A Year of building with LLMs
This is not a short read but could be an interesting series. It will be split into tactical, operational and strategic.
This is the tactical part.
What We Learned from a Year of Building with LLMs (Part I)
Read next
Thinking about privacy
My business phone is an Android phone. I didn't like it. Setting it up was painful as I had to deny so many requests for data and information (mind yer business!) It was never a pleasant experience. But I didn't think I could anything about it
Fixed and fixed properly
This is interesting.
'Exclusive' article on Fortune today explaining how researchers discovered a zero-click attack on MS Copilot which starts with sending an email with hidden instructions (prompt injection). Microsoft have definitely fixed it though
(https://fortune.com/2025/06/11/microsoft-copilot-vulnerability-ai-agents-echoleak-hacking/)
BUT, because I have a memory
They will never know what the problem is
I don’t go looking for examples of agentic AI. I’m not interested in terrible solutions. But sometimes they come across my radar, or I just can’t avoid them.
One of my key skills is recognising patterns in things that seem normal in isolation. It’s a good
Comments ()