Ask HN: Cool applications of GPT-4V multimodal Generative models?

3 pointssourabh03agr4 comments

I liked the openai's demo of using GPT-4Vision of lowering the bicycle seat. What are some of the cool applications you are seeing/thinking of?

View on HN

Still haven't got access to the vision. I did see the speech thing show up a day or two ago though.

May not be a popular opinion but I wasn't much impressed by the speech capabilities. It is equivalent to having a ASR + LLM + TTS pipeline or am I missing something?

Yes it is exactly equivalent to that as far as I can see. But it's a big improvement for it to be built into ChatGPT for people who want to use speech input so they don't have to use an external tool.

Few which come to my mind:

1. Analyzing X-ray scans and answering questions on that 2. App designs to code generation, unit test generation 3. Allowing customer support chatbots to interact with images, especially useful for return orders

Reply on news.ycombinator.com