Resources:
Join the discussion: Ask Jordan questions on ChatGPT
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Try Our Free AI Prompting Course: Register for our free Prime, Prompt, and Polish AI Course!
Unlocking the Potential of ChatGPT with Correct Internet Access
Understanding the interface of ChatGPT with the internet is essential for any business decision-maker seeking to harness the power of AI. When used correctly, initiatives involving generative AI can help solve complex problems, even showing a potential 40% improvement in performance for complex maths tasks. But take caution: an incorrect or outdated input can lead to potentially flawed outputs.
Pros and Cons of Browse with Bing
ChatGPT generally uses Browse with Bing to access the internet, querying keywords from URLs. While this method can yield the desired information, it might also pull outdated or irrelevant data, which can compromise business decisions requiring precise, fresh inputs.
Though once a standalone mode, Browse with Bing has since become the default mode for ChatGPT—thanks to OpenAI's partnership with Microsoft. As users access the internet via ChatGPT, a discerning eye is crucial to ensure the data's reliability and timeliness.
Beyond Bing: The Advent of WebPilot
Using an Internet-connected General Purpose Technology (GPT) like WebPilot expands the traditional limitations associated with ChatGPT, like bounded browsing. WebPilot can autonomously visit multiple URLs to conduct research, skirting the risk of a reliance on outdated Bing searches. Nevertheless, focusing on accuracy while utilizing these tools can guarantee significantly improved outcomes.
Fusing Knowledge into Action: The Role of Context Window
The correct way to use ChatGPT is to obtain relevant information through an Internet-connected GPT, such as WebPilot. By integrating the fetched information into the context window, users can derive the desirable insights without risking outdated or incorrect data.
The Art of Prompting: Leading AI for Better Outputs
Business leaders can utilize the concept of "chain of thought prompting" to guide the AI's search process step by step and make it more accurate. Furthermore, adopting a cooperative and patient approach when working with ChatGPT can lead to better outputs.
Vigilance and Precision: The Future of AI Usage
In the continuously evolving realm of AI, vigilance and precision in using browsing features are pivotal. Specific and targeted Browse with Bing calls, for instance, yield more accurate and up-to-date information compared to generic calls.
As promising and sophisticated AI technologies like ChatGPT and WebPilot become readily accessible, understanding their operations becomes paramount. Remember: as exciting as these advancements are, it's critical not to underestimate the importance of accurate, updated information as the foundation of successful AI utilization.
Stay Informed, Stay Ahead
Capitalizing on the potential of AI requires being in sync with the latest developments. Subscriptions to free AI-focused newsletters and educational platforms can keep users informed about key updates from tech giants, new AI models, and the latest in AI research. Keep an eye on such resources—your business might just benefit from the next big AI breakthrough.
Note: AI University is hosting a thanks-a-million giveaway on the website YourEverydayAI.com. Consider entering for a chance to learn more about the fascinating world of AI. Don't forget to share this valuable resource with others—retweet, repost, and refer friends to enrich the AI learning community.
Remember: as our world becomes increasingly dependent on AI, understanding how to handle these technologies correctly becomes invaluable. Let's embrace AI's fantastic potential responsibly, making the most out of tools like ChatGPT and WebPilot.
Topics Covered in This Episode
1. Understanding ChatGPT's Internet Interfacing
2. Correct Usage of ChatGPT
3. Problems with Outdated Data in ChatGPT
4. Chain of Thought Prompting With ChatGPT
Podcast Transcript
Jordan Wilson [00:00:02]:
When you're using ChatGPT, you probably think that you're connected to the Internet. You see that little icon come up, so you think that everything that you're getting from the outputs is going to be up to date and correct and accurate. And you're blindly trusting it, but you're wrong. Because unless you actually know what you're doing, there's a high likelihood that even when you're getting that little icon in chat gbt that assures you you're browsing with Bing, you're actually really not, or at least not doing it in the way that you think. But that's okay. We're gonna go over that today and help you fix it as we go over the correct ways to give ChatGPT access to the Internet. All right. I'm excited for this one.
Jordan Wilson [00:00:49]:
What's going on. Y'all not. My name is Jordan Wilson and welcome to everyday AI. This is for you. It's a daily live stream podcast and free daily newsletter, helping everyday people like you and me not just learn generative AI, but how we can leverage it to grow our companies and to grow our careers. And if I'm being honest, ChatGPT is probably a tool that almost all of us use if you're listening to this podcast. And, this is one thing that I've seen consistently people get wrong, even people who use chat gbt for hours a day. So we're gonna fix this.
