I tried it with C and C++ code, it can do them but not very well.

How large the repositories are that it can "reason" about?

It's smart enough to figure out the relevant part to change once it scans the codebase. It could do Linux kernel if not for the Linus' policy.

Thanks. For example, if I feed it with the 10 MLoC repository, how long does it take before it can start working through the problem?

Would it really work well with the mixture of at least C and assembly which you implied it would with Linux kernel example?

> For example, if I feed it with the 10 MLoC repository, how long does it take before it can start working through the problem?

The initial scan may take about a hour with a repository that size, and the knowledge base buildup will take about a week (but that one happens during the coding process). It will not continuously scan the entire codebase once it builds up the knowledge of the repository.

Fascinating and scary at the same time.

Is this the beginning when intelligence, domain expertise and ability to research becomes commodity?

Or CUDA code, as this will be somehow ironic given that LLMs inference engines and training are CUDA code in some way.

It can do that too, I tried that too.