how can one avoid building a chatgpt wrapper?

For LLM, grab a model from 🤗 and fine tune the head. But I still think you should make a wrapper that is interoperable with chatgpt, just in case they drop a v4.5 that blows everything away.

I just mean to abstract away from the model in code, that way you can plug-and-play with different models—including one that wraps the chatgpt api.

i see. yes, agree. also the notion of the user 'picking the model' and having control over which to use seems to be a nice track.

although i wonder if in 10+ years it's gonna be one mega base model, or every human with its own local model. like a tinybox.

i see. yes, agree. also the notion of the user 'picking the model' and having control over which to use seems to be a nice track.

although i wonder if in 10+ years it's gonna be one mega base model, or every human with its own local model. like a tinybox.
https://tinygrad.org/

it's coming! i'm so pumped for geohot's work, and the energy he brings into the table. first against elon, now against nvidia. taking on the whole challenge by himself.

to provide powerful models to the people. a true champ.

That’s the question! I’m hoping for Hotz’s bet to pay out. 

Even if true that error rates decrease only by increasing model parameters, we just need a point were the error rates are sufficiently low to not justify increased spending (usually better-than-human performance).

Then we wait for Huang's law.