<a href="http://musingsaboutlibrarianship.blogspot.com/p/subscribe-by-email.html">(Subscribe by email)</a>

Aaron Tay

I was asked to give a talk at CILIP Conference 2023 for the Data &amp; AI panel. I was given 10 minutes to send a recording which I eventually delivered.  But here's an extended 40-minute recording before I cut it down. As I was just practicing, the delivery might not be the best, and in fact the final 10-minute version might be better!

Recorded extended talk - The possible impact of AI on search and discovery​

In the last blog post , I argued that despite the advancements in AI thanks to transformer based large language models, most academic search still are focused mostly in supporting exploratory searches and do not focus on optimizing recall and in fact trade off low latency for accuracy.

Undermind.ai - a different type of AI agent style search optimized for high recall?

Audio Overviews in Google NotebookLM is making waves online. When I first tried it, it was a "wow" moment for me. The last time I felt that way was trying Perplexity.ai in late 2022 and realizing that search engines could now return answers (with citations) instead of just potentially relevant links and I realized this would be a huge paradigm shift.

Audio Overviews in Google Notebook LM made me go wow....

I've watched with interest, as academic search engines use AI to improve searching.  Elicit is probably currently the leading example of this, using transformer based language models to

A conceptual view of information retrieval - can we do better with AI?

One of the tricks about using the newer "AI powered" search systems like Elicit, SciSpace and even JSTOR experiment search is that they recommend that you type in your query or what you want in full natural language and not keyword search style (where you drop the stop words) for better results. So for example do

Why entering your query in natural question leads to better result than keyword searching with the latest AI powered (Dense retrieval/embedding models) search

I've spent a large part of my career as an academic librarian studying the question of discovery from many angles.

How learning evidence synthesis (systematic reviews etc) changed the way I search and some thoughts about semantic search as a complement search technique

Note: This is a lightly edited piece of something I wrote for my institution What is Google’s Search Generative Experience (SGE)?   In past ResearchRadar pieces, we have discussed about how search engines both general (e.g. Bing Chat, Perplexity) and academic (e.g Elicit, Scite Assistant, Scopus (upcoming)) are integrating search with generative AI (via Large Language Models) using techniques like RAG (Retrieval Augmented Generation).  But what

Google’s Search Generative Experience (SGE) is now available in 120+ countres. What you need to know

A decade ago in 2012, I observed how the dominance of Google had slowly affected how Academic databases and OPACs/ catalogues (now discovery services) work.

JSTOR generative AI pilot - Or is Semantic Search coming for academic databases?

On September 2023, OpenAI announced that ChatGPT Plus would be enhanced in three ways  1. It would allow you to speak directly with GPT and it would also be able to reply in voice  2. It would be able to create images using DALL-E 3, OpenAI's image generation model  3. It would be able to accept image inputs  Since I finally gained access to these features, I will briefly review them with my thoughts on how impactful they might be for

ChatGPT Plus - new DALL-E 3 (image creation) &amp;  Vision (image recognition) capability - A quick overview &amp; why I am disappointed.

List of academic search engines that use Large Language models for generative answers (for the latest version - see this page)
<strong>
</strong>
This is a non-comprehensive list of academic search engines that use generative AI (almost always Large language models) to generate direct answers on top of list of relevant results, typically using Retrieval Augmented Generation (RAG) Techniques. We expect a lot more!

List of academic search engines that use Large Language models for generative answers and some factors to consider when using

One of the earliest themes of this blog was to track tools that not only helped with discovery but also with delivery, helping users to gain access to full-text via institution subscriptions (and of course via Open Access) even if they did not start off the library homepage.

Two new browser extensions that help with delivery or access - ebsco passport and GetFTR browser extension and other developments

As academic search engines and databases incorporate the use of generative AI into their systems, an important concept that all librarian should grasp is that of retrieval augmented generation (RAG).   You see it in use in all sorts of "AI products" today from chatbots like Bing Copilot, to Adobe's Acrobat Ai assistant that allow you to chat with your PDF.

Retrieval Augmented Generation and academic search engines - some suggestions for system builders

Let's be clear here,
<i>
 Google Scholar is ill designed for use for systematic reviews
</i>
. I am not trying to argue otherwise. (Obligatory warning, I am not a real systematic review librarian) But why exactly?

