"Anthropic has published a new constitution for its AI model Claude. In this document, the company describes the values, behavioral principles, and considerations that the model must follow when processing user questions. The constitution has been made publicly available under a Creative Commons CC0 license, allowing the content to be used freely without permission. Anthropic published the first version of this constitution in May 2023."
"According to the company, the earlier version proved to have limitations, including Claude's difficulty in correctly applying safety and behavioral guidelines in new or unforeseen situations. When instructions did not provide explicit guidance for a specific prompt, the model could still generate undesirable or incorrect responses, reports SiliconANGLE. The new constitution, therefore, not only uses instructions but also contains detailed explanations of the underlying reasons for desired behavior. Anthropic argues that these explanations make it easier for Claude to apply the guidelines to unfamiliar tasks."
Anthropic released an updated constitution for Claude under a Creative Commons CC0 license, enabling unrestricted reuse. The document defines values, behavioral principles, and considerations the model must follow when processing user queries. The update addresses limitations of the May 2023 version, where Claude sometimes failed to apply safety and behavioral guidelines in novel situations and could produce undesirable or incorrect responses when instructions lacked explicit guidance. The new constitution supplements instructions with detailed explanations of underlying reasons for desired behavior to improve generalization. The constitution centers on four core principles, including helpfulness, tailored responses, broad safety, transparency, and ethical compliance.
Read at Techzine Global
Unable to calculate read time
Collection
[
|
...
]