The term "context engineering" is gaining traction over "prompt engineering" as it better describes the skill of providing LLMs with the necessary information (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Jun/27/context-…
This is just one example. "MCP" the protocol for "AI agents" is basically without security measures. It's like running random code on your infrastructure and data.
(Original title: GitHub MCP Exploited: Accessing private repositories via MCP)
https://simonwillison.net…
Man könnte ja denken das diese ganze Agent/MCP Geschichte grad doch sehr fast and loose abläuft ....
https://simonwillison.net/2025/May/26/github-mcp-exploited/
After months of coding with an #LLM I'm going back to using my brain
https://simonwillison.net/2025/May/20/after-months-of-coding-with-llms/#ato…
The lethal trifecta for #AI agents: private data, untrusted content, and external communication
https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/
Oh wow, if you ask Grok something it asks the great Elon Musk for guidance....😆
(Source : #grok
OpenAI updates its coding agent Codex with internet access, turned off by default, and expands availability to ChatGPT Plus users (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Jun/3/codex-agent-internet-access/
Musk: Come on, you need Grok!
Pentagon: Nah, we good.
[ Musk turns Grok antisemitism up to 11 ]
Musk: How about now?
Pentagon: Where do we sign!?
• https://www.bbc.com/news/articles/c628d9mre3go
•
@… @… Check out this discussion: https://