Why EXACTLY is Google Scholar bad for evidence synthesis, systematic reviews?

<b>
 Warning : I am not a information retrieval researcher, so take my blog post with a pinch of salt
</b>
In my last blog post, I described a simplified description of a framework for infomation retrieval from the paper -

Deep dive into AI powered embedding based search - sparse vs dense embeddings

Can Semantic Search be more interpretable? COLBERT, SPLADE might be the answer but is it enough?

I have been writing about what I call citation based literature mapping tools for over 5 years now, starting from Citation Gecko in 2018.

All about citation chasing and tools that does citation chasing like Citation Gecko, Connected papers, Research Rabbit, LitMaps and more

<em>
 Earlier related pieces - How Q&amp;A systems based on large language models (eg GPT4) will change things if they become the dominant search paradigm - 9 implications for libraries
</em>
In the ever-evolving landscape of information retrieval and library science, the emergence of large language models, particularly those based on the transformer architecture like GPT-4, has opened up a Pandora's box of possibilities and challenges.

Things I am still wondering about generative AI + Search in 2024 - impact of semantic search, generation of answers with citations and more..

Source Ex Libris surprised us by suddenly releasing Primo Research Assistant to production on September 9, 2024  (when the earlier timeline was 4Q 2024 with some believing it might even be delayed). Despite the fact that there are so many RAG (retrieval augmented generation) academic search systems today that generate answers from search, this is still quite a significant event to be worth covering in my blog. Why?

Primo Research Assistant launches- a first look and some things you should know

I recently watched a librarian give a talk about their experiments teaching prompt engineering. The librarian drawing from the academic literature on the subject (there are lots!), tried to leverage "prompt engineering principles" from one such paper to craft a prompt and used it in a Retrieval Augmented Generation (RAG) system, more specifically, Statista's brand new "research AI" feature.

Prompt engineering with Retrieval Augmented Generation systems - tread with caution!

IP and ethical issues surrounding the use of content in Large Language Models (LLMs) have sparked significant debate, but I’ve mostly stayed out of it as this isn’t my area of expertise, and while there’s much to discuss and many legal opinions to consider, ultimately, the courts will decide what’s legal. However, for those interested in exploring this topic further, I recommend Peter Schoppert’s AI &amp; Copyright substack.

AI &amp; Retrieval augmented generation search - the content problem -reactions from librarians, authors and publishers &amp; thoughts on tradeoffs

I've been a subscriber of OpenAI's ChatGPT plus for a while though I have been struggling to justify it to myself for a while until recently.

GPT4+Code interpreter - Playing Electronic Resources Librarian and Research Data Management Librarian roles

Aaron Tay's Musings about librarianship

#  {#section style="text-align: left;"}

[Audio Overviews in Google
NotebookLM](https://blog.google/technology/ai/notebooklm-audio-overviews/#:~:text=NotebookLM%20now%20offers%20%22Audio%20Overview,%22)
is making waves online. When I first tried it, it was a \"wow\" moment
for me. The last time I felt that way was trying Perplexity.ai in late
2022 and realizing that search engines could now return answers (with
citations) instead of just potentially relevant links and I realized
this would be a huge paradigm shift. (Before that it was[ trying GPT3 in
June
2020](https://musingsaboutlibrarianship.blogspot.com/2020/07/why-gpt-3-might-be-greatest-disruption.html)).

Audio Overviews many not be as big a wow moment but it\'s close.

# Introduction {#introduction style="text-align: left;"}

I have stayed away from reviewing or trying \"chat with PDF\" tools
(without search indexes) because they are a dime a dozen and most of the
startups working on it are destined to be blown away by the big boys. 

> I know Google and Microsoft is infamous for suddenly losing interest
> in beloved products and killing things, so even this is not certain.

Indeed [Google Notebook LM](https://notebooklm.google.com/), just proves
my point, you can upload anything from PDF, txt, markdown, audio files
either directly from your computer or google docs/slides.

The latest version even allows you to paste links to webpages or even
Youtube videos.  I believe there is a maximum of 50 sources per
notebook.

