Comment by ShamelessC 4 years ago And you’re aware that this is, at most, an incremental improvement over the existing GPT3 models? 2 comments ShamelessC Reply jerpint 4 years ago This is the craziest part, a little clever fine tuning and this model has turned into a completely revolutionary tool Tenobrus 4 years ago all this capability was already easily available in GPT-3 with some prompt engineering, this mostly just changed it from few-shot to zero-shot.
jerpint 4 years ago This is the craziest part, a little clever fine tuning and this model has turned into a completely revolutionary tool Tenobrus 4 years ago all this capability was already easily available in GPT-3 with some prompt engineering, this mostly just changed it from few-shot to zero-shot.
Tenobrus 4 years ago all this capability was already easily available in GPT-3 with some prompt engineering, this mostly just changed it from few-shot to zero-shot.
This is the craziest part, a little clever fine tuning and this model has turned into a completely revolutionary tool
all this capability was already easily available in GPT-3 with some prompt engineering, this mostly just changed it from few-shot to zero-shot.