Re:RLHF is just barely RL
by consteval on Thursday August 08, 2024 @10:59AM
(#41192239)
There's levels to this.
Certainly "compiled" is one reward (although a blank file fits that...)
Another is test cases, input and output. This doesn't work on a software-wide scale but function-wide it can work.
In the future I think we'll see more of this test-driven development. Where developers formally define the requirements and expectations of a system and then an LLM (combined with other tools) generates the implementation. So instead of making the implementation, you just declaratively say what the implementation should do (and shouldn't).
Certainly "compiled" is one reward (although a blank file fits that...) Another is test cases, input and output. This doesn't work on a software-wide scale but function-wide it can work.
In the future I think we'll see more of this test-driven development. Where developers formally define the requirements and expectations of a system and then an LLM (combined with other tools) generates the implementation. So instead of making the implementation, you just declaratively say what the implementation should do (and shouldn't).