- OpenAI added a new feature to ChatGPT that allows users to interrupt the AI’s response
- Users can write context or corrections to a prompt without restarting, using the “Update” button
- The feature is particularly aimed at those using GPT-5 Pro or Deep Research
Accidentally submitting a prompt to ChatGPT only to realize that you forgot to include some details or copied the wrong phrase from a website is a fairly common occurrence. Even so, it’s a real pain if you’re using the GPT-5 Pro model or ChatGPT’s Deep Research feature, as they take much longer to respond and you might have a limited number of prompts to send.
This should be less of a problem now that OpenAI allows ChatGPT users to interrupt the chatbot mid-response. During the minutes the AI is compiling a response, you can add new information and redirect its reasoning without having to start over. It’s a way to direct the conversation in real time.
While the AI is thinking about how to respond to your query, you can click “Update” in the sidebar and add any new context or clarification, then watch the AI immediately adjust what it says.
No reboot required. You can simply change ChatGPT’s mind while it’s still writing a response.
You can now abort long-running queries and add a new context without restarting or losing progress. This is especially useful for refining deep searches or GPT-5 Pro queries, as the model will adjust its response based on your new requirements. Just hit update in the sidebar and… pic.twitter.com/kESrkU9hc9November 5, 2025
In practice, the ability to edit an intermediate response can save a lot of time for researchers and analysts using ChatGPT for in-depth, multi-step queries. Imagine someone is writing a data analysis report and realizing halfway through that a key source was out of date.
Before this update, they would have to stop the model, rewrite their query, and run the whole thing again. Now they can simply say “replace 2022 with 2024 data” and watch the text update accordingly.
It’s a small miracle for anyone who has ever sat through a long, overconfident explanation of AI, waiting for the model to be finished just so they can correct a false premise at the beginning. For a predictive text-based system, this marks a shift from simple back-and-forth messaging to a more interactive format.
Real-time AI adjustments
Reducing the time wasted by errors in a prompt or AI understanding it is definitely something ChatGPT users will appreciate. The update also continues ChatGPT’s gradual evolution towards a more adaptive service.
Since GPT‑4, users can provide follow-up prompts, but the flow has always taken turns. The continuous, layered feedback loop is more useful because you are no longer waiting for your turn to speak. The AI listens while it writes.
In a sense, OpenAI gives ChatGPT a sense of conversational humility. Previous models were known to move forward, even when they misread a question or misunderstood the context. The update doesn’t make the AI self-aware, of course, but it does allow it to self-correct in a way closer to true collaboration with a person.
And of course you can too follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
The best business laptops for every budget
