[conorh]

We just changed a project we've been working on to try out the new gpt-4-turbo model and it is MUCH faster. I don't know if this is a factor of the number of people using it or not, but streaming a response for the prompts we are interested in went from 40-50 seconds to 6 seconds.

[0xDEF]

I noticed that too but I think it's because we are hitting new servers that just went online. They will probably get saturated and slower with time when other gpt-4 users start using gpt-4-turbo.