latest
I hosted services for my family, and the real work started after setup
I started self-hosting to escape subscriptions, but I didn't expect to become the unpaid IT department for my family.
My local models are worse than Claude at almost everything, but they still run most of my workflow for $0
There are some things that just don't need Anthropic's flagship model
I changed one llama.cpp flag, and my 8GB laptop GPU now runs a 35B model faster than I can read
8GB of VRAM isn't the bottleneck, your settings probably are
I ditched Google Translate for a local model running on my GPU, and it works offline too
I'm getting more out of my gaming hardware than ever before
I thought self-hosting would save me money, but my years of experience proved otherwise
My self-hosted setup was supposed to cut costs, not become another expensive hobby.
I replaced my $20 ChatGPT and Claude subscriptions with local AI to cut costs, but it backfired
Free AI models looked like a bargain until I factored in the real cost.
My local LLM didn't replace my $20 Claude subscription, it replaced everything I was never comfortable sending to the cloud
There are many things Qwen3.6 struggles with, but keeping my data safe isn't one of them
Self-hosting doesn't actually save you money, and the people who promise it does are setting beginners up to quit
Self-hosting is worth it, but not for the reasons you've been told
The file sync app I forget exists has moved my files across four devices for a year
I never have a reason to open the sync app that runs 24/7 on my devices.
I segmented my home lab's network from my smart home, and stability improved overnight
Everything in its place, and a place for everything
My Proxmox server now runs a full dev environment for AI agents, and it's surprisingly easy to manage
I brought the cloud, home.
I gave four local models the same messy spreadsheet, and not one found the cheapest graphics card on it
Local models can sometimes perform data analysis like storytelling
Self-hosting got dramatically easier this year, and coding agents are the reason
You don't need to spend hours trying to self-host something.
I gave Jellyfin a Kodi makeover, and my media library felt brand-new
My media center has never looked better
I moved my local models from Ollama to llama.cpp, and the reason I stayed has nothing to do with speed
Convenience beats tokens generated per second, always
I gave my local LLM my entire Steam library, and it recommends games better than Steam does
Can Gemma 4 figure out my gaming taste better than Steam?
I ran GLM 5.3, a 744-billion-parameter model, on my home lab, and the frontier suddenly feels a lot closer
1.5TB of model, 350GB of computer. Math shouldn't work like this.
My home lab was costing me money until I installed these 5 Docker containers
My home lab finally earned its keep.
I ditched OpenClaw for OpenAI's Dots, and setup took minutes instead of hours
It's (probably) safer by design as well
Voicebox cloned my voice from a few seconds of audio on my own PC, and it's the most terrifying thing I've seen local AI do
AI voice cloning is getting creepier and creepier