::: {.separator style="clear: both; text-align: center;"}
[![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEglwZQ0Y_zZF5aIUeTkv4pjUjb252eCZil9X0p_ZdUSWulDEWakChhvFhsgtiLrxYidDiKsGSFkH00-fPf_gsz52z5ytQTohm4W2-BTtGDgg5foUo0NsxIE0MspGXcl1CfAg_s3fyYOosQMgXHRHS3dUF17jfyyeLjIfADv3xeXFNnPP_SMPBiuz-aq1udN/w640-h378/googlenotebooklmsources.png){border="0"
original-height="797" original-width="1348" height="378"
width="640"}](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEglwZQ0Y_zZF5aIUeTkv4pjUjb252eCZil9X0p_ZdUSWulDEWakChhvFhsgtiLrxYidDiKsGSFkH00-fPf_gsz52z5ytQTohm4W2-BTtGDgg5foUo0NsxIE0MspGXcl1CfAg_s3fyYOosQMgXHRHS3dUF17jfyyeLjIfADv3xeXFNnPP_SMPBiuz-aq1udN/s1348/googlenotebooklmsources.png){style="margin-left: 1em; margin-right: 1em;"}
:::

  

From there you can type in questions to \"chat with the source\" (this
can be pdfs if you uploaded the pdf, but you can ask questions even if
the source is a webpage, a Youtube Video, audio files, text etc.)

  

::: {.separator style="clear: both; text-align: center;"}
[![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjAbejRePlXgEXjSOJ41FKTxvdaO91EGreP9KAspUMAXk9FpFB83dkoM-Kfs2AnLj2f5hDhyHNtM4IHVHjhSa6e4Xxqb83Gw4rKPt7deyIJOXvcK2sLWcGKWavLGd7VlhodYzJ7DS23vCWk6DoaRFCVFCH53AWO8PXR9P42gZn2oLWDcJBH4atXGL6y4Uym/w640-h366/googlenotebooklmsources-2.png){border="0"
original-height="894" original-width="1561" height="366"
width="640"}](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjAbejRePlXgEXjSOJ41FKTxvdaO91EGreP9KAspUMAXk9FpFB83dkoM-Kfs2AnLj2f5hDhyHNtM4IHVHjhSa6e4Xxqb83Gw4rKPt7deyIJOXvcK2sLWcGKWavLGd7VlhodYzJ7DS23vCWk6DoaRFCVFCH53AWO8PXR9P42gZn2oLWDcJBH4atXGL6y4Uym/s1561/googlenotebooklmsources-2.png){style="margin-left: 1em; margin-right: 1em;"}
:::

  

In the example above, I uploaded 7 PDFs of papers on the topic of using
LLM to generate boolean search queries for systematic reviews and then I
ask a question on how such methods address the limitations of
traditional Systematic review, and it generaes and answer with
citations. When you mouse over the citation it shows a sniplet of text
that supports the citation. If you like what was generated, you can save
it as a note. So far so normal.

The magic begins when you click on \"Notebook guide\" and you get the
next screen.  

::: {.separator style="clear: both; text-align: center;"}
[![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgsLZyvmZ8wO3zrngSLmA662WlK8ku6fPC-0nhbXzCDFNl7ISE0w_Cbknr-Oc57rGZ7I5JC3nIDquOQ-9fkWqbRgIu3CxaVodQOvqxdI1ANplb3uU8sz2Qgg_BxPiYw2b8LTP6U2Exv3pMAiEbztSZxACYP6nM8Ayz4q0MTvbOZj3ILlIJFH9Ih8lNTyhEN/w640-h410/googlenotebooklmsources-3.png){border="0"
original-height="720" original-width="1124" height="410"
width="640"}](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgsLZyvmZ8wO3zrngSLmA662WlK8ku6fPC-0nhbXzCDFNl7ISE0w_Cbknr-Oc57rGZ7I5JC3nIDquOQ-9fkWqbRgIu3CxaVodQOvqxdI1ANplb3uU8sz2Qgg_BxPiYw2b8LTP6U2Exv3pMAiEbztSZxACYP6nM8Ayz4q0MTvbOZj3ILlIJFH9Ih8lNTyhEN/s1124/googlenotebooklmsources-3.png){style="margin-left: 1em; margin-right: 1em;"}
:::

  

From there you have the option to create 

- FAQ
- Study Guide
- Table of contents
- Timeline
- Briefing doc

<div>

All these are interesting but the one that is causing the most buzz is
the \"Audio Overview\" feature.

