I have a question for people with knowledge of both LLMs and GOFAI: Why can’t we use LLMs to write as many symbolic rules as needed to fit the data while keeping the ruleset reviewable and maintainable?
loading story #50354486
The amount of finite rules necessary (that the LLM will write) to handle the noise and complexity of real data generates such a dense graph that it breaks the premise of a human-maintainable and auditable system.
We can and do! Here's one you can help maintain and review!
Define reviewable and maintainable