Protect your private dataWe share and access a ton of private data every day which can cause some big problems if that info gets into the wrong hands.

 Protect your private dataWe share and access a ton of private data every day which can cause some big problems if that info gets into the wrong hands.

Interestingly, Enderman ran this prompt on both the older, GPT-3 language model and on OpenAI’s newer GPT-4, and told us that the more recent model improved upon even what you saw in his video. In an email, Enderman (who requested we use his screenname) told Gizmodo that a certain number string in the key needed to be divisible by 7. GPT-3 would struggle to understand that constraint and created far fewer usable keys. In subsequent tests with GPT-4, ChatGPT would spit out far more correct keys, though even then not every single key was a winner or stuck to the prompt’s parameters. The YouTuber said this suggests “GPT-4 does know how to do math, but gets lost during batch generation.

GPT-4 does not have a built-in calculator, and those who want to use the system to generate accurate answers to math problems need to do extra coding work. Though OpenAI has not been forthcoming about the LLM’s training data, the company has been very excited about all the different tests it can pass with flying colors, such as the LSAT and Uniform Bar Exam. At the same time, ChatGPT has shown it can occasionally fail to spit out accurate code.