Hacker News Reader

Parent Full thread

iandanforth

This feels like it owes more to LangChain than a link at the bottom of the page.

Compare their prompt:

https://github.com/microsoft/visual-chatgpt/blob/main/visual...

With that of the LangChain ReAct conversational agent:

https://github.com/hwchase17/langchain/blob/master/langchain...

Also it seems appropriate to cite the original ReAct paper (from Google mainly)

https://arxiv.org/abs/2210.03629

View on HN

I think you mean here: https://github.com/hwchase17/langchain/blob/master/langchain...

Fixed thanks!

Yes, in this integration GPT3 connects with the image space only through text and doesn't consume or emit image space embeddings / tokens. With GPT4 that perception modality will be available directly in the model. And it'll be a better integration.

How do you know? I’ve seen multiple claims about GPT4 online but people never say where they came from.

Reply on news.ycombinator.com