Weaviate Podcast cover image

Stephanie Horbaczewski and Gunjan Bhattarai on Vody - Weaviate Podcast #53!

Weaviate Podcast

00:00

How GPT-4 Can Generate Text Based on Visionless Input

In instruct flip, essentially that would be sort of like taking these ideas to the LLM space. GPT-4 prove that it's possible to build a multi-model LLM that takes visionless input or Texas input and is able to generate text based on that. The idea of using instruction tuning to generalize to new sorts of tasks is something that allows for scalability. It makes us really excited about the potential of what these models can be used for.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app