What do people realistically do with these? It's too slow and du... not SOTA-level for coding. It's way too slow for video. I tried simulating an "Fable herding Qwen subagents" and it takes much longer and delivers a much worse result than Fable/Astra alone.
You run uncensored local models where you can ask questions that would get denied by public providers, or questions that you prefer them not to know the intricate details (like your financial planning)
Ah I see. I guess people who have spare $10-20k on a PC to run a "personal assistant" perhaps really benefit from a personal assistant. A niche in itself.
mstaoru · · focus · HN ↗
manyatoms · · focus · HN ↗
You run uncensored local models where you can ask questions that would get denied by public providers, or questions that you prefer them not to know the intricate details (like your financial planning)
EricE · · focus · HN ↗
mstaoru · · focus · HN ↗
apexalpha · · focus · HN ↗
There's value in knowing what capabilities local models will have on regular hardware in the near future.