Article is intended for cron jobs but the logic in the last example works for any shell script or cli stuff:
curl -s "<https://news.google.com/rss?hl=en-US&gl=US&ceid=US:en>" | llm --system "Reply strictly 'yes' or 'no'. Does anything in the news today suggest it is a good reason to run a script that I only want to send when the world is on fire and crazy and terrible things are happening?" | tr -d '[:space:]' | tr '[:upper:]' '[:lower:]' | grep -qx yes && /path/to/oh_no
https://github.com/ai-boost/Awesome-GPTs
Applying LLMs & GenAI to Cyber Security
I get asked a lot how to become an AI security researcher. If I had to do it all over again in 2025, here’s how I’d do it:
Brew some coffee. You’re going to be up late. There’s a lot to learn–I’m not trying to scare you, you can totally do it. But it’s going to take time, and work. And coffee.
Start with the OWASP AI Exchange. Back in the 2010s there wasn’t a centralized repository of knowledge, industry insight, and best practices just waiting to be absorbed. Now there is. This is the place to start.
If you’re not coming from a security background: Take any cybersecurity classes you can get your hands on. See where it takes you. The fundamentals of security aren’t changing. And you need to learn to think like a security professional.