Jordan Wilson [00:01:20]:
But before we do, gotta go ahead and call this out. If you haven't already, make sure to go to your everyday ai.com. Sign up for our free daily newsletter. Also, hey, on the website, it's like a free generative AI university. There's hundreds of episodes, blog posts that you can read all for free from the, world's brightest minds in AI. So whatever you need to learn around generative AI, it's on our website at your everyday ai.com. While you're there, sign up for our thanks a million giveaway. Alright.
Jordan Wilson [00:01:49]:
Before we get into this topic today about the correct way to browse the Internet and the correct way to bring in up to date and accurate information inside of ChatGPT, let's first go over the AI news. So Salesforce has partnered with Anthropic to enhance AI capabilities inside of Salesforce with its Claude model. So Salesforce has announced a partnership with Anthropic to integrate Claude models into Einstein 1 Studio, marking a significant advancement in AI powered business applications. This collaboration is noteworthy as it provides Salesforce customers with enhanced options for AI capabilities, aiming to improve operational efficiency and personalization across various sectors. So Salesforce customers can now use Cloud 3 models, including 3 5 SONNET, and Cloud 3 OPUS and Cloud 3 Haiku within their applications. So, specific applications in clip for, you know, kind of this AI, infusion here inside of Salesforce's, Einstein. It includes, I mean, a lot of things, but, generating personalized content, that's gonna be the big one. Summarizing customer service cases and analyzing contracts, which can significantly streamline workflows and improve outcomes.
Jordan Wilson [00:03:10]:
So this integration, if you're looking for it, it's actually facilitated through the bring your own large language model or by LLM feature inside of Einstein 1 Studio. So you have to make sure you have a subscription to that and have that enabled, and then it allows users to connect Claude models via existing Amazon Web Services, bedrock environments. Alright. Next piece of AI news. The Department of Justice has issued subpoenas to NVIDIA amid antitrust concerns. So the Department of Justice has taken significant steps to investigate NVIDIA's market practices, raising concerns about the company's dominance in the AI sector. So the DOJ has recently issued those subpoenas to NVIDIA and other companies, signaling a deeper investigation into potential antitrust violations. So this follows earlier questionnaires sent to those companies marking a shift towards a formal complaint against NVIDIA.
Jordan Wilson [00:04:08]:
So antitrust officials are worried that NVIDIA may be making it difficult for customers to switch to competing suppliers and could be penalizing those who do not exclusively use its AI chips. The investigation also includes NVIDIA's planned acquisition of Run AI, a company that specializes in software for managing AI computing resources. So following these developments, NVIDIA's stock experienced a 2% dip, early last week and then a significant 9 and a half point dip on, Tuesday, the overnight session, falling below its 50 day and 21 day moving averages. Alright. Last but not least, new details have emerged about OpenAI's next model from 2 separate conferences, one in Japan and one in Taiwan. Yeah. Both of these happening in the last couple of hours. So OpenAI Japan CEO, Tadao Nagasuki, showed details of OpenAI's next model categorized under the heading GPT Next on his slide at the KDDI conference in Japan.
Jordan Wilson [00:05:15]:
So his slide revealed that the new model is projected to increase performance by a factor of 100 compared to gbt 4. Yeah. Compared by a factor of 1 or sorry. Improved by a factor of 100. That's wild. Also, some more future OpenAI model specs were leaked. At the CEO Summit in Taiwan, a corporate president and head of memory at Samsung revealed on a slide that OpenAI's GPT 5 model may have 3.5 trillion parameters or about double the parameters of the current class GPT 4 models. So, this comes after, obviously, recent reporting from the information, showing, details about this new strawberry mode or model, formerly called QStar inside of ChatGPT that's currently being reviewed by federal regulators and will reportedly be used to create synthetic data for training OpenAI's next model.
Jordan Wilson [00:06:19]:
Presumably, that would be GPT 5, right now, codenamed Orion or Orion. So, alright. It's a lot a lot of AI news, for today. There's always more. Make sure to go to your everyday ai.com, and sign up for the free daily newsletter. And, hey, livestream audience, love seeing y'all today. So thanks for joining us, Brian and Chrissy and Tara, Rolando, Marie, Cecilia, Kobe, Jay. We got a lot in the house today.
Jordan Wilson [00:06:44]:
Milka, our our friends from YouTube, Michael and Big Bogeyface. Thanks for joining in. So here's the thing y'all. I'm always one that brings receipts. Alright? And when we're talking about ChatGPT and getting up to date information from the web, It's an extremely important topic to cover. This might seem like a small detail, but it might seem like a footnote, but on the contrary, y'all, this is actually one of the most important things you need to understand when using a large language model. Right? So we've taught literally I I I think our, number's up to, like, 7,000. We've taught, like, 7,000 business leaders prompt engineering live inside of ChatGPT, with our free prime prompt polish PPP course.
