News for hackers. Stuff that matters.

A comment on 'Positive review only': Researchers hide AI prompts in papers. Parent comment

Re:'Positive review only': Researchers hide AI prompts in pa... by jeroenhd on Saturday July 05, 2025 @03:17PM (#44474865)
If you cheat using an "agent" using an "MCP server", it's still rm -rf on the host, but in a form that AI startups will sell to you.

MCPs are generally a little smarter than exposing all data on the system to the service they're using, but you can tell the chatbot to work around those kinds of limitations.

[ Parent | on HN ]
Re:'Positive review only': Researchers hide AI prompts in pa... by MichaelOldfield on Saturday July 05, 2025 @03:47PM (#44475043)
Do you know that most MCP servers are Open Source and can be run locally?

It's also trivial to code them. Literally a Python function + some boilerplate.

[ Parent | on HN ]
Re:'Positive review only': Researchers hide AI prompts in pa... by shusaku on Saturday July 05, 2025 @08:01PM (#44476545)
I was sort of surprised to see MCP become a buzz word because we’ve been building these kinds of systems with duck tape and chewing gum for ages. Standardization is nice though. My advice is just ask your LLM nicely, and you should be safe :)
[ Parent | on HN ]