Everyday AI Podcast – An AI and ChatGPT Podcast - EP 121: Faster and More Accurate Results From ChatGPT with ScholarAI

Episode Date: October 12, 2023

ChatGPT plugins are a crucial way to help you get more reliable and accurate information out of ChatGPT. Hallucinations can be common when prompting so using ChatGPT plugins helps to reduce them. ScholarAI is one plugin we recommend to help with those issues. Damon Burrow, Co-Founder & CSO of ScholarAI, joins us to talk about the ScholarAI plugin and how to get better information out of ChatGPT.Newsletter: Sign up for our free daily newsletterMore on this Episode: Episode PageJoin the discussion: Ask Damon and Jordan questions about ChatGPTUpcoming Episodes: Check out the upcoming Everyday AI Livestream lineupWebsite: YourEverydayAI.comEmail The Show: [e-mail] with Jordan on LinkedInTimestamps:[00:01:30] Daily AI news[00:04:40] About Damon and ScholarAI[00:08:10] ScholarAI allows for up-to-date info[00:13:30] ScholarAI plugin walkthrough[00:18:05] Other use cases for ScholarAI[00:21:05] Plugins to pair with ScholarAI[00:22:00] How ScholarAI came to be[00:25:00] Audience questions[00:28:25] Final takeaway on ScholarAITopics Covered in This Episode:1. Importance of Accuracy in AI Systems2. ScholarAI Plugin for Reliable Information Retrieval3. ScholarAI Plugin Demonstration4. Addressing Hallucinations and Lack of Transparency in AI Models5. Infusing Trust and Accuracy in AI Systems with ScholarAIKeywords:generative AI systems, electricity consumption, water for cooling, energy consumption, Argentina's energy usage, electricity usage in AI systems, power usage in generative AI, NVIDIA, AI and ML research, radiation therapy, cancer tumors, large language models, research and commercial settings, accuracy in AI, ScholarAI systems, creativity in generative AI, grounding in truth, domain expertise, peer-reviewed literature, semantic search, synthesizing information, multiple sources, BARD assistant, drafting emails, negotiating job offers, integration into smartphones, data centers, "show me diagrams", visual learning, simplifying information, ChatGPT, ScholarAI plugin, CheckCVT, citing papers, real-time information access, cutoff dates, context window, providing necessary information for ChatGPT, accessing abstracts, paper summaries, user demographics, due diligence, assessing technologies, mergers and acquisitions, journalists, COVID-19 pandemic, misinformation, hallucinations in language models, trust in AI-generated responses, transparency, tethering AI output to reliable sources, hyperlinks to sources, professional knowledge workSend Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info) Start Here ▶️Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com Also, here's a link to the entire series on a Spotify playlist. 

This is the Everyday AI Show, the Everyday Podcast where we simplify AI and bring its power to your fingertips. Listen daily for practical advice to boost your career, business, and everyday life. Meet Firefly AI Assistant, now live in Adobe Firefly, the All-in-One creative AI studio. Just describe what you want to create and the assistant handles the rest, orchestrating multi-step workflows across Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome. The assistant accelerates execution. We talk a lot about chat GPT plugins on this show and how they can help you get more

reliable and accurate information out of chat. Chat GPT because here's the reality, y'all. If you don't know what you're doing and sometimes even if you kind of do, chat GPT can lie quite a bit. It can hallucinate just like any large language model. But there's one plugin that we even recommend to people that really helps with that. And I'm excited because we're going to have the co-founder today of Scholar AI to talk about how to create more reliable and trustworthy AI, specifically within chat chabit. Not just that, but a lot more. So welcome to everyday AI.

My name is Jordan Wilson. I'm your host. And this is your daily live stream podcast and free daily newsletter helping all of us, everyday people, make sense of what's going on in the world of AI because there's so much. And it can be difficult to actually understand and apply it to grow our. careers in our company. So we're going to be doing that today. And if you are joining us live, thank you. Make sure to get your question in, whether it's about how to create more reliable and accurate conversations within chat, GPT, or if you just want to know more about the Scholar AI plugin, make sure to leave a comment. Leave us a question. If you're joining us on the podcast,

make sure to check out the show notes. We're going to send a link or leave a link so you can even come and join the conversation on LinkedIn. All right. So before we get to that, let's talk about the AI news like we do every single day. So, Big news out of chat GPD speaking of, right? So it can talk to photos now. So this new feature, being able to upload photos negatively, is now being rolled out to many more users that have the chat GPD plus subscription. So this is part of a larger group of updates that are kind of unofficially being called GPT4V with the B standing for vision.

