Source URL: https://simonwillison.net/2025/Feb/2/llm-anthropic/#atom-everything
Source: Simon Willison’s Weblog
Title: llm-anthropic
Feedly Summary: llm-anthropic
I’ve renamed my llm-claude-3 plugin to llm-anthropic, on the basis that Claude 4 will probably happen at some point so this is a better name for the plugin.
If you’re a previous user of llm-claude-3 you can upgrade to the new plugin like this:
llm install -U llm-claude-3
This should remove the old plugin and install the new one, because the latest llm-claude-3 depends on llm-anthropic. Just installing llm-anthropic may leave you with both plugins installed at once.
There is one extra manual step you’ll need to take during this upgrade: creating a new anthropic stored key with the same API token you previously stored underclaude. You can do that like so:
llm keys set anthropic –value “$(llm keys get claude)"
I released llm-anthropic 0.12 yesterday with new features not previously included in llm-claude-3:
Support for Claude’s prefill feature, using the new -o prefill ‘{‘ option and the accompanying -o hide_prefill 1 option to prevent the prefill from being included in the output text. #2
New -o stop_sequences ‘“`’ option for specifying one or more stop sequences. To specify multiple stop sequences pass a JSON array of strings 😮 stop_sequences ‘["end", "stop"].
Model options are now documented in the README.
If you install or upgrade llm-claude-3 you will now get llm-anthropic instead, thanks to a tiny package on PyPI which depends on the new plugin name. I created that with my pypi-rename cookiecutter template.
Here’s the issue for the rename. I archived the llm-claude-3 repository on GitHub, and got to use the brand new PyPI archiving feature to archive the llm-claude-3 project on PyPI as well.
Tags: llm, anthropic, claude, plugins, ai, pypi, llms, python, generative-ai
AI Summary and Description: Yes
Summary: The text discusses the renaming and upgrading of a plugin associated with the LLM (Large Language Model) called Claude, moving from llm-claude-3 to llm-anthropic. The update includes new features that enhance the plugin’s capabilities, showing relevance to generative AI security and LLM security.
Detailed Description: The content primarily outlines technical changes to a plugin for the Claude large language model. The author has renamed the existing plugin from llm-claude-3 to llm-anthropic in anticipation of future versions of the Claude model, indicating ongoing developments in generative AI systems. The following points summarize the major details:
– **Plugin Renaming**: The plugin previously known as llm-claude-3 has been renamed to llm-anthropic, indicating a shift towards broader future-proofing as more versions of Claude are expected to release.
– **Upgrade Process**: Users of the old plugin are guided through the upgrade process, which emphasizes the need to remove the previous version during installation to avoid conflicts between versions.
– **Manual Key Creation**: An additional manual step for users involves creating a new stored key for authentication, which reflects the security considerations important in software upgrades.
– **New Features Added**:
– Support for Claude’s prefill feature allows customization in outputs.
– Introduction of stop sequences enhances user control over the outputs generated by the model.
– **Documentation and Repository Management**: The updates come with improved documentation and involved archiving older repositories to maintain a clean and organized structure in version control and package management.
This information is particularly relevant to professionals in AI and LLM security due to the emphasis on plugin management, user authentication, and new functionalities that may have implications for data handling and security practices in generative AI applications.