← Back to context

Comment by mvkel

5 days ago

I'd rather use the best possible model available than permanently relegate my work to an inferior one because it's "open"

It's not only about being open but predictability and unforeseen rug pulling.

  • Would you rather work with a team that is hit or miss, but has moments of brilliance, or predictably, consistently bad?

    • Moments of brilliance yet unpredictable versus reasonably good (lets be fair: 27b models are pretty damn good now) and predictable.

      I'm an old school engineer. I like predictable boring technology that consistently gets the job done over hotness. A 27b model at high quant is "hot" enough.

      Speaking in terms of teams: I hate working with hotshots. They ruin teams. And they're usually inconsistent and bad for morale.