I don't think that's an official name. It's just what a lot of people online are calling it. So early users have had access to this for a few weeks now, but general access is happening now. Even myself got access to it late last night. Actually, shout out Dr. Harvey Castro, a former guest on the show who said, hey, do you have access? I have access. So we're going to have more on this in AI and 5. Next piece of news, Google's Bard is coming to new places.

So Google's newer smartphones like the Pixel 8 in Samsung Galaxy S-24 will feature an assistant with bar. That's not new news, but there is some new news because the publication 9 to 5 Google recently found some references in the source code, claiming that you could, as an example, tell the Bard assistant to draft an email to my recruiter to accept the social media manager job offer and negotiate a later start date. So we're going to have more about that in the newsletter, but some new details leaking on how this new assistant with Bard will work natively inside of some of these new, you know, Google. Google smartphones such as the Pixel 8 and Samsung Galaxy S24. All right. Our last piece of news to go over. AI is soon going to be consuming more energy than an entire country. Yeah, that's right.

So all of these data centers that are helping to produce generative AI, they take up a lot of electricity and a lot of water to, you know, a lot of times cool these systems down. So a recent report from the journal Jolet, I believe that's how it's but researchers in Netherlands showed that by the year 20, 27, that all of these different, you know, servers, server farms and plants essentially where they help to create these generative AI systems could use anywhere between 85 to 134 terawatts of energy per year. I don't speak terawatts in energy, but apparently that is about as much power as Argentina uses in a year. It's actually very fascinating to talk about electricity and power in Gen. AI.

We actually had someone from Nvidia talk about that this week. So we'll drop the link to that in the comments. But you probably showed up here not to talk about energy and how to cool generative AI systems. You probably want to know, you probably want to hear a little bit more about Scholar AI. And full disclosure, we have people hitting us up all the time and saying, hey, I have this plug-in. I want to come on your show.

I have this product and we normally say no. But with Scholar AI, this is something we've been using and recommending for months. So I'm extremely excited to bring onto the show and welcome on as a guest we have today. And help me welcome on Everyday AI. We have Damon Burrow, the co-founder of Scholar AI. Damon, thank you for joining us. Hey, Jordan. Happy to be here.

Thanks so much. All right. So, hey, just like Brian right here, who said he's excited to learn in today's episode. If you are excited, if you have a specific question in our joining this live, please, please drop, please drop your question for Damon, if you want to know a little bit more about Scholar AI. But Damon, let's let's start high level. What is Scholar AI? What do you all do and kind of how does this thing work? Yeah, excellent, excellent question. So at the very core, Scholar AI is building systems that infuse trust into large language models. And right now that large language model is the GPT4 transformer that powers Chad CBT. And we do that through some very specific applications.

I'm very happy to dive into the specifics of any of that. But I, again, kind of remaining at the highest level. We essentially tether the AI generated output that comes out of chat GPD to peer-reviewed and publicly accessible scientific articles, databases, textbooks, etc. What that does is it significantly reduces almost virtually eliminates hallucinations in general. It pulls information directly from those sources and it provides hyperlinks to those sources such that anybody using those generative AI systems can immediately follow up. They can ask more questions, those kinds of things. Longer term, we plan more applications outside of chatGBT.

So like Google Bards, like you mentioned earlier, we've got systems coming for that. We've got a browser plug-in, browser extension coming for Google Chrome and others. And then we're also going to have some dedicated web apps inside of very specific domains in which some of our core user bases are going to be receiving some outsized value there. Yeah, I love it.

