GitHub is additionally not subject to prompt logging for abuse monitoring. + +In order to provide better service quality and reduce latency, GitHub uses [prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching). You can read more about prompt caching on [Anthropic PBC](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching), [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html), and [Google Cloud](https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude-prompt-caching). When using {% data variables.copilot.copilot_claude_sonnet %}, input prompts and output completions continue to run through {% data variables.product.prodname_copilot %}'s content filters for public code matching, when applied, along with those for harmful, offensive, or off-topic content.