Of course, it still requires tremendous domain knowledge, although that domain knowledge is faster acquired working with AI. However, although the debugging trap is of course real with ALL sub-Fable models it seems, it takes the tedium out of running a homelab and turns it into a net positive to even have in your home!
This is great. Homelab AI feels like it's going to fun as heck. I currently have Claude maintain my homelab across all devices; it made homelab setup and maintenance go from "This is a trap that will fascinate you for years but never fully work right and waste time that would have better been spent elsewhere" to "This is actually a great idea and really extends my capabilities."
Brutal. I've been noticing that 4.7 eats my Max Subscription like crazy even when I do my best to juggle tasks (or tell 4.7 to use subagents with) Sonnet 4.6 Medium and Haiku. Would love to know if anybody's found ideal token-saving approaches.
As an ethical conundrum, this one is clear. The safety of women and children online (human trafficking, r*pe and child abuse networks openly coordinate at industrial scale on Discord, Roblox and Telegram) trumps the concerns of a relatively small group of Richard Stallman-level purity obsessives. Good move on Discord's part; hopefully Roblox and Telegram shape up and follow suit. If you don't understand the severity of the current situation in 2026, Google the group "764."