Yeah. And I think people who use ChatGPaths, pretty frequently have probably either heard of Scholar AI or have used it before. So from a very high level, you know, perspective, David, and we are going to explain this here in a couple of minutes, but, you know, maybe let's answer the question, why? Like, why do we need to use, you know, a plugin like Scholar AI to get better results? Yeah. So I think, I think in some cases you don't. I think the reality is so where some of the, you know, truly generative AI systems really shine through her for creative tasks. So if you're trying to write a new short story or you're trying to

write a new song or, you know, design some sort of theatrical play or something like that, you don't really care if the output in that is grounded in what would be considered truth across the board, right? If you transition, though, into professional knowledge work, so think about you're a doctor trying to save somebody's life. Think about you're a CEO of business trying to use the last bit of runway you have to either save your business or to expand into new domains, right? Think about a lawyer who is doing a patent search for a client of theirs being able to express whether they are free to operate in those space. And those kinds of things, you must be accurate, essentially, with your use

of AI. And so it's those times in which the systems that scholarly AI is building become essential. And again, the way that works is we essentially distill the creativity out of these generative AI systems, a little bit, not completely, but just a little bit, just enough such that all the output that comes out of there is grounded in truth as is kind of supported by the domain expertise, right? So basically the way that this works in science, I can speak most thoughtfully towards that because I am a PhD student. I kind of live in this world every single day, right? The scientific literature that has gone through the peer-reviewed process is kind of the gold standard for the most up-to-date knowledge of across scientific literature. And so scholarly ad gives people

who want to use the large language models to interact with these sources in a much more thoughtful, much more rich way access to that to that material and so that their responses that come out of the AIs that they're using are again more accurate, more reliable and then ultimately more transparent. Yeah. And you know, I think it's worth noting and maybe even hitting like rewind here a little bit, Damon, because if you are brand new, if you're listening and maybe you haven't really used chat GPT a lot or you're just a casual user, you know, there's a couple of important things to keep in mind, you know, it has a knowledge cutoff. So if you're using the free version of chat, at GPT, it has a knowledge cutoff of September 2021.

If you're using the paid version, it has a knowledge cut off of January 2020. But regardless, you know, so I guess there's two things that I kind of wanted to talk about here, Damon, and maybe to ask a question. So, yeah, one, can Scholar AI give us, you know, more, more recent knowledge, you know, past that kind of cutoff date? And then two, can Scholar AI also just give us more specific and more fact-based things, you know, even included in that knowledge, you know, cut off just for more accurate and more specific citations. Adobe just introduced an entirely new way to create, bringing the power and precision of its

creative suite into one conversational experience. Meet Firefly AI Assistant, now live in the Adobe Firefly app, the all-in-one creative AI studio. Powered by Adobe's creative agent, Firefly AI Assistant lets you start with your vision, just describe what you want, and shape the outcome as it takes form with the assistant. The assistant orchestrates multi-step workflows drawing on 60-plus pro-grade tools across Adobe Creative Cloud apps, including Photoshop, Illustrator Premiere, Lightroom Express, and more to help bring your ideas to life. You can also get started with creative skills, a growing library of pre-built workflows for common creative tasks, like batch editing photos, creating mood boards, portrait retouching, and creating social variations.

Every step the assistant takes is visible so you can refine, redirect, or take over at any time. You stay in the driver's seat as the creative director. Adobe Firefly AI assistant now in public beta. See it today at firefly.adobie.com. Yeah, so all excellent questions. And yes, you basically nail it. So basically, you know, the cutoff dates are September 21 or January 2020, depending on exactly which model that you're using.

scholarly ad provides access to up-to-date information seemingly in real time. So as soon as the information is published, ScholarI has access to it through our various API endpoints, depending on which database you're pulling from. Those usually get updated daily. Sometimes it can be twice a week, those kind of things. So in very short, yes, and then to your larger point of how we maintain accuracy across the sources, we basically go beyond not just the cutoff window, but also what is called the context, not the knowledge cut off

and the context window rather. So we actually dissect that source material through some proprietary and trade secret algorithms that we develop such that we can actually package more dense information into large language models such that it can actually hold a larger breadth of information think about

thousands of sources at a time in its kind of working memory, so to speak, such that it pulls directly from those sources rather than having to rely so much on its predictive capabilities. So we're playing less of a probabilistic game, much more of a information gathering game. And just that seems like a very timely response because yesterday on the show,

and we'll make sure to leave a link to that. We talked about like tokens and in memory. So you're also saying even the way that Scholar AI processes information, it kind of takes up less of that token memory so it can retain knowledge longer. Yeah. The way that I would classify it is we, so based on the semantic search functions that we've built, we can identify the most important aspects of it. each source just that we can kind of disregard the like less important tokens, if you will,

so to speak. And so what that does is it doesn't actually truly extend the context window, but it puts more of the information you care about in the context window. So everything that you're pulling from is the most relevant, the most accurate, the most important pieces of all those articles. And so what, again, what you get is reliable, accurate information from the most relevant of even parts of sources. So again, we're trying to synthesize information across sources, not just pull information from a single source. And so that's when it really becomes effective to kind of break those into their most meaningful chunks, if you will.

