Tune the system prompts to extract package names or ecosystems #428
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
With Copilot+Anthropic the user message can contain instructions that are passed from the chat client and really sound like a system message. For whatever reason, the chat client includes them with `role=user`. These instructions confuse the LLM when extracting the package names or ecosystem and it replies with a mix of JSON and natural language. To work around that, Pankaj suggested to tune the system prompt and tell the LLM to ignore the instructions. This seems to work and helps Anthropic extract the package names even with copilot user message. Co-authored-by: Pankaj Telang <[email protected]> Related: #401
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
With Copilot+Anthropic the user message can contain instructions that
are passed from the chat client and really sound like a system message.
For whatever reason, the chat client includes them with
role=user.These instructions confuse the LLM when extracting the package names or
ecosystem and it replies with a mix of JSON and natural language.
To work around that, Pankaj suggested to tune the system prompt and tell
the LLM to ignore the instructions. This seems to work and helps
Anthropic extract the package names even with copilot user message.
Co-authored-by: Pankaj Telang [email protected]
Related: #401