Jordan Wilson [00:07:33]:
Alright. And this is one of the 3 biggest mistakes that people routinely make. Oh, also, hey. If you've taken the course, livestream audience, shout it out, or if you want access, just type in PPP. I'll I'll send you the registration link. We hide it. You won't find it, you know, on our website unless you have the link. So this is one of the three most common mistakes that people make is assuming that the information that they have inside of ChatGPT is correct, especially when they say, oh, well, it's using browse with Bing.
Jordan Wilson [00:08:04]:
So speaking of receipts, more than a year ago, I said do not use browse with Bing. It is terrible. And to be honest, at the time, it was. But over the last 4 months, OpenAI has quietly rolled out some very impressive updates to Browse with Bing. We've covered those, literally step by step, piece by piece in our newsletter and on our YouTube channel, which, yeah, I know the YouTube channel's a little cringe sometimes, but we cover up to date stuff on there. So you should be subscribed and go check it out. But, essentially, about 4 months ago, they didn't announce this. OpenAI didn't announce this.
Jordan Wilson [00:08:46]:
And I put out a video, and I said, hey. You know, we've heard all these reports, and this was 4 months ago. We've heard all these reports that OpenAI is releasing this new, search engine project, product, you know, aimed at Google. You know, now we know it's called search GPT. OpenAI has has started to roll out beta access to it. It might be a while before there's a general release. But even before that, I said, y'all, no one has noticed this, but browse with Bing has been wildly updated. Under the hood, OpenAI didn't announce anything, because, essentially, it is an answers engine right now.
Jordan Wilson [00:09:25]:
Yeah. So if you like perplexity, if you use ChatGPT and browse with Bing correctly, you can get that very up to date accurate information. And y'all So we go through a process in our PPP course called RefineQ, and a big part of that is, the f in the I, which is fetching insights, because you are working with a very old knowledge cutoff when you are working, when you're working with ChatGPT. So that's something, again, you don't like, we don't talk about it a lot, but it's a problem. And this is why you now need to use browse with Bing. Well, you should've been using it, especially for the last 4 months, but we're gonna detail it. Alright? And the biggest reason is we need to get around the October 2023 knowledge cutoff date. Alright? Here's what that means.
Jordan Wilson [00:10:27]:
Unless you're properly using browse with Bing, and we're gonna go over the pros and the cons, alright, here live on today's show, Unless you're properly using it, you're rolling the dice. Right? You're rolling the dice to danger. You're rolling the dice to, I might get a very bad output. Alright? Because if you are not tapping into browse with Bing, you are working with data, y'all. It is September now. Right? Unless you're listening to a replay of this in the future, but it is September right now. October 2023 is almost a year old now, and that is the absolute best case scenario. So to oversimplify this, the way that large language models, including chat gbt work, is they essentially scrape the open Internet.
Jordan Wilson [00:11:13]:
Yeah. There's a lot of, you know, copyright aspects that are gonna get be getting litigated over the next, coming months, quarters, and years. Right? So we'll save that for another day. But, essentially, these large language models are trained on the entirety of the open Internet, closed Internet, copyrighted pieces of works, etcetera. But the absolute freshest data inside of ChatGPT is October 2023, but that doesn't mean that everything in there is October 2023. So now think. Think of all those things. Let's say most of it, best case, is just from the year 2023, but probably from earlier in the year.
Jordan Wilson [00:11:51]:
So you're probably looking at a lot of data that you don't know, and it's generative y'all. So every time you're gonna get something different, you're rolling the dice with a large language model, unless you know, you know, unless you know the tips and tricks. We're gonna give you the weighted dice. You know? We're gonna do that today on today's show. But, otherwise, you could be working with data that's 18 months old, 12 months old. Right? At the very best case scenario, you're working with data that's 11 months old. And I'm gonna go out on a very sturdy limb and say that if you're using ChatGPT for business, I'm guessing 9 out of 10 queries that you're putting in, you don't know where or or sorry. When the information is from.
Jordan Wilson [00:12:36]:
And I'm gonna go ahead and say on another very sturdy limb that 9 out of 10 times, it's going to be extremely out of date, and you don't know. And you're just taking that, and you might have a false sense of security. And you say, oh, this is good. This is this is fresh information. I can use this. Wrong. It's, in almost all cases, out of date. And when you're working with out of date or old information, it makes it inaccurate.