Yeah, absolutely. Hey, and, you know, for those, we have a lot of people here in the live stream. Let me know. Have you used scholarly AI? What do you like about it? What are things that you want to know? Because I'm going to ask Damon here in just just a minute to kind of share his screen so we can take a look at this.

But before we do that, Damon, like talk, let's talk a little bit more because you said, hey, in the future, once some of these other large language models, you know, officially release, you know, plug-in capability or third-party, you know, developers to be able to work within their models. But can you access Scholar AI right now without chat GPT? Can you just log in and use it? Or what's is, are there other use cases, I guess? Yeah, so the public cannot. We have a few kind of applications that are in their alpha or beta forms for specific, you know, what I would consider, that are professional co-pilots. So think about a lawyer doing the patent search like that earlier as an example. The short answer to your question is no. Those things are coming down the pipeline,

still TBD on when exactly those will be released. For the public, what I can tell you is people should, especially avid users of scholar, I should be excited because in the relatively near future, we're going to have things like browser extensions for their Google Chrome, Chrome, et cetera, and we're also going to have some dedicated UXUIs that give us some increased capabilities, that things that were just simply limited to inside chat, GBT. So all those things are coming down the pipeline. There is no publicly available link right now. But if you are a scholar AI user and you feel that there's an element of scholarly AI that's

missing, then we would love to hear from you. We've got a community of about 180,000 right now users. And a lot of us, you know, we would like to engage with. them and see if there's a gap that we can we can fill. Yeah, love it. Well, hey, let's let's actually give, give everyone a chance to kind of see it side by side. So Damon's going to pull up his, his screen here. And we're going to walk you through.

So we're going to show, Damon's going to show an example of what you might see when you're using chat GPT by default. Because like we talked about at the beginning of the show and we talked all about it yesterday is if you really don't give a large language model access to the information and the resources that it needs, you write. the risk of it kind of sometimes making things up or just, you know, giving you poor responses. So Damon's now going to kind of walk us through, you know, what kind of happens before and after so we can see the difference that a plug-in like Scholar AI makes.

Yeah, thanks, Jordan. So it's incredibly well said. The one thing I will say is open AI is making chatGBT, both the models 3.5 and 4 better all the time. And so it is getting better at just simply telling you when it can't do things rather than just making it up, but people still do need to be careful because the answers, the hallucinations still do happen, especially with a 3.5 model. But I'm kind of jumping into this demo. What you're seeing here on screen is a prompt that I've used several times, which I'm asking the standard chatGBT, running the Transformer 3.5, to show me three new papers about recent advances in artificial intelligence. And unfortunately, it says it cannot do that. Some of that's because it doesn't have access to the internet in real time.

And also it has a knowledge cutoff that is in September 2021. So it can't actually see anything that's happened beyond that. It tells you that you can use other academic search engines like Google Scholar, PubMed, etc. The problem there is that you can't actually then use the large language model to interact with those sources. So we don't want to just use this as a reference finder. We actually want to engage that content. We want to read PDF.

We want to ask questions from that content. We really want to get the knowledge out of that source material. We don't just want to simply find the material. And that's what those LLMs are so great. So swapping over to a use case after Scholar AI, the plugin has been installed on the GPT4, Transformer. Here you can see a much different response. Stain prompt, this is exactly copied and pasted one into the other. And here what we're seeing is three papers.

I asked specifically for three. You can ask for much more. I just learned to do three just for the sake of time here in this kind of conversation. But what you're seeing here is papers with direct link to papers. And you can see here directly to your question earlier, Jordan, about the knowledge cutoff. So this paper came out in December of 2022, obviously well after both knowledge cutoffs, but given access to chat TVT via the Scholar AI plugin. We're also seeing an abstract here, how many times been cited if the PDF is or is not available,

and then just notice that in this title is actually hyperlinked. So if anyone wants to kind of go up and then follow up with the sources, they can do that. One interesting thing is what I can do is I can say to the scholarly eye plugin, as we said, we don't just care about the information finding. we actually want it to provide a summary of paper one. And then kind of in real time, I might have to zoom out just to show you that. But what it's going to do is it's going to actually give you a decent understanding of what the summary is. So in the cases when it can find the full text, it will be explicit and it will tell you that it has found the full text.

