The LLM can only generate text. The harness can do more than just generate text. By joining the two you're allowing the LLM (through text) to carry out whatever actions the harness can take.

My brain can only generate electrical signals. My hand responds to electrical signals and can interact with the real world. The two together can do more than just what my brain alone can do.

If you don't trust a particular brain, don't put a gun in the hand which is connected to it. If you don't trust a LLM, don't connect it to a harness which has access to your production database and only recent backups (https://www.theregister.com/2026/04/27/cursoropus_agent_snuf...).

We’ve trained models on JSON schemas for “tool calls”, and then built software to interpret and run those calls for the LLMs