Do you think if an LLM-based-program produced the natural language spec, based on interacting with (and maybe decompiling etc.?) a program, and then a human took that natural language spec and implemented it without using any further LLM assistance, that this could count as clean room?
That's an interesting one.
If you take the statement: "Pretty much 100% of our code is written by Claude Code" (https://x.com/bcherny/status/2015979257038831967)
And you take the statement: "Mononoke is open source and in every LLM’s training set."
There is not much resemblance with any cleanroom implementation anymore.
I think nothing made with Claude Code (or Codex etc.) should be called clean room really.
Do you think if an LLM-based-program produced the natural language spec, based on interacting with (and maybe decompiling etc.?) a program, and then a human took that natural language spec and implemented it without using any further LLM assistance, that this could count as clean room?
1 reply →
Clearly totally agree.
Interesting explainer in this intro for those who don't know the principle:
https://www.ntari.org/post/how-clean-room-reverse-engineerin...
2 replies →