Jordan Wilson [00:13:01]:
And one thing large language models, well, you could call it a feature or a bug, But literally in their system prompt, they are made to be a helpful assistant. Right? Helpless assistant. So if CHAD GPT or other large language models aren't a 100% sure about something, and mainly that uncertainty is caused by, hey. If you're not giving it enough information, what happens at you you know, we talk about this in our free PPP course a little bit, is these models become overly verbose. Right? And they just spit out a bunch of buzzwords at you. And you read it, and you're like, wait. Did this actually answer my question? It's not because large language models are dumb. That's because you don't understand the knowledge cutoff.
Jordan Wilson [00:13:43]:
And if you're asking for up to date, accurate, recent information, a large language model can't provide that. So if a large language model does not feel super confident that it's able to, answer a question, it's just gonna give you these these vague statements, these blanket statements. So let's address that. So number 1 or sorry. That's number 1, that you need to get around that knowledge cut off. And by doing so, number 2, you are ensuring your outputs are accurate and hallucination free. That's the biggest thing y'all. Because, yes, large language models can hallucinate.
Jordan Wilson [00:14:16]:
They can make stuff up. And what and the reason behind that is because you're not starting your chats. Right? We we, preach and teach, this concept of creating expert chats. And a big part of that, like like you would training a new employee, you need to give them the most up to date information first, right, before you're asking a model for an output. You need to go through a training process and give it the most up to date, act accurate information first. But the good thing now is you can do that with browse with Bing. Whereas 6 months ago, a year ago, I literally said on this very show, do not touch Browsing with a 6 foot pole. It's bad.
Jordan Wilson [00:14:57]:
It's very good now. You should be using it. Let's dive in. So, and and, hey, livestream audience, let me know. I'm sorry. Am I still frozen, y'all? Hopefully not. Gotta gotta love tech problems on a on a live stream. Speaking live stream audience, let me know.
Jordan Wilson [00:15:19]:
Are you using browse with Bing? Are you calling out to it, or are you just seeing that ChatGPT is using it? Because there's a big difference. Alright? Let's dive in. So here is a live example. Alright? For pod podcast, audience, I'm showing some things on the screen here. I'm gonna do my best to to read them and explain them, so you can, understand what's going on. So I am in ChatGPT. I'm in the paid account. Right? And I am in the latest version.
Jordan Wilson [00:15:54]:
This even if you have a free account, this is still gonna be relevant to you. Alright. So all I'm saying is, tell me about LLMs or large language models. Right? And then, obviously, within a fraction of a second, ChatGPT spits out, some some good content. Right? So here it is. It's talking about, foundation in architecture, neural networks, parameters. Great. Alright.
Jordan Wilson [00:16:22]:
Fantastic. So we're getting some good information. One thing, though, you should always be doing. Alright? And I need you to train your eyes for this, when using ChatGPT. And shout out to OpenAI, because this is how it should be done. You always need to be looking between your query and the response from OpenAI. And you'll see right here, there's nothing in between there. Okay? So what that means is when I'm saying, tell me about LLMs, and chat gbt spits something back, that means it's pulling from its knowledge.
Jordan Wilson [00:17:05]:
Right? It's pulling from its training data. Here's why that's important. Alright? We're gonna take this concept. Again, this is very simple. Normally, you know, if I was using this for real purposes, I would go through Prime Prompt Polish, right, if I was creating a research assistant. I'm doing this for, simple, explanations today, y'all. So next prompt. And each time I'm showing you a new example, I'm doing this in a new window as to not, muddy up the context or, impact the output that we might be getting from ChatGPT.
Jordan Wilson [00:17:41]:
So now I'm saying, use browse with Bing, and tell me about large language models. So now I'm specifically telling ChatGPT to use browse with Bing. And then you'll see right underneath so I said, remember, you need to train your eyes, because a lot of times, ChatGPT is instantly gonna, you know, spit out a bunch of great content super fast. And what do we all do? We all immediately start scrolling. Right? And you almost start scrolling as fast as ChatGPT start spinning it out. Hey. Admit, livestream audience, is that what you do? That's what I do as well. But between your query and chat gbt, you're gonna see this little icon.
Jordan Wilson [00:18:23]:
Right? And it popped up here because I said using browse with Bing. So I'm calling out to chat gbt. So before I dive into this a little deeper, I wanna talk about GPT-4 o. It is GPT-4omni. So omni model. Alright. So if you rewind to, more than a year ago, and this is when I used to say, do not use browse with Bing. Browse with Bing was a dedicated mode inside of ChatGPT.
