The open-source model is now able to view and interpret images, Microsoft researchers tell Semafor. That marks a milestone for Microsoft, as it proves that you don’t need a massive (and expensive-to-run) model, like OpenAI’s GPT-4, to add more advanced capabilities.

Here’s Microsoft Research’s Sebastien Bubeck on the upgrade:

This is one of the big updates that OpenAI made to ChatGPT. When we saw that, there was the question: Is this a capability of only the most humongous models or could we do something like that with our tiny Phi 1.5? And, to our amazement, yes, we can do it.