[kennethologist]

Just ask the LLM to walk you through each line of code, create an explain the dependency graphs and in a relatively short period of time they’ll know exactly how their code works. Using Claude Code is quite useful for this - I use it on GitHub repositories I’m curious about.

[NBJack]

I think the problem is "but why?" What incentive would they have when they just need a brief answer or solution, i.e. just make code do this, get the boss their answer on that, etc.?

It's going to be fun when LLM agents do all the communication for us.

[az09mugen]

For one thing, I never want to be held responsible of what an LLM says. Too much randomness.