Issues and training when updating the LLM model on a project

[anon10827405]

@dgovergun

Is it normal that changing from one OpenAI model to another results in such a significant difference in comprehension and outcomes?

Yes, but it’s usually not worse

@dgovergun

Does any model change necessarily mean the entire set of instructions needs to be refactored?

Yes

@dgovergun

Should we be doing things differently?

Probably. You have used a bunch of bootstrapped black boxes together and now are going to have a hell of a time debugging it

@dgovergun

Are OpenAI models suitable for building such a tool?

Yes