Eleven posts on what it really takes to run AI on your own hardware, from a private AI server...
The last post in the series: what our private AI lab set out to prove, the platform we ended...
A local model needs memory for its weights, for a KV cache that grows with context and parallel slots,...
Chatbots get the attention, but most of what businesses ask of private AI is quiet work: reading requests, turning...
We ran a Telegram AI agent on local models in our lab. It gave bad answers, then refused to...
We ran an open-source team of AI analysts, debaters and managers on our lab AI server, with public market...
If nobody can see inside a private AI server, it freezes without warning. In our lab we built tracing,...
A silent image upgrade, a pruned container image and a backup that had quietly stopped pushed us to run...
Our first smart router made every request slower and pushed other clients' models out of memory. This is how...