Jordan Wilson [00:18:55]:
They eventually, you know, made it, into the default mode, but it used to be its own dedicated mode. So if you wanted to use browse with Bing before you started a conversation, you had to select it from a drop down, and then all of your conversations, essentially, they were querying the Internet. Okay? And I should explain OpenAI has and this is amazing. This is actually an amazing feature now that it works how it should work as an answer, Zincheng. So they have this because of their partnership with Microsoft. So Microsoft has reportedly, invested $13,000,000,000 for a 49% stake in OpenAI's profit arm. Alright? So they have access to use Bing. It is very quick, sometimes too quick.
Jordan Wilson [00:19:44]:
So previously, it was its own mode. So now you need to do what's called a call. Sometimes, ChatGPT, depending on your query, will decide on its own that it's going to use browse with Bing. And like I said, this is why you need to train your eye, Because even when you are not making a call to browse with Bing, there's many instances in which ChatGPT will automatically browse with Bing, which might be a good or a bad thing depending on what your query is and depending how that browsing works. Right? And I'm an SEO geek too. Right? I've I've been in the, you know, in and out of the SEO game actually for, I don't know, 15 10 to 15 years, pretty pretty easily. Not counting back when I was a teenager, and, you know, I think I made my first website when I was, how old was I? 12 or 13. Right? And I learned very early on how to game the SEO systems.
Jordan Wilson [00:20:39]:
But this is back in, like, Geocity days, you know, back in the late nineties. But browse with Bing, it's both good and bad because it's essentially, it queries something. And depending on that query, it might bring you back bad information. And like I said, you may or may not even know or realize when Chat gbt is using browse with Bing, unless you train your eye. So don't just scroll down to the bottom to quickly see, oh, let let me see all this great information that open that that Chat g Chat gbt just did for me. No. You first need to train your eye because even if you're not calling out to Bing, it might use Bing without you even noticing. So you need to look for that little it's going to say searched blank sites.
Jordan Wilson [00:21:26]:
Alright. Yeah. More on that here in a second. So in this instance where I said, using browse with Bing, tell me about large language models. I see that it searched 5 sites. So that means we have up to date and accurate information. Right? It used browse with Bing. We're safe.
Jordan Wilson [00:21:49]:
We don't have to worry whether it's 12 months old, 18 months old. Correct? Nope. Because when we hit that drop down when we hit that drop down button right there, so when it says searched 5 sites, that's actually a toggle, and it is, toggled up by default or you do not see any of the information. So you go have you have to go click that toggle that says searched 5 sites. And look what happened. This browse with Bing thing and, again, y'all, generative AI is generative. It does weird things sometimes. You can run this exact same prompt.
Jordan Wilson [00:22:30]:
Using browse with Bing, tell me about LLMs. And even the queries that it sends to browse with Bing, they might they might be different each and every time. So, unfortunately, in this run, here's what it sent to Bing. So it sent a query to Bing. So all I said using browse with Bing, tell me about LLMs. It sent to Bing, LLMs, recent developments, 2023, large language models. What happened y'all? I just got a very false sense of security. Because number 1, most people just completely scroll past, and they don't even see or realize that they use browse with Bing.
Jordan Wilson [00:23:12]:
Number 2, even fewer people click that button and look at the sources. Think of how often you or your team are probably using ChatGPT. Right? Yeah. That's right. If you're a manager or director and if if if if you have a ChatGPT ban or you don't have a an official, you know, policy in place, guess what? All your not all your employees. Many of your employees are already using, Chad gbt, Copilot, etcetera. So, yeah, your employees are doing this, so you should probably understand how to do it the correct way. So that's bad.
Jordan Wilson [00:23:49]:
Right? That is a bad thing that we just got there. Because I said using browse with Bing, tell me about LLMs, and it's queried into being LLMs recent developments 2023 large language models. Here's the thing. ChatGPT is aware of today's state. That is one thing it is aware of. And if you run the same query multiple times in different windows, you're not going to get this every time. Sometimes it might put the correct date. Alright? And here's the thing with SEO y'all.
Jordan Wilson [00:24:22]:
These some of these so some of the results we're getting are okay. Right? So the first one is hugging face 2023 year of open LLMs. So it's like, okay. That's an okay result. And then we have something from Open Science 2023. So it's it looks like we're getting a lot of these, like, yearly recaps for 2023. But then we also have, something from infoq..com. And here's the thing with SEO.
Jordan Wilson [00:24:49]:
So many times, someone's gonna be ranking, an article from 2020, 2021, and here's what they do. They do some little tricks. They change something in the title. They change something in the meta description, but they actually don't update the content. That is a dirty little secret. So so many of these things that browse with Bing and other perplexity, etcetera, might not be bringing in the information that you want, especially when you have more of an open ended kind of browse with Bing call. Alright. So now let's keep going on, and Marie Marie has a question here, and y'all, if you have a question, please get it in.
