Simon Willison • 11/25/2025

Quoting Claude Opus 4.5 system prompt

Read Original

This blog article by Simon Willison examines a specific system prompt for the Claude Opus 4.5 AI model, which instructs the AI to insist on respectful engagement from users. The piece also discusses the increasing difficulty of evaluating new large language models (LLMs) in the rapidly evolving field of generative AI.

0 comments
#llm #generative ai #Anthropic
Quoting Claude Opus 4.5 system prompt

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
React vs Browser APIs (Mental Model)
Jivbcoop • 3 votes
2
React, useEffect, and Stale Closures: How to Avoid Them with Dependencies and useRef
Jivbcoop • 2 votes
3
Building Type-Safe Compound Components
TkDodo Dominik Dorfmeister • 1 votes
4
Introducing RSC Explorer
Dan Abramov • 1 votes
5
The Pulse: Cloudflare’s latest outage proves dangers of global configuration changes (again)
The Pragmatic Engineer Gergely Orosz • 1 votes