It has parsed the full text and has created the summary from the full text. If because of publisher restrictions, scholarly ad does not have access to the full text, it will tell you that doesn't have access to the full text. and it will still create a summary from the bits of information it has access to. So it's not just going to guess and extrapolate the information. It's just going to say, I'm only limited to seeing this much. Here's what I can do for you. Here's what I can give you that is accurate and reliable. There's kind of your information.

If you want more information, please follow up through the hyperlink. Yeah. I love it. And, you know, I think David just did a great job of explaining. And, you know, if you're listening on the podcast, again, come in. We'll leave a link so you can watch this. But, you know, even just showing in real. time. It's fast. It's responsive. Something that I love that I wish all plugins would do is always

providing a link to read more to the original resource because when you talk about transparency, that's something that we always kind of worry about with large language models, you know, because there's always that little seed of thought where you're like, all right, is this real? Is this a lie? So being able to have the link is great. Damon, like right away, I thought of a couple of great use cases. Right. So if you're trying to learn a new subject, this seems to really cut down the time, even using chat GBT cuts down the time, but using chat GBT with Scholar, amazing, right? So if you're a, maybe if you're a student, you know, working on a topic, working on a paper, this seems great. Maybe what are some other kind of everyday use cases or

very wide ranging applications of the Scholar AI plugin? Yeah, excellent question. So roughly 60 to 70% of our use cases come from what I would consider graduate students, so master's PhD students and or researchers, meaning people in academia doing kind of hardcore, you know, research. The other, you know, roughly 30 to 40 percent come from, you know, other business professionals, specifically people doing due diligence, again, trying to assess whether some businesses' technology is above board, what the maybe kind of isolated advantages of one technology are over a competing technology, that kind of thing. Also, as I said, at the C level, executives can use this kind of to do, maybe mergers and acquisition due diligence or maybe just market research and seeing, you know,

which kind of path might be most advantageous for their kind of business in its current state. We see a lot of journalists using this platform when they're doing a story and their core expertise may lie slightly outside of the story that they're writing about, right? You can think of without diving into the specific of anything, you can think about, you know, how kind of groundbreaking and how kind of earth-shattering the COVID-19 pandemic was and how much, you know, kind of information was swirling and people were having a hard time deciphering what was real, what was not real, that kind of thing. So you can imagine some very important use cases there. And like you said, students of all ages just kind of coming in saying, hey, I don't understand this.

Can you please explain this to me at a level that I do understand? Can you please provide me links for this if I want to keep reading, that kind of thing? So we do see a very wide range of uses and we're getting better and better at serving each one of those use cases. like I said, we kind of started with this science and medicine focus, and then we realized what we were building was much more applicable to everybody else. I'm also seeing the chat, the comment coming through in the chat. Yes, a lot of clinician scientists are using us both to propel their research forward, but also helping treat patients. You can imagine how important it would be to be helping a cancer patient who has failed the standard of care treatments and who, you know, their physicians who are whoever helping them nurses, etc. need to be parsing, not just published data, but also clinical trial information to say, how can we help this person? You know, how can we have to, how can we give them and improve quality of life? How can we help them live longer, live happier, et cetera, et cetera. So, yeah, no, it's so many, so many great use cases.

And, you know, the one that you really mentioned there. And I have to call students out, you know, students, if you're using chat GPT, don't use the free plan. Like, it's worth the $20 a month to be able to tap into plugins like what Damon is showing us here, Scholar AI, and there's so many other great plugins that if you are just trying to learn or help write papers, this right here is going to save you so much time, not only improving the quality of what you're trying to write, but it's also going to help you learn. It's going to help you learn faster, learn a little bit better. So I want to get to a couple of questions here,