</div>

<div>

  

</div>

<div>

  

</div>

::: {.separator style="clear: both; text-align: center;"}
[![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiU88N5KqTAtH6eXZg8ebgxK3vNdUogl1CojvGX_8ndm60yTtDFZEA7emvq6emnNtz7xfTvxXb2aT5AYpHL33BYMNwstyeP1eSGcxEg6bpOKDE1wn19daaIxq_aKm30uw8YyQYkk1JidbUf-kOuozirFvvrMXg9z2uRG5ciG_kOP3tUigt64mPf7afkO-kJ/w640-h230/googlenotebooklmsources-4.png){border="0"
original-height="195" original-width="543" height="230"
width="640"}](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiU88N5KqTAtH6eXZg8ebgxK3vNdUogl1CojvGX_8ndm60yTtDFZEA7emvq6emnNtz7xfTvxXb2aT5AYpHL33BYMNwstyeP1eSGcxEg6bpOKDE1wn19daaIxq_aKm30uw8YyQYkk1JidbUf-kOuozirFvvrMXg9z2uRG5ciG_kOP3tUigt64mPf7afkO-kJ/s543/googlenotebooklmsources-4.png){style="margin-left: 1em; margin-right: 1em;"}
:::

  

<div>

  

</div>

<div>

  

</div>

<div>

Taking a few minutes to generate, this will create a \"podcast\" in
English between two hosts (a male and female voice) discussing the
sources you uploaded. It is extremely realistic and natural that unless
you knew before hand, there is a high likelihood you think it is a real
podcast.

</div>

<div>

  

</div>

<div>

I fully encourage you to [listen to a sample of
this ](https://notebooklm.google.com/notebook/b5236ecd-735a-4f20-96e4-9dcee7775f3d/audio) [which
was generated off an earlier blog
post](https://musingsaboutlibrarianship.blogspot.com/2024/08/ai-retrieval-augmented-generation.html). 

</div>

For me, it was a \"wow\" moment the first time, I played with it. The
voices were very human, they discussed the topics in a reasonable way
(not too technical but this podcast was meant to explain to lay person
why the content is important) and I was stunned to see they go beyond
the content uploaded. For example, in the blog post, I [never mentioned
the word
bias. ](https://musingsaboutlibrarianship.blogspot.com/2024/08/ai-retrieval-augmented-generation.html) but
of course if RAG systems are prohibited from certain sources, who knows
what biases might emerge as discussed by the hosts!

The last time this \"Wow\" happened, I was playing with
perplexity.ai/Elicit in 2022 and realizing that search engines were now
able to return specific answers with citations instead of just
displaying possibly relevant links. And the time before that, I was
playing with GPT3 in June 2020.

Here are some first thoughts on this audio overviews feature.

## It may not be good enough if you want a deep dive into a research paper currently {#it-may-not-be-good-enough-if-you-want-a-deep-dive-into-a-research-paper-currently style="text-align: left;"}

Just before I realized Google Notebook LM had the audio Overview
feature, I was amazed by a very similar google product called
[illuminate. ](%20https://illuminate.google.com/%20) (There\'s also
[paperbrief](%20https://paperbrief.net/))

It basically had the same concept, you upload a research paper and it
would generate two voices discussing the paper.

I was really excited by it, because I was always looking for ways to a)
quickly get the gist of papers b) help researchers find ways to
publicise their work with a explanation of their work. However it is
still not available except via waiting list at time of writing.

As such, I was surprised to discover a few days later,  \"Audio
Overviews\" features was launched in Google Notebook LM which was more
or less the same feature.

But I quickly noticed a difference between the two.

Essentially the audio overview in Google Notebook LM, pitches the
discussion at the level of  a layperson with zero background knowledge
and discusses the content uploaded into it at a very general level and
using a lot of often overly cutey analogies to try to make things more
understandable.

Compare say [Google Notebook LM\'s Audio Overview of the \"Attention is
all you
need\"](https://notebooklm.google.com/notebook/b0145486-b080-4210-bbf1-f81afe81e63f/audio) with
[Illuminate\'s AI -generated audio discussion of the same
paper](https://illuminate.google.com/home?pli=1&authuser=0&play=SKUdNc_PPLL8),
despite the later being only 4 mins vs 10 minutes, it directly talks
about Q,K,V in transformers, multi-head attention etc.

