Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)
1–4 of 4 posts
Re: Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)
#2[dead]
Re: Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)
#3you can also download the paper from zenodo
https://zenodo.org/records/19438943
slightly different version but the core ideas remain the same
Re: Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)
#4One thing I didn’t make clear in the post:
The core issue is that prompt-based agents recompute reasoning every time.
ORCA tries to make reasoning reusable — more like software, less like a one-shot prompt.
Working on a minimal example to show this clearly.