For the "ask" phase, I feel like that the chat interface makes sense as the first step for the adjust phase because ChatGPT is a LLM, which works seamlessly with any natural language prompts.
But it's a bad interface for most applications. It took me out of context on the work I'm doing and forces me to describe what I am working towards in natural language. I will still use it now because it is a big step forward from Googling. But I think the bigger challenge (which brings the much better experience) lies in how we could deeply integrate the iterative creation process with ChatGPT into the app workflow itself.
Also, I wanted to add that I see two big obstacles that are difficult to overcome unless we fundamentally change how the current generative AI works:
1. Generative AI is inherently non-deterministic. We have no guarantee if the final product it generates works 100% based on the provided prompt.
2. Generative AI is inherently out-of-date. There are limited improvements on very specific apps that allows an interface for AI to grab its updated information. But its difficult to imagine us having a new iteration of GPT daily or even monthly
2 comments
[ 2.8 ms ] story [ 15.7 ms ] threadBut it's a bad interface for most applications. It took me out of context on the work I'm doing and forces me to describe what I am working towards in natural language. I will still use it now because it is a big step forward from Googling. But I think the bigger challenge (which brings the much better experience) lies in how we could deeply integrate the iterative creation process with ChatGPT into the app workflow itself.
1. Generative AI is inherently non-deterministic. We have no guarantee if the final product it generates works 100% based on the provided prompt.
2. Generative AI is inherently out-of-date. There are limited improvements on very specific apps that allows an interface for AI to grab its updated information. But its difficult to imagine us having a new iteration of GPT daily or even monthly