The fomer also doesn\'t stick directly to the paper, the generated
voices talk about the implications and impact of the attention based
tranformer model, for example at one point talking about how the
transformer model has led to impact not just in text but image generator
models like DALLE (which is in the future of the attention is all you
need paper) use it as well while the paper itself only says 

> \"We plan to extend the Transformer to problems involving input and
> output modalities other than text and to investigate local, restricted
> attention mechanisms to efficiently handle large inputs and outputs
> such as images, audio and video.\"

Want to deep dive into how [SPLADE algo works? (also used in
Elicit.com) ](https://arxiv.org/abs/2107.05720) The [audio
overview](https://notebooklm.google.com/notebook/1c2098e9-c2d5-437b-8978-9518c52a42d9/audio)
is better than nothing if you don\'t have any basic knowledge of
information retrieval but stops short of really explaining the algo
exact in a super hand wavey way. 

About lexical expansion in SPLADE , its explains the problem of
vocabulary mismatch and goes\...

> \"SPLADE doesnt just add every related term it can find, it uses these
> really really advanced algo and it does involve neutral networks to
> really zero in on the only most important connections, finds the key
> relationships without being boggled down in all the irrelevant
> stuff\".

 Yeah but how? what said is not useful, that\'s like the goal of every
expansion method ever. 

Then spends a large part of 11 minutes belabouring the obvious point
about how more effective search algos like SPLADE could be ground
breaking.

How about something closer to librarian\'s? Here\'s [audio overview of a
series of papers on the use of LLM to construct boolean queries for
systematic.](https://notebooklm.google.com/notebook/8d8ee1c5-5233-4363-9c7b-340e630d720f/audio) and
predictably it spent a big part of the podcast explaining what a
systematic review and why it\'s important.

I was curious how it would summarise this [complicated
paper](https://www.sciencedirect.com/science/article/abs/pii/S1386505622002428) in
the set. It just said it uses \"contextual embeddings\" which is
teaching AI to go \"beyond matching keywords and looking at the
relationship between those words and the nuances between these words\"
and it goes on and on about what a systematic review is and why if AI
can do it how big a timer save it is.

In short, if you literally don\'t know anything about the area the paper
it is on, and just want the most superficial surface sense of what the
paper is about and the implications of such a paper, Audio overviews is
great.

But if you want even the slightly amount of detail, you should probably
give it a miss *at least for now*, I have no doubt, Google is working on
adding options like ramping up how technical it goes into etc.

  

## It works surprising well for my blog posts and slides

<div>

The part that blew me away from when I uploaded some of my blog posts
and **powerpoints slides!**

</div>

<div>

  

</div>

<div>

- [Primo Research Assistant launches- a first look and some things you
  should
  know](https://musingsaboutlibrarianship.blogspot.com/2024/09/primo-research-assistant-launches-first.html) -
  [audio
  overview](https://notebooklm.google.com/notebook/946a3b40-6bac-42a7-b80d-10e48d92071c/audio)
- [AI & Retrieval augmented generation search - the content problem
  -reactions from librarians, authors and publishers & thoughts on
  tradeoffs](https://musingsaboutlibrarianship.blogspot.com/2024/08/ai-retrieval-augmented-generation.html) -
  [audio
  overview](https://notebooklm.google.com/notebook/b5236ecd-735a-4f20-96e4-9dcee7775f3d/audio)
- [Prompt engineering with Retrieval Augmented Generation systems -
  tread with
  caution!](https://musingsaboutlibrarianship.blogspot.com/2024/07/prompt-engineering-with-retrieval.html) -[audio
  overview](https://notebooklm.google.com/notebook/6bf76670-a5bc-4eb9-916c-c0f830a4ff85/audio)
- [All about citation chasing and tools that does citation chasing like
  Citation Gecko, Connected papers, Research Rabbit, LitMaps and
  more](https://musingsaboutlibrarianship.blogspot.com/2024/06/all-about-citation-chasing-and-tools.html) -
  [audio
  overview](https://notebooklm.google.com/notebook/d6af117b-374f-4b2b-bee4-5b2cae6d23c9/audio)
- [Citation 101 metrics presentation for
  workshop](https://drive.google.com/file/d/1LyX7DVAfMPXf7UFHoMTyJxBFVOc9l_q3/view?usp=sharing) -
  [audio
  overviews](https://notebooklm.google.com/notebook/d2522973-35e4-4419-80a9-4f5ad58af3a6/audio)

<div>

  

</div>

</div>

<div>

The second one and the fourth one is the probably the best (most
accurate) but as mentioned they don\'t always stick directly to the
content but talk around the content. For example, I never once mentioned
\"bias\" though it is hinted at and when these LLMs seem to want to keep
warn about biases, lecture us on how it\'s AI+Human not AI vs human etc.

