I started learning by giving GPT-4 big chunks of code to read through, and they would break them down line-by-line for me, then trying to come up with my own small changes. It really helped me get that intuition for how different systems/fu
GPT4 was one-shotting utilities that GPT3 Davinci couldn't. So, I'd have my limited tokens on GPT4 crank out the initial program before iterating with my abundant, GPT3 tokens.
社区评论
精选近 7 天的不同意见，摘录条数不代表真实好评比例。
2 条精选摘录
展开原文
I started learning by giving GPT-4 big chunks of code to read through, and they would break them down line-by-line for me, then trying to come up with my own small changes. It really helped me get that intuition for how different systems/fu
展开原文
GPT4 was one-shotting utilities that GPT3 Davinci couldn't. So, I'd have my limited tokens on GPT4 crank out the initial program before iterating with my abundant, GPT3 tokens.
展开原文
I remember when GPT-4 came out and the perceived performance upgrade seemed underwhelming for a major release compared to 3.5
近 7 天暂时没有符合此筛选条件的精选评论。