Is anyone surprised? By definition LLM can’t be 100% correct and LLM hallucination poses significant challenges in generating accurate and reliable responses. ChatGPT Answers Programming Questions Incorrectly 52% of the Time: Study. To make matters worse, programmers in the study would often overlook the misinformation. gizmodo.com/chatgpt-answers-wr

Follow

@nixCraft For most of my programming questions, it can't give a valid solution. I mean, technically, if it gives a solution, you can probably find the same solution after reading several stackoverflow answers and documents.

Sign in to participate in the conversation
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.