Comment by julianlam
4 hours ago
You have to read between the lines (or wait for someone on HN to do it for you).
It's never "cheaper and faster and more intelligent", it's pick 2. Sometimes (as was the case this month), it was "cheaper per token, but reasons five times as much", so your costs go up.
the nice thing about local models is you can limit reasoning and keep things even all the time.