On 4/8/24 14:19, Bruno Haible wrote:
My experience is that ChatGPT (3.5) provides good answers for things that have a lot of mentions on the web. Whereas for things that are rarely mentioned, it starts to hallucinate and often provides wrong answers. Therefore, for routine questions around Python or C++, it is perfectly suited.
For what it's worth, the business about the cost of x.append(y) (it's O(len(x)), and O(1) amortized) has been a standard part of the cost model lecture in my programming languages course for more than two decades, so I hope that UCLA graduates, at least, are still a step ahead of ChatGPT.
