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…::ChatGPT went from answering a simple math correctly 98% of the time to just 2%, over the course of a few months.
My (random user) opinion is that the answer is a mix between the required computational power being too expensive and thus reduced and somehow how they “fixed” the models so they cannot be “jailbroken”