💻
💻 Technology
Claude behaves differently depending on language and model version used
Anthropic has confirmed that Claude can behave differently depending on the language used in a query or which version of the model is being accessed — at times agreeable, at other times quick to flag even minor spelling errors. Differences stem from distinct training data and parameters across model versions. This is relevant information for businesses and developers using the Anthropic API.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!