</div>

<div>

  

</div>

<div>

I also find it quite fascinating it does quite well for powerpoint
slides at least those that follow my style

</div>

<div>

- Here I send it my slides I use to teach literature review to
  postgraudates and [it does a good job creating a narrative over
  them. ](https://notebooklm.google.com/notebook/62e74398-333c-49d2-83f7-e10da56c2218/audio)
- [Academic search and discovery tools in the age of AI and large
  language models: An overview of the
  space](https://ink.library.smu.edu.sg/ai_research_week/Programme/Programme/1/) -
  this is based on slides from a fairly successful talk I gave
  recently.[audio
  overview](https://notebooklm.google.com/notebook/c7d75417-eb5e-48ee-b9b6-d3b1dd1f2a74/audio)

<div>

I am not sure if the model is a multi-model model that can see images,
but my slides tend to have enough text I guess.

</div>

</div>

<div>

  

</div>

<div>

  

</div>

## **System prompt of Audio Overviews** {#system-prompt-of-audio-overviews style="text-align: left;"}

<div>

On Twitter, [people are wondering what the system prompt is and it seems
possible to make the podcast itself discuss it\'s hidden
prompt!](https://x.com/JadenGeller/status/1839924780855672925) That\'s
very meta of course.

</div>

<div>

  

</div>

::: {.separator style="clear: both; text-align: center;"}
[![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjPgJzHB4VupIvFQk0jtaCxYKggsTsCTsC-FcoWH5WDE7CFDeuiCU5S_3WH7dnFbs2_FfwGJq4_x_Th0ZUVarWGdX8ipZHNz1Aaiu_NxWzacmVT8yTWl7qefP93GAai_6Y4guofoYOCsS9ajnA4M_k9Q6_UliSudDvyo1ZUNWlmi5FNXq6zy15maXR2oQjU/w602-h640/googlenotebooklmsources-5.png){border="0"
original-height="811" original-width="762" height="640"
width="602"}](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjPgJzHB4VupIvFQk0jtaCxYKggsTsCTsC-FcoWH5WDE7CFDeuiCU5S_3WH7dnFbs2_FfwGJq4_x_Th0ZUVarWGdX8ipZHNz1Aaiu_NxWzacmVT8yTWl7qefP93GAai_6Y4guofoYOCsS9ajnA4M_k9Q6_UliSudDvyo1ZUNWlmi5FNXq6zy15maXR2oQjU/s811/googlenotebooklmsources-5.png){style="margin-left: 1em; margin-right: 1em;"}
:::

  

<div>

  

</div>

<div>

  

</div>

<div>

[I tried](https://x.com/JadenGeller/status/1840458708234699256) and
[this is what I
got. ](https://notebooklm.google.com/notebook/0fe40313-a9f3-4727-a8b3-b8666d923ef3/audio) None
of it is that surprising. 

</div>

<div>

  

</div>

<div>

  

</div>

# Conclusion {#conclusion style="text-align: left;"}

<div>

I am still, reeling by how amazing audio overviews is. Sure it\'s not
100% accurate, but even when real hosts discuss some content they can
get things wrong! 

</div>

<div>

  

</div>

<div>

I suspect there are more interesting things you can do besides uploading
papers and presentation slides and youtube videos. 

</div>

<div>

  

</div>

<div>

For example, I tried to [upload my CV and it gave a very hype discussed
of my \"Storied career\"
ha](https://notebooklm.google.com/notebook/810e6406-90b3-4d0d-8794-7f6029bb0526/audio)[.](https://notebooklm.google.com/notebook/810e6406-90b3-4d0d-8794-7f6029bb0526/audio)
I would say it is like 70% accurate.

</div>

<div>

  

</div>

<div>

  

</div>

<div>

 

</div>