Jordan Wilson [00:25:29]:
So she's saying, Jordan, did did your prompt need to be more specific? Oh, absolutely. Marie, it's like you you know my slides. Mind reader. Alright. So we get bad information. Alright. Because here's just a zoomed in version. Right? But we're getting these things.
Jordan Wilson [00:25:48]:
Some of them are coming back. Like I said, I ran the exact same thing again, and I got different results. So in this time, it even searched September 2023. I did it again, and it did, give me 2024. So this is what we need to figure out with targeted browse with Bing calls. Alright. If you've done any of our free trainings, if you've, heard me on this podcast before, you've heard me say targeted browse with Bing calls. Here's what you need to know, and this is the solution.
Jordan Wilson [00:26:26]:
So just like Marie said, we need to be more specific. So here's what I'm saying next. I'm saying, using browse with Bing, tell me recent developments about large language models from August 2024 to September 2024. So, yeah, I'm not gonna put in just September 2024, because, it's only been a couple of days so far in the month. So now this is a targeted browse with Bing call. So what that means, like we talked about, you need to call out to browse with Bing. Because if you don't, if you just say, tell me about large language model developments, it may or may not use browse with Bing. And if it doesn't, it's bringing in old old information.
Jordan Wilson [00:27:10]:
And then if you do make a generic browse with Bing call, you're probably gonna get old information. So we need to do a targeted browse with Bing call. And now you'll see and for our podcast audience, we're getting better results because now I see that, it's binging. Did that ever catch on, y'all? Binging? I don't know. Bing? You bing it? Google's a good verb. Are we binging? Yeah. Maybe. Alright.
Jordan Wilson [00:27:36]:
So now it's binging. Uh-huh. LLM developments, August 2024 to September 2024, news. So this time, it decided to add the word news, even though I didn't tell it to, where previously it didn't, but that's okay. So now I can see the different sites. Right? So alright. And it looks like most of these are from 2024. Not bad.
Jordan Wilson [00:28:02]:
So we got improved outputs. Alright? But I noticed I don't really know these sites. Right? Pastel dot network. Right? There were some other ones. It's like, what if you don't know them? What if they're not authoritative sites? And if I'm being honest, going through these 4 different sites, that's not a lot. Right? Like I said, what if 2 of the 4 are just old SEO sites? Right? And they've essentially been the same since 2020, and they're just doing some, topical updates, and the information is actually pretty old and pretty bad. Right? You need to do a little more research. Here's where we turn ChatGPT's browse with Bing into an answers engine.
Jordan Wilson [00:28:47]:
Here's where we turn it into a legit perplexity competitor. And, unfortunately, right now, search GPT, it's it's almost like a separate product. It doesn't connect, kind of asynchronously to the rest of the ChatGPT ecosystem, which is unfortunate, unless you're listening to this right now. That's why you tune in to everyday AI. We give you cheat codes. Alright? We're taking it a step further. Now we're doing a highly targeted browse with Bing call. So here's what we're doing.
Jordan Wilson [00:29:18]:
Using browse with Bing, tell me recent developments about LLMs from August 2024 to 2024 to September 2024 only. Please search 8 or more different sources, making sure that, while using Browse with Bing, those 8 sources are from 8 different domains. Please go step by step researching deeply, taking your time, and report back only once you've researched the topic thoroughly and have the best possible view of recent developments about LOMs from August 2024, September to to September 2024. So we're throwing in a little bit of, you know, chain of thought prompting here. Right? We're telling it to go step by step. We're telling it exactly what to do, almost in, like, a chronological order here. Right? And now you'll see and it's not always gonna do this. Right? I've I've I've found y'all kind of the magic number is 8.
Jordan Wilson [00:30:11]:
If you ask for 10 or 11 or 12, sometimes it's just gonna give you 5 and give up. Right? It feel like like, literally, if you ask for too many, chat GBT and browse with Bing, it's it's it's like they're, you know, a defeated kid. They're like, oh, I can't do it. I did 3. But if you ask for about 8 or 9, usually, it's gonna give you, you know, 7 or 8. Does a pretty good job, but I've I've noticed through our testing, that's probably the max. And that's okay because that's a pretty good number. So now you'll see when I asked that, it went through and it found 9 sites.
Jordan Wilson [00:30:42]:
Alright. Tara said we'd be binging. Alright. I guess we're binging y'all. So now we found 9 sites, and we see the query that we binged that we beat Bing in. Alright. So it said LLMs, recent developments, August 2024 or sorry. August, September 2024 AI.
