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

121–130 of 511 posts

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#121

Post by djur »

infogulch wrote: post #11
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.

Look I agree with you at a certain level, maybe it can't emulate deep conversations about big topics (maybe it can, I haven't seen an attempt...), but a vast vast majority of podcasts and radio shows are just like this: shallow and incredibly simplified with no more than a nod to the underlying concepts. 70% personality, 20% dumb analogies that the producer thought up in thirty minutes, and Honestly, given the person…

Kind of feels like looking at an overflowing landfill and thinking "I wonder if we can invent a robot that just generates new trash directly into the landfill".

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#122

Post by FranzFerdiNaN »

sqeaky wrote: post #55
richardw wrote: post #45

Earlier quoted context omitted.

I think and hope that you're wrong. There's always been cheese, and there's a lot of it now. But there is still a market for top-notch insight. For example, Perun. This guy delivers an hourlong presentation on (mostly) the Ukraine-Russia war and its pure quality. Insights, humour, excellent delivery, from what seems to be a military-focused economist/analyst/consultant. We're a while away from some bot taking this ki…

I know I'm not the first to say this, but I think what's going on is that these AI things can produce results that are very mid. A sort of extra medium. Experts beat modern LLMs but modern llms are better than a gap. If you just need voice discussing some topic because that has utility and you can't afford a pair of podcasters (damn, check your couch cushions) then having a mid podcast is better than having no podcas…

> I know I'm not the first to say this, but I think what's going on is that these AI things can produce results that are very mid. A sort of extra medium. Experts beat modern LLMs but modern llms are better than a gap.

I've seen people manage to wrangle tools like Midjourney to get results that surpass extra medium. And most human artists barely manage to reach medium quality too.

The real danger of AI is that, as a society, we need a lot of people who will never be anything but mediocre still going for it, so we can end up with a few who do manage to reach excellence. If AI causes people to just give up even trying and just hit generate on a podcast or image generator, than that is going to be a big problem in the long run. Or not, and we just end up being stuck in world that is even more mediocre than it is now.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#123

Post by goodpoint »

hn_throwaway_99 wrote: post #26

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...

Instead of teaching AI to write so poorly we should be teaching people to write and speak properly.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#124

Post by oxym0ron »

theptip wrote: post #85
richardw wrote: post #45

Earlier quoted context omitted.

I think and hope that you're wrong. There's always been cheese, and there's a lot of it now. But there is still a market for top-notch insight. For example, Perun. This guy delivers an hourlong presentation on (mostly) the Ukraine-Russia war and its pure quality. Insights, humour, excellent delivery, from what seems to be a military-focused economist/analyst/consultant. We're a while away from some bot taking this ki…

This is true but the quality frontier is not a single bar. For mainstream content the bar is high. For super-niche content, I wouldn’t be surprised if NotebookLM already competes with the existing pods. This will be the dynamic of generated art as it improves; the ease of use will benefit creators at the fringe. I bet we see a successful Harry Potter fanfic fully generated before we see a AAA Avengers movie or simila…

I would say the opposite is true - mainstream cares much less about the quality content but more about catchy headline.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#125

Post by firtoz »

djur wrote: post #118
famahar wrote: post #105

I uploaded my detailed game design document for a project I've been working on in my free time and it was kind of a weird confidence boost. The two hosts seem to treat ideas like their the most insightful relevatory information they've ever heard. After a few uploads of other documents you start to notice the same overly surprised tone.

This seems to be a common trait of a lot of the more "aligned", "helpful" LLMs out there. You can drop any random excerpt from your diary into ChatGPT and it will tell you about how brilliant, sensitive, and witty you are. It's really quite sickening.

Reminds me of my father who'd tell every kid that they're a genius, including myself. It got me motivated to try things, but whenever there was a failure, I felt terribly betrayed.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#126

Post by michaelteter »

I tried it with my resume, and the results surprised me. My observations:

- They do some interesting communication chicanery where one host asks a question to me (the resume owner); I'm not there, so obviously I can't answer. But then immediately the co-host adds some commentary which sort of answers while also appearing to be a natural commentary. The result is that the listener forgets that Michael never answered the question which was directly asked to him. This felt like some voodoo to me.

- Some of the commentary was insightful and provided a pretty nice marketing summary of ideas I tried to convey in my terse (US style) resume.

- Some of the comments were so marketing-ey that I wanted to gag. But at the same time, I recognize that my setpoint on these issues is far toward the less-bs side, and that some-bs actually does appeal to a lot of people and that I could probably play the game a little stronger in that regard.

Overall I was quite impressed.

Then for fun I gave it a Dutch immigration letter, one which said little more than "yeah you can stay, and we'll coordinate the document exchange". They turned that into a 7 minute podcast. I only listened to the first 30 seconds, so I can only imagine how they filled the rest. The opener was funny though: "Have you ever thought of just chucking it all and moving to a distant land?" ... lol. Not so far off the mark, but still quite funny to come up with purely from an administrative document.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#127

Post by theptip »

slhck wrote: post #88

Gave it a bunch of technical papers and standards, and while it's making up stuff that just isn't true, this is to be expected from the underlying system. This can be fixed, e.g., with another internal round of fact-checking or manual annotations. What really stands out, I think, is how it could allow researchers who have troubles communicating publicly to find new ways to express themselves. I listened to the podcas…

The underlying NotebookLM is doing better at this - each claim in the note cites a block of text in the source. So it’s engineered to be more factually grounded.

I would not be surprised if the second pass to generate the podcast style loses some of this fidelity.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#128

Post by kombookcha »

djur wrote: post #118
famahar wrote: post #105

I uploaded my detailed game design document for a project I've been working on in my free time and it was kind of a weird confidence boost. The two hosts seem to treat ideas like their the most insightful relevatory information they've ever heard. After a few uploads of other documents you start to notice the same overly surprised tone.

This seems to be a common trait of a lot of the more "aligned", "helpful" LLMs out there. You can drop any random excerpt from your diary into ChatGPT and it will tell you about how brilliant, sensitive, and witty you are. It's really quite sickening.

Honestly, it's obviously horrendously gag-worthy and everything, but also kind of funny that there is so much bullshit marketing copy out there that LLM's invariably converge on this inspirational Stanford application letter / upbeat linkedin influencer tone of voice, and just apply it to everything.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#129

Post by ileonichwiesz »

djur wrote: post #118
famahar wrote: post #105

I uploaded my detailed game design document for a project I've been working on in my free time and it was kind of a weird confidence boost. The two hosts seem to treat ideas like their the most insightful relevatory information they've ever heard. After a few uploads of other documents you start to notice the same overly surprised tone.

This seems to be a common trait of a lot of the more "aligned", "helpful" LLMs out there. You can drop any random excerpt from your diary into ChatGPT and it will tell you about how brilliant, sensitive, and witty you are. It's really quite sickening.

Well, an LLM doesn’t have the capability to like anything more than anything else. It doesn’t really matter to GPT if your diary excerpt is the worst piece of writing ever written, or the most brilliant - it’ll just tell you what you want to hear and that’s that.

Re: NotebookLM's automatically generated podcasts are surprisingly effective

#130

Post by janoc »

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…

Well, yes. Replace the various music and book publishing mills with LLMs for even more low quality drivel filling the marketplaces because now even the already low barrier of having to actually pay someone to produce it will be removed.

That's definitely going to be an improvement. Not.

Post reply on HN