"Simplistic lifestyle with lots of technology added."
Former pilot, electrical engineer. Switched to computers back in 2009 and have found myself in charge of all things IT related at a small company.
Posts are my own.
| Personal Website | https://www.gonyea.io |
| Github | https://github.com/jgonyea |
| Gitlab ($DAYJOB) | https://gitlab.com/jeremygonyea |
| Gitlab (personal) | https://gitlab.com/jgonyea |
Wanna take another #CMS for a spin but you're feeling stuck on #WordPress?
Come try the newly improved exporter!
Well, crapola. Was replacing disk 1 and it got to 99% when disk 2 gave out. Running rsync's off to some other drives and then I guess a full rebuild is next.
Unrelated, how are #ugreen NAS's? Worthwhile?
Accidentally pushed one prominent, unmarked button on my #github app, and now I get this unwanted email.
If I wanted to use #Copilot, I would have by now.
I've been struggling lately with how to properly secure AI tool usage within $DAYJOB.
I really like this article [1] "New prompt injection papers: Agents Rule of Two and The Attacker Moves Second" by Simon Willison. It references a post [2] from Meta "Agents Rule of Two: A Practical Approach to AI Agent Security".
This makes a lot of sense to me, and gives me hope of selling my coworkers on a process of approaching their usage of these tools.
Pick no more than two for any tool, and be careful when tools mix-and-match capabilities (i.e. MCP servers).
[1] https://simonwillison.net/2025/Nov/2/new-prompt-injection-papers/
[2] https://ai.meta.com/blog/practical-ai-agent-security/