Jordan Wilson [00:31:04]:
So even the, the terms that, browse with Bing is is sending through and querying are changing a little bit, but that's okay. I would have liked to see August 2024, September 2024. That's okay, though. We can do that for another day. Maybe we'll have an advanced course on using browse with ping. Alright. But here's what we see. Now we have 9 different sites, and they're all from different domains like we asked.
Jordan Wilson [00:31:32]:
Because sometimes if you don't, it just gives you the same results from the same domain, you know, very similar information. So if you want a really good overview of, as an example, large language model developments, you want to be able to see a wide variety of sources. But something else, let's say you're you're using this for more academic purposes. And one thing I noticed when doing it this way, even with a very targeted browser with Bing call, we're giving it giving it a date, we're giving it some kind of chain of thought, prompting. Alright? If you don't know what that is, don't worry. It's just kind of think of how humans think. Right? If you have a complex problem or a multistep problem, chain of thought just essentially means breaking it down into smaller steps. Right? So when we're assigning browse with Bing to go do this, we're kind of giving it steps.
Jordan Wilson [00:32:19]:
Right? And we're saying, hey. Do this. Look for this query. Go slowly. Take your time. Go different domains. Right? So we're we're we're breaking the problem down, and we're giving specific instructions. But unfortunately, it looks like it brought up a bunch of blog posts.
Jordan Wilson [00:32:34]:
Right? These listicles, you know, list of 20 list of the 21 best large language models. And it's like, okay. That's not necessarily what we wanted. If we're asking for recent developments in large language models. We don't necessarily want, you know, blog posts or in listicles and, you know, these these, entities that just have great SEO. Right? It's probably not what I wanted. So if the sources aren't very good, you take it a step further. Alright.
Jordan Wilson [00:33:06]:
I'm not gonna read this whole thing, but here's what we added to the end, of this query. So we add in now, please only use authoritative sources for information, such as and then we're giving examples of some authoritative sources of, large language model paper, scientific research, etcetera. So I'm saying such as, ARXIV, Microsoft, OpenAI, Google DeepMind AI, Kaggle, and others. And then again, saying, please take your time and search at least 8 sites. Now you'll see search 7, but that's okay. Because now I'm looking, and it's only searching these authoritative sites. It's looking at Microsoft. It's looking at DeepMind.
Jordan Wilson [00:33:50]:
It's looking at Brookings. It's looking at a r, a r 5 ID. It's looking right. So it's only giving me now more authoritative sources. Alright? So that's great. Guess what y'all? We just solved so many of your problems, whether you know it or not. That is how you should be using ChatGPT. Okay? Again, you should be taking our, our free prime prop polished PPP course, and we go over, we go over this a little bit in our priming phase when we talk about RefineQ.
Jordan Wilson [00:34:29]:
Because one of the biggest things that you need to do and, you know, obviously, a trend of 2024 has been RAG, Retrieval Augmented Generation. That's essentially when you connect your data into a large language model. You do some fine tuning, etcetera. So you can't technically do that in the front end version of, you know, checkGPT.com. We kind of call this process, though, mini rag. Right? In in RefineQ, that's our process of you take a 1.8 trillion parameter, large language model, and you need to make it smaller. Right? And you do that in the beginning by giving it more up to date, accurate, and relevant information, because now I can have a conversation, and I can direct the outputs better knowing that number 1, I'm probably not working with data that's 18 to 12 months old. That's problem number 1.
Jordan Wilson [00:35:22]:
Number 2, I have much more control. I have a a granular level right now of control over where of the rest of the conversation goes. Now that in the context window of this chat, ChatGPT understands exactly what I'm looking for. It has more up to date information. So it's it's it's not gonna give me this, you know, wishy washy, overly, content that says nothing. Right? If you put in the work up front, you're gonna get better results. Alright. Good good good question here.
Jordan Wilson [00:36:00]:
And if you have a question, get it in now. I'm gonna be wrapping this one up soon. I don't need this to turn into an hour long podcast episode. Where'd it go? Where'd it go? Okay. Marie asking Jordan, I noticed in most of your prompts, you asked the LLM to take your time. Why is that? Great question. Great question, Marie. So there's been plenty of studies that show when you, tell ChatGPT to take your time, take a deep breath, use manners, right, you get better outputs.
Jordan Wilson [00:36:32]:
There's technically been research that show both sides. Right? There's been research, and from world class researchers, there's been, examples. I believe that when you talk chat gbt, in a friendly manner, when you tell it to take your time, take a deep breath as an example, it performed about 40% better, on solving some complex math problems. So, you know, kind of encouraging it to, think in chain of thought, to take its time, etcetera. Then there's been other research that says it doesn't matter. So I'm gonna go on the side of, I don't know. My mom raised me to be nice. Right? So whether I'm talking to a human or a large language model, right, anecdotally, I say it works much better.
