"On Thursday, OpenAI announced that ChatGPT users can now branch conversations into multiple parallel threads, serving as a useful reminder that AI chatbots aren't people with fixed viewpoints but rather malleable tools you can rewind and redirect. The company released the feature for all logged-in web users following years of user requests for the capability. The feature works by letting users hover over any message in a ChatGPT conversation, click "More actions," and select "Branch in new chat.""
"Think of it almost like creating a new copy of a "document" to edit while keeping the original version safe-except that "document" is an ongoing AI conversation with all its accumulated context. For example, a marketing team brainstorming ad copy can now create separate branches to test a formal tone, a humorous approach, or an entirely different strategy-all stemming from the same initial setup."
OpenAI enabled ChatGPT users to branch conversations into multiple parallel threads, rolling the feature out to all logged-in web users. Users can hover over any message, choose "More actions," and select "Branch in new chat" to create a new thread that contains all prior conversation history up to that point while keeping the original conversation intact. The branching mechanism functions like copying an ongoing AI conversation to test alternate approaches without losing context. The feature removes the prior need to overwrite prompts or start fresh to try different strategies, enabling parallel what-if exploration. A 2024 study from Tsinghua University and Beijing Institute of Technology found that linear dialogue interfaces increase cognitive load in multi-layer tasks such as brainstorming, structured learning, and large project analysis.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]