Damon. So speaking, like, I love this question. So Val is asking, you know, what other plugins maybe work well with Scholar AI, because, you know, Scholar AI serves a very specific purpose. And it does it well, right? Like I've used it. A lot of our, you know, listeners use it all the time. But maybe what other plugins complements Scholar AI? Yeah, the one that I would call attention to is it's called Show Me diagrams. And there are other similar plugins that do kind of diagram work. But like for me, I'm somewhat of a visual learner. So I want to go beyond the text, right? It's very good to get that summary. But I actually maybe want to work, maybe make a mental framework or some sort of mental model, you know, diagram explaining some sort of kind of arcane

or very specific concept to me that maybe I wouldn't understand. otherwise. So the one that's very top of mind, the one that we see most frequently is, is showing diagrams, but basically anything that's going to allow you to take information, especially dense information, and to simplify in some sort of visual graphic is, you know, really powerful. Yeah, absolutely. It's, it's actually funny. You say that, Damon, like we, we have our kind of free prime prompt polished PPP course. We do it twice a week, doing it later this afternoon. So if anyone wants to access, just, you know, drop PPP. I'll send it to you. But we actually have, you know, Scholar AI and that exact plug-in, you know, diagram on this name page, you know, for our

recommended plug-in. So I love that you brought that one up as well. Question, question here for Monica, saying the episode's blowing her mind, but saying she loves learning from leaders in the AI space and asking, how did you even come up with the idea for Scholar AI? That's a, that's a fantastic question. Thank you, Monica, for asking that. So I've been doing AI and what would be considered more ML research since roughly 2015. So back when it was kind of called gradient descent, I was doing it in undergrad, and there I was helping optimize radiation therapy for cancer patients. So basically just trying to get the radiation to go to the cancer tumors and leaving the healthy tissue alone. You know, roughly a year ago, we saw this kind of momentum of these large

language models gaining power. They were becoming, you know, more useful. People were kind of interacting with them in their everyday lives. And we were using them both in the research setting and also kind of just commercially, whatever was available. And we were seeing some of these shortcomings, right? The hallucinations, the lack of transparency. In the very beginning, you would ask these large language models for sources. And rather than telling you they couldn't give you sources, they would just predict the text that was supposed to come next and they would just make them up.

So they would be real author names, not real people, they'd be real titles, not an actual title that's linked to a source, fake BOIs, etc., etc. And so we said people are going to be using this in their professional lives and they're going to be making, you know, important decisions based on this. And these systems are going to need guardrails or structural supports, if you will, that are going to make them ultimately useful for the things that we care most about. And again, Scholar eye emphasizes any use case in which the loss of life, the loss of revenue or the loss of reputation is kind of occurring.

And so you can think about fields like medicine, science, and research, law, business, etc. But that's kind of how we came up with this. We saw the momentum of large language models becoming more use. becoming more powerful, but we're still kind of, you know, being handicapped, if you will, by these shortcomings. And we saw a need to overcome these shortcomings and, you know, we think it's going to be an evergreen problem because even as some of these AI systems improve, there's always going to be the superabundance of sources in which case you don't really want to be just pulling things randomly from the Internet. You want these things to be context aware. You want the most relevant sources being pulled into your chats or into your AI. in general. And so that's that's kind of, you know, where we, where we hang our hat at scholar.

Yeah. Yeah. Love it. Love it. All right. We have a couple more questions. We're going to try to go rapid fire here so we can try to fit, fit more in here. And again, if you're joining us, joining us a little late. We have Damon Burrow, the co-founder of Scholar AI, joining the everyday AI show, going through some questions on the very popular Scholar AI chat, GPT plugin. So a question here from Gabriel asking, do you include international sources in Scholar AI? Yep. Answers yes. So we just recently, as of this week, have access to over 200 million different articles,

databases across the world. So globally inside of the United States and outside, we have access to virtually all published scientific literature, even the preprints. Wow. And like as someone that uses, y'all, like a large language model a lot, the ability to tap into all of those sources in one plugin is extremely valuable, right? Especially when you are kind of limited, you know, because you're like, you know, because You can only have three plugins at once when you start a new chat.

So you want to be a little judicious about what those are. All right. Another great question here from Douglas. Thanks for the question saying, would this be something you could look for drug interactions? Obviously, consult with your doctor. But when it comes to drugs and how they work, is that something you can also ask scholar. Yeah, short answer. Yes.

