2y ago

ChatGPT can get worse over time, Stanford study finds | Fortune

By June, “for reasons that are not clear,” ChatGPT stopped showing its step-by-step reasoning.

2y ago

Over just a few months, ChatGPT went from correctly answering a simple math problem 98% of the time to just 2%, study finds. Researchers found wild fluctuations—called drift—in the technology’s abi...

fortune.com /2023/07/19/chatgpt-accuracy-stanford-study/amp/