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

NotebookLlama: An open source version of NotebookLM

github.com

Post reply on HN
Print view View original

31–40 of 78 posts

Re: NotebookLlama: An open source version of NotebookLM

#31

Post by wodenokoto »

jrm4 wrote: post #23

Great to see this: Fellow tech-geeks, ignore the NotebookLM thing at your peril. NotebookLM, far and away, has been the "AI Killer App" for the VAST MAJORITY of bright-but-not-particularly-techy people I know. My 70ish parents and my 8 year old kid are both just blown away by this thing and can't stop playing with it. Edit: As someone pointed out below, I absolutely mean just the "podcast" thing.

As someone who doesn’t listen to podcasts what perils will I suffer from not making podcasts in notebookLM?

Re: NotebookLlama: An open source version of NotebookLM

#32

Post by albert_e »

rmorey wrote: post #14
ttul wrote: post #12

The more I listen to NotebookLM “episodes”, the more I am convinced that Google has trained a two-speaker “podcast discussion” model that directly generates the podcast off the back of an existing multimodal backbone. The two speakers interrupt and speak over each other in an uncannily humanlike manner. I wonder whether they basically fine tuned against a huge library of actual podcasts along with the podcast transcr…

I feel similarly about NotebookLM, but have noticed one odd thing - occasionally Host A will be speaking, and suddenly Host B will complete their sentence. And usually when this happens, it's in a way that doesn't make sense, because Host A was just explaining something to or answering a question of Host B. I'm actually not sure what to make of that, but it's interesting to note

I think this is an important enough quality that betrays that there are no two minds here creating 1+1=3.

One cheap trick to overcome this uncanny valley may be to actually use two separate LLMs or two separate contexts / channels to generate the conversations and take "turns" to generate the followup responses and even interruptions if warranted.

Might mimic a human conversation more closely.

Re: NotebookLlama: An open source version of NotebookLM

#33

Post by factsaresacred »

dartos wrote: post #29
jrm4 wrote: post #27

Earlier quoted context omitted.

Good question: I absolutely mean the podcast stunt.

Idk if I’d call it a killer app. The podcasts are grating to listen to and usually only contain very surface information I could gain from a paper’s abstract. It’s a wildly impressive technical achievement though.

It does have a tendacy to meander or spend too time reflecting on a topic instead of distilling the details. However the new ability to add a prompt improves this greatly.

Some instructions that worked for me:

- Specifics instead of high level

- Approach from non-critical perspective

- Dont be philosophical

- Use direct quotes often

- Focus on the details. Provide a lesson, not reflections

- Provide a 'sparknotes' style thorough understanding of the subject

Re: NotebookLlama: An open source version of NotebookLM

#34

Post by magic_hamster »

factsaresacred wrote: post #33
dartos wrote: post #29

Earlier quoted context omitted.

Idk if I’d call it a killer app. The podcasts are grating to listen to and usually only contain very surface information I could gain from a paper’s abstract. It’s a wildly impressive technical achievement though.

It does have a tendacy to meander or spend too time reflecting on a topic instead of distilling the details. However the new ability to add a prompt improves this greatly. Some instructions that worked for me: - Specifics instead of high level - Approach from non-critical perspective - Dont be philosophical - Use direct quotes often - Focus on the details. Provide a lesson, not reflections - Provide a 'sparknotes' st…

Oh, when was this added? I'll have to check it out.

Re: NotebookLlama: An open source version of NotebookLM

#36

Post by refulgentis »

famouswaffles wrote: post #22
swyx wrote: post #16

Earlier quoted context omitted.

> the more I am convinced that Google has trained a two-speaker “podcast discussion” model that directly generates the podcast off the back of an existing multimodal backbone. I have good and bad news for you - they did not! We were the first podcast to interview the audio engineer who led the audio model: https://www.latent.space/p/notebooklm TLDR they did confirm that the transcript and the audio are generated sepa…

Soundstorm is probably the TTS https://google-research.github.io/seanet/soundstorm/examples...

Really good catch. Ty.

Re: NotebookLlama: An open source version of NotebookLM

#37

Post by imjonse »

lelag wrote: post #9

Pretty weird choice of TTS engines. None of them are anywhere near state of the art as far as open TTS system goes. XTTSv2 or the new F5-TTS would have been much better choices.

From improvements needed on the page:

"Speech Model experimentation: The TTS model is the limitation of how natural this will sound. This probably be improved with a better pipeline and with the help of someone more knowledgable-PRs are welcome! :)"

Re: NotebookLlama: An open source version of NotebookLM

#39

Post by thomashop »

albert_e wrote: post #32
rmorey wrote: post #14

Earlier quoted context omitted.

I feel similarly about NotebookLM, but have noticed one odd thing - occasionally Host A will be speaking, and suddenly Host B will complete their sentence. And usually when this happens, it's in a way that doesn't make sense, because Host A was just explaining something to or answering a question of Host B. I'm actually not sure what to make of that, but it's interesting to note

I think this is an important enough quality that betrays that there are no two minds here creating 1+1=3. One cheap trick to overcome this uncanny valley may be to actually use two separate LLMs or two separate contexts / channels to generate the conversations and take "turns" to generate the followup responses and even interruptions if warranted. Might mimic a human conversation more closely.

Funnily, even two different LLMs, when put in conversation with each other, can end up completing each other's sentence. I guess it has something to do with the sequence prediction training objective.

Re: NotebookLlama: An open source version of NotebookLM

#40

Post by hitradostava »

dartos wrote: post #29
jrm4 wrote: post #27

Earlier quoted context omitted.

Good question: I absolutely mean the podcast stunt.

Idk if I’d call it a killer app. The podcasts are grating to listen to and usually only contain very surface information I could gain from a paper’s abstract. It’s a wildly impressive technical achievement though.

The point being made is that while this may be grating for you. It is magic for a large part of the population. This combined with chatgpt advanced voice mode shows a direction of travel for AI agents. It makes it possible to imagine a world where everyone has personalized tutors and that world isn't very far away.
Post reply on HN