Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)(github.com)
github.com
Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)
https://github.com/gfernandf/agent-skills
3 comments
you can also download the paper from zenodo
https://zenodo.org/records/19438943
slightly different version but the core ideas remain the same
https://zenodo.org/records/19438943
slightly different version but the core ideas remain the same
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.