Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

NotebookLM's automatically generated podcasts are surprisingly effective

simonwillison.net

Post reply on HN
Print view View original

21–30 of 511 posts

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#21

Post by timoth3y »

NotebookLM's is incredibly good at generating the affect and structure of a quality podcast.

This is in-line with all art, music, and video created by LMM at the moment. They are imitating a structure and affect, the quality of the content is largely irrelevant.

I think the interesting thing is that most people don't really care, and AI is not to blame for that.

Most books published today have the affect of a book, but the author doesn't really have anything to say. Publishing a book is not about communicating ideas, but a means to something else. It's not meant to stand on its own.

The reason so much writing, podcasting, and music is vulnerable to AI disruption is that quality has already become secondary.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#22

Post by bbor »

whyenot wrote: post #17

This is amazing. I uploaded the instruction manual for a Scholander pressure chamber (a piece of equipment for measuring plant moisture stress) and made a podcast from it. The information in the podcast was accurate, it included some light banter and jokes, while still getting across the important topics in the instructions. I don't know what I would use a podcast like this for, but the fact that something like this…

Yeah I totally get people’s criticisms that the podcasts aren’t quite human-expert-level in terms of symbolic reasoning, but this still blows my mind. The intuitive skill these show, not to mention the ability to accurately (again, if shallowly) parse and transform huge bodies of content in seconds is absolutely scary, IMO.

I’d feed it the Singularity paper, but I’m not sure I need that extra boost of anxiety these days…

https://edoras.sdsu.edu/~vinge/misc/singularity.html

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#23

Post by hu3 »

This is better than I expected.

I sent the podcast audio to friend, and English is not their first language. Without telling them it was AI generated.

They found it entertaining-worthy enough to listen to the end.

Sure it needs more human unpredictably and some added goofiness. Maybe some interruptions because humans do that too. But it's already not-bad.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#25

Post by ranger_danger »

JonathanFly wrote: post #18
ranger_danger wrote: post #5

Earlier quoted context omitted.

I was blown away by how impressive it was. I honestly thought it was real. I still can't believe these realistic audio capabilities are not being used for pure evil everywhere we look. > like thrown into every sentence I think that's actually part of why it sounds real, because tons of people do actually talk like that. To me what would make it even better is the ability to throw in random jokes and utilize informati…

Bark can sound as good, but Google is using SoundStorm which was specifically trained on dialogs. Surprisingly Bark can even sort of match it without being trained to do so, but not reliably. ( https://x.com/jonathanfly/status/1675987073893904386 ) And SoundStorm has more than twice the context window of Bark so dialogs are a tight fit.

I just tried the default bark.cpp example from the github readme, and to me it still doesn't sound close enough to realistic, and the audio quality itself was a bit scratchy... maybe I'm doing something wrong.

When I tried my own text with it, it went completely off the rails... skipping completely over random words, and also switching to different voices in the middle of a sentence. Trying to run the large model also crashed entirely.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#26

Post by hn_throwaway_99 »

OK, this is pretty amazing, but is there a "Valley Girl" setting in NotebookLM somewhere? In the sample given in this article, both of the "podcasters" had to add a "like", like every 5 seconds. I couldn't take it:

> this tech is just like leaps and bounds of where it was yesterday like we're watching it go from just spitting out words to like...

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#27

Post by abraxas »

ColinEberhardt wrote: post #3

I don’t think this is all that impressive, the generated podcast is pretty shallow - lots of ‘whoa meta’ and the word ‘like’ thrown into every sentence. Yes, it will generate a middle-of-the-road waffling podcast, but not one with any real depth.

At the risk of sounding cliche but this is the worst this tech will ever be. I find it equally scary and fascinating what lies ahead.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#28

Post by shreezus »

ColinEberhardt wrote: post #3

I don’t think this is all that impressive, the generated podcast is pretty shallow - lots of ‘whoa meta’ and the word ‘like’ thrown into every sentence. Yes, it will generate a middle-of-the-road waffling podcast, but not one with any real depth.

I think it’s “impressive” the first time you use it, but with subsequent runs it’s evident how formulaic it is. The end result, the personalities of the podcast “hosts” and their interactions are similar regardless of the context of inputs.

Basically it’s a neat party trick at the moment. I do hope to see it improve however!

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#29

Post by NitpickLawyer »

wenbin wrote: post #20

Do people actually enjoy this type of AI-generated "podcasts" vs human-produced shows? As a podcast listener, I lose interest if I can tell the audio is AI-generated...

If you had received one of these podcasts, say 3-5 years ago, I guarantee you wouldn't be able to tell it's AI generated. And I'm willing to bet it's valid for 90%+ of the people here, even those heavily involved in the field. The quality of the voices, the mimicking of umms, and ahhs, the subtle speaking over each other, they really are extremely impressive.

If you want you can do a test with people that haven't heard about the tech. Have it generate something you know they'll enjoy, maybe 2-3 min long, and have them listen to it without knowing it's AI generated. Ask them about the subject, and see if anyone mentions anything about being fake. You'll be surprised.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#30

Post by abraxas »

wenbin wrote: post #20

Do people actually enjoy this type of AI-generated "podcasts" vs human-produced shows? As a podcast listener, I lose interest if I can tell the audio is AI-generated...

would you know it's AI if you didn't know going into it?
Post reply on HN