Screen Sharing for Windows and Web App

The screen sharing is great on my iPhone but I can get a lot more use out of it on my Windows machine.

Currently resorting to Gemini Experiments to achieve this and waiting not so patiently for OpenAI to add this feature across the different platforms.

I love the innovation at OpenAI but sometimes the selective rollout of features to Mac OS only or Web App only or Mobile only is stifling my creativity. :slight_smile:

I have found sharing my screen to be a great way to learn how to use a new piece of software like Figma and even when it doesn’t know everything, it thinks more logically than I do about where a feature or setting might be hidden. It’s like having a tutor sitting next to you while you learn.

I assume this is coming but it’s been a minute and I’m starting to worry that it’s not going to reach Windows.

I think they’re holding this back because of the potential bandwidth impact. However, I truly believe they should make this available—it would be life-changing. Currently, only Google Studio offers this functionality.

That said, I definitely think it should be available in some capacity, at least for those spending $200 a month, until they’re able to roll it out more broadly.

Agreed, this has been the main use case for me with Google Gemini Studio.

Some of my greatest aha moments have happened sharing my computer screen as I work through a problem. So much easier to show and tell rather than describe my issue.

I’m a plus user, but this would make me pay for pro if it was available. That said, I hope it rolls out to all users. I wonder how it works in terms of bandwidth, a) it’s got the stream the video into the LLM and then b) how much processing does it do based on what it sees in terms of tokens. It would be interesting to know.

I guess while it’s available on the mobile app, people likely aren’t using it for long periods on their phones.

Microsoft Copilot now offers it for free too.

I’m surprised this still hasn’t been discussed much or added to the ChatGPT web and Desktop. This is the one thing I use Gemini for the most, and if OpenAI are serious about trying to prevent Gemini running away with the gold medal over the next few years, it’s features like this that can make the difference.

Literally my thoughts. At this point even copilot supports vision + screen highlighting/boxing if you’re pc supports copilot ai.

Thank you for taking the time to share this feature request. We appreciate and value your feedback. While we can’t promise implementation or provide a timeline, we’re grateful you shared it with us. We’re closing this topic while keeping it visible for reference.