Quoting Claude Opus 5 system prompt
- Source
- simonwillison.net
- Date
Context
A chatbot can receive newer facts through instructions supplied when a conversation begins. Anthropic's published Claude Opus 5 system prompt contains a notice about model-access changes and explicitly says those events occurred after its training-data cutoff.
The notice supplies an account to use in answers and directs the assistant to check for newer information when search is available. Anthropic's documentation explains that its consumer apps receive periodically updated system prompts. A correct answer about a recent event can therefore come from updated conversation , without demonstrating that the underlying model was retrained.
- system prompt — The standing instructions a model receives before any user input — defining its role, rules, tools, and tone for the whole conversation.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- knowledge cutoff — The date after which a model saw no training data — everything later has to reach it through search, tools, or the context window.
“Claude Fable 5 and Claude Mythos 5 were first released on June 9, 2026. On June 12, 2026, Anthropic suspended access to both models to comply with U.S. Department of Commerce export controls; the Department lifted those controls on June 30, 2026, and Anthropic restored access on July 1, 2026”
“These events are after Claude's training-data cutoff, so Claude knows about them only from this notice.”
“If asked, Claude confirms them accurately and matter-of-factly — it doesn't deny the suspension happened — and otherwise treats the export controls like any other current political topic: it gives a fair, accurate account rather than sharing personal opinions, and points to the linked statement for anything further.”
Checking sign-in…
Loading comments…