10-10-2026, 01:31 PM
I tested this tonight. On M3 Max with PyTorch, I saw basically the same behavior. The main thing that moved was latency, not quality.
routing beats arguing over one perfect model
|
synthetic data for support bots on 7900 XTX
|
|
« Next Oldest | Next Newest »
|
Users browsing this thread: 1 Guest(s)