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

91–100 of 511 posts

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#91

Post by juliushuijnk »

I fed it some info about my UX mobile app. Some parts are very cringe, extremely positive, but in the end it went on to brainstorm a potential 'next step' feature that was quite creative; letting end-users test-out prototypes during the wire-framing process. Also some more marketing-like text like "It's like drawing on napkin, but the napkin in your phone". I like that.

So as a brainstorming tool, it's a nice low-effort way to get some new perspectives. Compared to the chat, where you have to keep feeding it new questions, this just 'explores' the topic and goes on for 10 minutes.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#92

Post by rcarmo »

Reminds me of Futurama news stories. Actually, what if NotebookLM could be customized to generate podcasts voiced by Morbo the Annihilator and his co-host Linda van Schoonhoven?

Still, I don’t hold much confidence on podcasts as knowledge transfer tools. It’s a nice gimmick with great voice synthesis, but it feels formulaic and a bit stilted from a knowledge navigation perspective.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#93

Post by JonathanFly »

peutetre wrote: post #36
timoth3y wrote: post #21

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, b…

But why would I buy those books or listen to those podcasts that are synthetic affectations of no substance?

>But why would I buy those books or listen to those podcasts that are synthetic affectations of no substance?

A randomly selected NotebookLM podcast is probably not substantial enough on its own. But with human curation, a carefully prompted and cherry-picked NotebookLM podcast could be pretty good.

Or without curation, I would use this on a long drive where audio was the only option to get a quick survey of a bunch of material.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#94

Post by JonathanFly »

vochsel wrote: post #51

They've really nailed the back and fourth of the two speakers! It would be interesting to know if it's multimodal voice, or just clever prompting and recombining... I added single voice podcasts to Magpai after seeing how useful this was. Allows for a bit more customisation of the podcast too https://www.youtube.com/watch?v=OEsh9MlbA6s I've got a daily podcast of hackernews being generated here too: https://www.magpa…

It's almost certainly Google SoundStorm, a traditional TTS trained on dialogs from last year: https://x.com/jonathanfly/status/1675987073893904386

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#97

Post by probably_wrong »

GaggiX wrote: post #76
Ardren wrote: post #67

Earlier quoted context omitted.

Because they assumed that there was a good reason that their friend sent it!? I had a friend who did the same to me, I was sent a message asking my opinion on a tech topic. I spent 30min researching/reading to make sure my reply was accurate and then found out the question was generated by a LLM, and he just wanted to show off how good a LLM was. It will color every interaction you have with that person...

If it was vomit, it will be recognized quickly, AI or not, not an hour of listening for sure; yes, even if it was sent by a friend.

I think you are leaving the human out of the loop. When a friend of mine recommends me something I'll lower my skepticism because I'm assuming my friend would not send me garbage.

If a random podcaster says "I've proved that P=NP" I'd say "no you didn't", but if a math professor sends me that same link I'll keep listening to see where this goes. And I've definitely read texts making wild assertions that only at the end were revealed as hit pieces and/or propaganda.

Post reply on HN