I said my example was contrived because I didn’t test the prompt (admittedly I should have tried to).
I still think there’s a lack of explainability to the whole model though, and I struggle to understand how we could continue improving these models without understanding how they fundamentally make their decisions.
That being said, after reading some more output from GPT-3, it is more coherent than I remembered.
I still think there’s a lack of explainability to the whole model though, and I struggle to understand how we could continue improving these models without understanding how they fundamentally make their decisions.
That being said, after reading some more output from GPT-3, it is more coherent than I remembered.