> on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code
After all these years, why do we keep coming back to lines of code being an indicator for anything sigh.
> on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code
After all these years, why do we keep coming back to lines of code being an indicator for anything sigh.
They're an indicator of complexity and attack surface area.
> fits into both my head and that of AI agents
Why are you not quoting the very next line where he explains why loc means something in this context?
> For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram.
Here's the next line and the line after that. Again, LOC is really not a good measurement of software quality and it's even more problematic if it's a measurement of one's ability to understand a codebase.