Updated my GPT-5+RAG blog post with more findings:
https://blog.pamelafox.org/2025/08/gpt-5-will-it-rag.html

GPT-5 reasoning models are more likely to:
* realize when they don't know enough to answer a question
* use top-level lists when answering
* use smart quotes
* generate wordier queries […]

There's so much interest in MCP, but also so much risk, so I'm trying to understand the MCP auth story.
Two helpful articles:
https://github.blog/ai-and-ml/generative-ai/how-to-build-secure-and-scalable-remote-mcp-servers/
https://modelcontextprotocol.io/specification/2025-06-18/basic/authorization

I edited my Cross-Site Request Forgery countermeasures research into a stand-alone article, including recommendations reusable by other projects.

tl;dr: no need for tokens or keys, modern browsers tell you if a request is cross-origin!

words.filippo.io/csrf