It’s annoying to be interrupted. Apparently, even AI-generated podcast hosts agree.

Or so Google NotebookLM users discovered. NotebookLM was launched last year and went viral for its feature that creates fully AI-generated podcast-like discussions from content users upload, discussed by chatty AI bots that act like podcast hosts. In December 2024, NotebookLM launched a new feature called “Interactive Mode” which allows the user to “call” the podcast and ask questionsessentially interrupting the AI ​​hosts while they are talking.

When the feature was first launched, AI hosts seemed to resent such interruptions. Sometimes they give snippy comments to people who call in like, “I got that” or “Like I said,” which feels “weirdly counterintuitive,” explained Josh Woodward, VP of Google Labs. , in TechCrunch.

So the NotebookLM team decided that some “friendly tuning” was in order, and posted a self-deprecating joke about it on the product’s official X account:

Woodward said the team fixed the problem in part by studying how its own members responded to interruptions more politely.

“We tried a variety of different prompts, constantly studying how people on the team respond to interruptions, and we came up with a new prompt that we think feels more friendly and attractive,” he said.

It’s not entirely clear why the issue arose in the first place. Human podcast hosts sometimes show frustration when interrupted, which can be achieved in a system’s training data. A source familiar with the matter said that this case likely stems from the inductive design of the system, not the training data, however.

Regardless, the fix appears to be working. When TechCrunch tested the Interactive Mode, the AI ​​host wasn’t annoyed but expressed surprise, exclaiming “Woah!” before politely asking the person to speak.

TechCrunch has a newsletter focused on AI! Sign up here to get it in your inbox every Wednesday.