how can one avoid building a chatgpt wrapper?

agree. what do you mean by 'interoperable with chatgpt'? plugins?

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.

The open web is dead, long live the open web. ⌐◨-◨

Building /warpcast and /farcaster

— gabrielayuso.com

i suspect tuning will play a big role in creating value that can't be captured by the owners of base models. but still a tough nut to crack.

we might go through something similar as the dot com crash. specially if openai keeps shipping so firmly as they do. they understand the market and adapt accordingly.

Everything in LLMs is built on top of a base model.

There are just different strategies to achieve what you need.

I guess what people call a "wrapper" is when prompt engineering is used.

Maybe tuning will get you away from the "wrapper" moniker?

i'd also start with hugging face
https://huggingface.co/models