You can finally make Claude 3 shut up — Anthropic adds stop button to its chatbot
Time to quieten Claude 3.
Anthropic has finally released on of the most asked for features for Claude 3, bringing it inline with similar offerings from Google Gemini and OpenAI ChatGPT.
Claude 3 AI chatbot will now offer a "stop generating" option to cut it off mid-flow if you get the information you need - or just don't want to deal with it anymore.
As shared by Alex Albert, Anthropic's prompt engineer on X, the update was borne from "countless requests" from users. Albert jokes that it's Claude 3's "most important and revolutionary feature yet", with a screen capture showing Claude 3 being asked to write a "really long, boring story" that "goes on and on and on".
Claude obliges, and after a couple of paragraphs is stopped by the new "stop generating" command and waits ready to receive another prompt. That's in contrast to prior versions which needed Claude 3 to finish its generative process before being ready to do anything else.
What next for Claude 3?
We have finally done it. After all this time and due to countless requests from our users, we've shipped what I think is our most important and revolutionary feature yet.You can now interrupt Claude's yapping with our new stop generation button! pic.twitter.com/LdXchaRdGUApril 24, 2024
As much as Albert's post is very tongue-in-cheek, this could save a lot of processing power given how resource-intensive AI generation can be.
At present, you'd need to let Claude 3 finish its generation, which for complex tasks that can actually be answered within the first paragraph means a lot of wasted effort on the chatbot's behalf.
We've previously written about how Claude 3 is the most human-like chatbot out there, and this is certainly a never step in Anthropic's plan to make it much more organic.
Sign up to get the BEST of Tom's Guide direct to your inbox.
Here at Tom’s Guide our expert editors are committed to bringing you the best news, reviews and guides to help you stay informed and ahead of the curve!
Still, from the responses to Albert's post on X, there's more to come. One user asked if "editing user messages", presumably by adjusting prompts mid-generation, would be coming.
Albert responded with the "Soon" emoji, joking that the team "doesn't want to drop too many revolutionary features at once."
Are you ready to interrupt your chatbot, or change your mind while it works? Then Claude 3 might be best for you.
More from Tom's Guide
A freelance writer from Essex, UK, Lloyd Coombes began writing for Tom's Guide in 2024 having worked on TechRadar, iMore, Live Science and more. A specialist in consumer tech, Lloyd is particularly knowledgeable on Apple products ever since he got his first iPod Mini. Aside from writing about the latest gadgets for Future, he's also a blogger and the Editor in Chief of GGRecon.com. On the rare occasion he’s not writing, you’ll find him spending time with his son, or working hard at the gym. You can find him on Twitter @lloydcoombes.