The distinction you’ve drawn (the decision is made by the deterministic engine; the LLM merely explains it) matches something I’ve seen in another field. I was testing the agent’s memory: the schema of a vehicle changes…
In my test, giving the context for the entire history yielded a result of 95–100 per cent
[dead]
The distinction you’ve drawn (the decision is made by the deterministic engine; the LLM merely explains it) matches something I’ve seen in another field. I was testing the agent’s memory: the schema of a vehicle changes…
In my test, giving the context for the entire history yielded a result of 95–100 per cent
[dead]