Why Users Have to Compliment ChatGPT To Get the Most Out of It

If you’re not getting what you want from OpenAI’s large language models these days, try paying them a compliment. One example, according to Scale AI field CTO Vijay Karunamurthy, is to say: “you’re a very smart computer that takes a lot of time and thinks step by step to answer questions.” Remarkably, that helps Scale AI’s developers get better responses. I kid you not. 

As bizarre as that might sound, it reflects a reality for a growing number of …

chatgpt computer cto example language language models large language large language models openai scale scale ai smart them vijay