> GPT-3.5 series is a series of models that was trained on a blend of text and code from before Q4 2021. The following models are in the GPT-3.5 series:
code-davinci-002 is a base model, so good for pure code-completion tasks
text-davinci-002 is an InstructGPT model based on code-davinci-002
text-davinci-003 is an improvement on text-davinci-002
You're totally true. But it turned out, that proper prompting (like packing dialog context into the prompt) worked great.
I spent many hours with orig ChatGPT and with this recreated version. The main difference I have found is that the recreated ChatGPT is more inclined to ask questions on questions (maybe can be fixed with more prompt engineering). I didn't find any major differences in the quality or usefulness of the answers.
d_watt|3 years ago
> GPT-3.5 series is a series of models that was trained on a blend of text and code from before Q4 2021. The following models are in the GPT-3.5 series:
code-davinci-002 is a base model, so good for pure code-completion tasks
text-davinci-002 is an InstructGPT model based on code-davinci-002
text-davinci-003 is an improvement on text-davinci-002
karfly|3 years ago
I spent many hours with orig ChatGPT and with this recreated version. The main difference I have found is that the recreated ChatGPT is more inclined to ask questions on questions (maybe can be fixed with more prompt engineering). I didn't find any major differences in the quality or usefulness of the answers.