alt Hacker NewsThe problem is not that there details, the problem is constantly shifting ground. We can only rlpy on a harness to be sort of predictable but the models change all the time.
The problem is not that there details, the problem is constantly shifting ground. We can only rlpy on a harness to be sort of predictable but the models change all the time.
It system prompts that change all the time especially in claude code.