ValentaTomas

Related https://en.wikipedia.org/wiki/Bootstrapping_(compilers)

In essence when working with code stops being the major thing you do (you abstract that away) and start managing the agents working on code and writing the spec, you need new tools and working environment to support that.

This is a valid concern and we are still experimenting with how to do this right. A combination of preserving the reasoning history, having the generated code, and using tests to enforce the public interface (and fix it if anything breaks) looks promising.

I think the crucial part is indeed not being able to deterministically go from NL to code but to take an existing state of the codebase and spec and "continue the work".

Right now you just need the GPT-4 API key to run it but we plan to support custom models in the future.

Revisions prompting is not there yet but it is one of things that we are experimenting with.

The feedback/review loop is spot on - a lot of the problems can be fixed automatically in a few steps but you actually need the outputs/errors.

Can you please elaborate on what you mean by the term zero-dimensional mythology?

People often seems to be keeping git repositories with the commands, but I'm not sure how often is this approach used in companies.

On a similar note - is there a service offering serverless functions where you can precisely specify the CPU?