What if ChatGPT could remember enough about what you were doing to help you pick up where you left off without a long recap? That’s the idea behind ChatGPT’s new opt-in Computer History feature, and we’ll look at the convenience it offers and the choices that come with it as we sit down and sync up with Rocket IT’s weekly technology update.

In this episode, you’ll hear more about:

• How Computer History helps ChatGPT understand what you’ve already been working on.
• Why someone might choose to give ChatGPT more context about their activity.
• What Computer History records and what it leaves out.
• How users can control which apps and websites are included.
• What to consider before using the feature with workplace or sensitive information.
• Why features like this could change how we interact with AI assistants.

Video Transcript

If you use ChatGPT while you work, there’s a good chance you’ve run into a pretty common problem. You spend time researching something, reading through documents, jumping between apps, and figuring out what you need. Then you open ChatGPT for help, and before it can do much of anything, you have to get it caught up.

That might mean copying and pasting information, uploading files, sharing links, or writing a detailed prompt explaining everything you’ve already done. It works, but sometimes getting the AI up to speed takes nearly as much effort as asking it for help in the first place.

Computer History is OpenAI’s attempt to close some of that gap. Right now, it’s available through ChatGPT on macOS, and when you choose to turn it on, ChatGPT and Codex can reference activity from apps and websites you select. The goal is to give the AI more background about what you’ve already been working on, so every interaction doesn’t have to begin from scratch.

Imagine you’ve spent part of your morning comparing options for a project, reading through a few websites, and working across different applications. Later, you want ChatGPT to help organize what you found or figure out your next steps. Instead of spending the first several minutes recreating all of that background, Computer History could give ChatGPT more of the information it needs to pick up where you left off.

And if you’re someone who already uses AI throughout the workday, that could be genuinely useful. A lot of the friction with AI isn’t necessarily getting it to answer a question. It’s giving it enough information to understand what you’re trying to accomplish in the first place.

Of course, the same thing that makes Computer History useful is also what makes it worth understanding before you turn it on. You’re allowing ChatGPT to remember more about your activity, so it’s important to know what that actually involves.

OpenAI says Computer History records what it calls interaction events from the apps and websites you choose. It doesn’t record screenshots, screen recordings, microphone input, or system audio, and private browsing isn’t included.

It’s also opt-in. You can choose which apps and websites are included, pause Computer History when you don’t want it running, review what appears in your timeline, and delete items. For ChatGPT Business and Enterprise, an administrator also has to make the feature available before individual users can choose to enable it.

Those controls are important because you probably don’t need every application on your computer to become part of an AI workflow. Maybe having ChatGPT remember activity from the websites you use for research would save you quite a bit of time. That doesn’t necessarily mean you’d want to include an application containing financial information, client records, or other sensitive material.

So rather than thinking about Computer History as something you either give access to everything or don’t use at all, it may be more helpful to think about what you actually want it to help with. Which apps or websites would provide useful information, and which ones don’t need to be part of the equation?

That distinction becomes even more important when you’re using a work computer. On your own device, the decision may mostly come down to your personal comfort level. At work, your organization may have policies around AI, client information, confidential data, or which services are allowed to interact with company systems.

So even if you see a productivity benefit, it’s still worth making sure the way you use the feature matches the rules your organization has in place. And if you’re responsible for those rules, Computer History is another example of why having a clear AI policy is becoming increasingly important.

If you do decide to use it, there’s also nothing wrong with starting small. You could enable it for the places where you see an obvious benefit, see whether it actually makes ChatGPT more useful, and adjust from there. Because the feature can be paused and its timeline reviewed, this doesn’t have to be a decision you make once and never think about again. And I think that’s what makes Computer History interesting beyond this one feature.

Most of us are used to working with AI by intentionally bringing information to it. We write the prompt. We upload the document. We paste in the information. Then the AI works with whatever we’ve decided to provide.

Computer History starts to shift that relationship. Instead of constantly rebuilding the background for every request, the assistant can have more continuity around the work you’ve already been doing.

That could make AI feel a lot more useful in everyday work. But it also means being a little more intentional about where that additional awareness is helpful and where it isn’t necessary.

So, I wouldn’t look at Computer History as something everyone needs to turn on, and I wouldn’t dismiss it simply because it keeps a history either. The better question is whether it solves enough of a problem for you to make the additional access worthwhile.

If it does, take advantage of the controls and give it access where there’s a clear benefit. If it doesn’t, you can leave it off. Because as AI assistants become better at understanding the work happening around us, getting more value from them doesn’t have to mean giving them access to more than they actually need. For help, contact Rocket IT using the link in this video’s description. And to stay up to date on trending technology news, hit that subscribe button and the bell to catch us on next week’s episode of Sync Up with Rocket IT.