Blesta: Not Everything Should Be Vibe Coded. Apparently, Security Reports Can Be Vibe Ignored.
A WHMCS refugee, two AI assistants, 32 security findings, twelve matching code fixes, and a support ticket that has apparently taken a vow of silence.
AI & LLM
Using AI and local LLMs for actual sysadmin work — and what happens when you let them near production.
I Taught an AI to Read My Analytics. Then It Started Doing My Marketing.
“Wait, can you even do that?” It started, as the best bad ideas do, with a question I didn’t expect a real answer to. I’d been hearing about MCP — the Model Context Protocol, the thing that lets an AI assistant actually talk to your stuff instead of just hallucinating about it. And I had … Read more
Local LLM spam classifier — model shootout
We tested 9 local LLM models as spam classifiers on an AMD EPYC 4545P running Ollama. Here’s what we found. After setting up the SpamAssassin + Ollama integration (see the previous post), the obvious next question was: is qwen2.5:7b actually the best choice, or did we just get lucky picking it first? So we ran … Read more
Local LLM for mail spam/ham classification Part 1
In which I spend a Sunday morning asking a local AI to tell me whether emails about cheap Viagra are, in fact, about cheap Viagra. Spoiler: the 0.5b model cannot. The Problem SpamAssassin is great. Bayes is great. RBLs are great. But spam has gotten weird. Greek-language product spam from hacked domains with randomized subfolders … Read more