easy enough to solve with RL probably

There is no RL for programming languages. Especially ones w/ no significant amount of code.

nl an hour ago | parent | next [-]

I guess the op was implying that is something fixable fairly easily?

(Which is true - it's easy to prompt your LLM with the language grammar, have it generate code and then RL on that)

Easy in the sense of "it is only having enough GPUs to RL a coding capable LLM" anyway.

	▲	measurablefunc 37 minutes ago \| parent [-]
		If you can generate code from the grammar then what exactly are you RLing? The point was to generate code in the first place so what does backpropagation get you here?

not even wrong

	▲	measurablefunc 6 hours ago \| parent [-]
		Exactly.