All those clinical guidelines come from research that is conducted in the industry or academia. All that normally is published in the academic research, all of which scholar AI has access to. So yes, obviously consult with your physician and doctor. Don't trust these things blindly, but direct answer is yes. Yeah. I love that because I always tell people like, don't trust me just because I recommend something, right? People always ask me on. I say, no, don't, you know, trust some random person on the internet or a random plug-in.

Go try it for yourself. You know, make sure fact check it first. Make sure it works for your use cases before you just blindly start, you know, trusting anything, really. I think that's a great point there. Mike asking how is this monetized? Yeah, excellent question, Mike. So we have three tiers. Scholar AI is available to everybody for free so long as they subscribe to

Chad GPT Plus, which does cost $20 a month. That is limited up to 25 requests per week. So it requests is anything like search for a paper, show me the full text, give me a summary, those kinds of things. The Scholar Eye Basic Package is available for $4.99 per month or $50 per year, and that basically just comes with unlimited use. We also have a premium plan that's $89 a month or $85 for the year, and that comes with unlimited use, but also some advanced features. One of the things that we're most excited about is figure and table extraction.

So in the sources that you find or the PDFs that you upload to Scholar AI, you can actually ask questions not only of the text of that material, but also from the figures and the tables itself for premium subscribers. And you can see at the very bottom there, we have a meta analysis coming soon. And meta analysis is probably a much longer discussion than needs to be had here, but basically is information synthesis across a wide range of sources on a singular topic. So think about condensing the information insights that come from 10,000 sources on infectious disease as an example. Great, great overview. And I love the ability in that highest plan to be able to read tables, charts.

That's so important, right? Like we opened up the show talking about how we can kind of do that now with chat, GPT, with the uploading the photo. But the downside of that, y'all, is right now that only works in default mode. So you can't combine that with any other plug-ins. So that's a huge, huge benefit to Scholar AI. So, all right. Well, Doug, like we, Damon, we went through a little bit of everything in today's

episode. You know, you took us on like why this started, you know, what Scholar AI does, the benefits of it, how it can help us get more reliable and accurate information. But maybe what is the one takeaway that you hope people get? on the benefit of scholar AI and how it's going to help us, you know, just put out and create more reliable information. Yeah, I think that, like I said, these large language models are going to continue to become better and better over time. I think that we're going to see, especially professionals in the knowledge world, science, medicine, law, business, journalism,

etc., are going to have to learn to use these systems more thoughtfully. And we want to be the system that help people do that. So they can get to doing the things in their daily lives that make a maximum impact and don't have to worry about the information that's coming out of their things being accurate. Right? We want them to be able to trust the responses coming out of their AI-generated either chats or kind of interfaces regardless of whether that is. And we also want to create the level of transparency, like we said, to where we're not

necessarily saying trust us completely. We're saying here's the material. Here's where it came from. Please, please follow up. you know, please continue to push us to get better. And please continue to, to kind of, you know, make your impact on the world doing kind of whatever you are best at. Oh, love that. Yeah, you always got to show your sources. An old saying, I believe I learned in journalism school as someone said, hey, if your mom says she loves you, get it in writing.

Right. So, hey, I love that scholarly. AI plug in does this. It's one of our favorites. It's one we recommend. Damien, thank you so much for coming on the show to join us. Yeah, thank you, Jordan. Thanks so much. All right. And, hey, just as a quick reminder, We covered a lot. If you didn't, if you can't type as fast as we can, take notes. Don't worry. Make sure to go to your everyday AI.com. Sign up for the free daily newsletter.

We're going to have a lot more about Scholar AI, maybe even some things that we didn't get to that the plugin can do. So make sure you go do that. And make sure you join us back tomorrow and every day for more everyday AI. Thanks, y'all. Meet Firefly AI assistant. Now live in Adobe Firefly, the Allman One Creative AI Studio.

Just describe what you want to create in your own words and the assistant handles the rest, orchestrating multi-step workflows across Adobe Creative Cloud apps, including Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome while the assistant accelerates execution. Stand control with the ability to step in and refine at any time. See it today at firefly.adobie.com. And that's a wrap for today's edition of Everyday AI. Thanks for joining us.

If you enjoyed this episode, please subscribe and leave us a rating. It helps keep us going. For a little more AI magic, visit Your EverydayAI.com and sign up to our daily newsletter so you don't get left behind. Go break some barriers and we'll see you next time.