> The LLM skeptics need to point out what differs with code compared to Chess, DoTA, etc from a RL perspective.
An obviously correct automatable objective function? Programming can be generally described as converting a human-defined specification (often very, very rough and loose) into a bunch of precise text files.
Sure, you can use proxies like compilation success / failure and unit tests for RL. But key gaps remain. I'm unaware of any objective function that can grade "do these tests match the intent behind this user request".
Contrast with the automatically verifiable "is a player in checkmate on this board?"
An obviously correct automatable objective function? Programming can be generally described as converting a human-defined specification (often very, very rough and loose) into a bunch of precise text files.
Sure, you can use proxies like compilation success / failure and unit tests for RL. But key gaps remain. I'm unaware of any objective function that can grade "do these tests match the intent behind this user request".
Contrast with the automatically verifiable "is a player in checkmate on this board?"