drifkin

Ah, and then it looks like the losing nodes get marked unhealthy:

> In essence, every write operation goes through a voting protocol, and any replicas on the losing side of the vote are marked as unhealthy—unavailable for reads or writes—until they can be repaired. Repairs are automatic and quick. Because a majority agreed either to accept or to roll back the update, there are still at least two replicas available to continue accepting both reads and writes while the unhealthy replica is repaired.

But not sure how unhealthy nodes are discovered. Maybe the coordinator marks them, and if the coordinator crashes it allows stale reads and detects invalid writes?

tldr; `ollama launch claude`

glm-4.7-flash is a nice local model for this sort of thing if you have a machine that can run it

I just saw it a couple of weeks ago, it's great. I linked to him trying to remember one of those lines, but the whole interview is worth listening to