Provides similar functionality to Google Gemini and OpenAI ChatGPT.

Claude 3's AI chatbot will now offer a "stop generating" option to disconnect it in the middle of a flow if you get the information you need, or simply don't want to deal with it any more.

As Anthropic prompt engineer Alex Albert shared on X, this update was born out of "countless requests" from users. Albert joked that it was Claude 3's "most important and revolutionary feature to date" and showed a screen capture of Claude 3 being asked to write a "really long and boring story" that "goes on and on."

Claude complied, and after a few paragraphs was stopped by a new "stop generating" command, waiting to be ready to receive another prompt. This is in contrast to the previous version, where the generation process had to be terminated before Claude 3 was ready to do anything else.

Albert's post is very cynical, but given how resource intensive AI generation is, this would save a lot of processing power.

Currently, you have to let Claude 3 finish its generation, which means a lot of wasted effort on behalf of chatbots for complex tasks that can actually be answered within the first paragraph.

We previously wrote about Claude 3 being the most human-like chatbot, but this is by no means a step in Anthropic's plan to make it a more organic chatbot.

Still, judging by the response to Albert's post on X, it looks like there is more to come. One user asked if an "edit user message" would be forthcoming, perhaps by adjusting the prompt mid-generation.

Albert responded with a "Soon" emoji, joking that the team "doesn't want to drop too many revolutionary features at once."

Ready to interrupt your chatbot or change your mind while it's running? Then Claude 3 may be the perfect fit.