Being interrupted is annoying. Apparently, even AI-generated podcast hosts agree.
Or so Google NotebookLM’s customers found. NotebookLM launched final yr and went viral for its characteristic that creates fully AI-generated podcast-like discussions from content material customers add, mentioned by chatty AI bots appearing like podcast hosts. In December 2024, NotebookLM launched a brand new characteristic known as “Interactive Mode” which permits the consumer to “call in” to the podcast and ask questions, primarily interrupting the AI hosts as they speak.
When the characteristic was first rolled out, the AI hosts appeared annoyed at such interruptions. They had been often giving snippy feedback to human callers like, “I was getting to that” or “As I was about to say,” which felt “oddly adversarial,” Josh Woodward, VP of Google Labs, defined to Ztoog.
So NotebookLM’s workforce determined that some “friendliness tuning” was so as, and posted a self-deprecating joke about it on the product’s official X account:
Woodward stated the workforce mounted the issue partly by learning how its personal members would reply interruptions extra politely.
“We tested a variety of different prompts, often studying how people on the team would answer interruptions, and we landed on a new prompt that we think feels more friendly and engaging,” he stated.
It’s not completely clear why the problem cropped up within the first place. Human podcast hosts generally show frustration when interrupted, which may find yourself in a system’s coaching information. A supply conversant in the matter stated this case more than likely stemmed from the system’s prompting design, not coaching information, nonetheless.
Regardless, the repair seems to be working. When Ztoog tried out Interactive Mode, the AI host did not sound annoyed however did specific shock, exclaiming “Woah!” earlier than politely asking the human to chime in.