Jordan Wilson [00:37:12]:
That's just me. Alright. So here's the last thing about the correct way to give ChatGPT access to the Internet. Alright. Because if you are putting in a I see this a lot. This is a big mistake. If you're putting a URL into ChatGPT and you think, oh, well, it's browse with Bing. It's going to find the correct information.
Jordan Wilson [00:37:32]:
No. It's not. Alright? So if you say as an example, right, and and and you see the little browse with Bing thing flicker, and you're like, oh, it went to this, this web page. No. It didn't. So all it does when you give chat gbt, if you say, hey. You know, go research these specific sites or go bullet point and give me the takeaways from this specific article. You need to look at it.
Jordan Wilson [00:37:55]:
Right? Click the drop down and see if it actually went there. But all it does is it bings or it queries the keywords in the URL, which may or may not bring up the actual web page you want. So it's technically, a way that you might be bringing in hallucinations and not knowing it. So all it does is it bings the, keywords in that URL, which may or may not actually be bringing up the page that you want, at least when you do this inside of ChatGPT's default mode using browse with Bing. Easy way around that, use an Internet connected GPT. So in this case, I'm using a GPT called web pilot because a couple of our other, GPTs we use a lot were being a little finicky, this morning when I was planning this show, you know, using VoxScript, web reader, etcetera. But there's a lot of Internet connected GPTs. So what this means is you need to, GPTs are free to use, if even if you have a free ChatGPT account.
Jordan Wilson [00:38:54]:
If you if you want to build a a GPT, a custom GPT, you have to have a paid account. But if you use an Internet connected GPT like WebPilot, then I can say right. So I pulled 2 different URLs, about some LLMs. Right? Because that was our our whole topic, our example. And I'm saying, please bullet point the main points in these articles. Right? I just dropped 2, but you could drop. I I I I'd say most GPTs do a pretty good job handling 5, at least 5, maybe 6 URLs. And then it's going to go through an Internet connected GPT.
Jordan Wilson [00:39:27]:
It's going to autonomously visit. Right? You don't have to do it one time for each URL. Like I said, most GPTs can handle somewhere from 4 to 8. So if you have a bunch of research that you wanna do inside of ChatGPT before getting, your chat started, and maybe you don't want to leave it up to the discretion of Bing, even if you're using a targeted browse with Bing call. Right? So maybe there's some long industry papers that you wanna look at. Maybe it's something on your company's website, maybe a competitor's website, maybe a market research trend, etcetera. Right? And maybe you're like, how am I gonna trigger this with a targeted browse with Bing call? So an easy way to do that is to instead first use a GPT. So you need to go into the GPT store, install it for the first time, and then after that, all you need to do is click the at button on your keyboard.
Jordan Wilson [00:40:14]:
That's called an at mention. You start typing the name of the GPT, and that's it. And then when you're done grabbing that information and putting it into the context window, you can click the x button, and then go back to kind of talking with the default version of ChatGPT. Alright. Y'all, that's it. Now you know the correct way. And, like, Ben just said what up, Ben? Good to see you. Ben just said, Wednesday gold bada boom bada bing.
Jordan Wilson [00:40:45]:
Thanks. No. Thank you. Thank you, guys. But, also, you need to put this into practice. You need to go out, do this for yourself now. So very quick recap. Huge problem if you are not careful when using large language models, even ChatGPT, that now has a great browse with Bing feature.
Jordan Wilson [00:41:09]:
You always need to be looking with your eyes to see, because ChatGPT, even when you tell it even if you don't tell it to, it might be going to browse with Bing. So you always need to scroll up and look. Did it go to browser Bing? Yes or no. If it did, did you want it to? And also check out the sources that it's that it's going to. And then do a targeted browse with Bing call. Make sure you steer the model in the direction of the information that you want, and then you need to put that information into the context window. So then do this in the beginning when you start, when you're having a conversation, when you're having an assignment. Right? So it's literally like if you were to be working with a a a consultant.
Jordan Wilson [00:41:48]:
You always wanna know, hey, consultant. Do you know the most up to date information on whatever I'm using chat gbt for right now? Because if not, you're gonna get old, out of date information. You're gonna get this overly, content or output that says nothing, and worse, you're probably gonna get some hallucinations if you aren't doing this the right way. But if you listened, if you went through today's show, you got it all right. Alright. I hope that was helpful. Hey. Marie said, terrific session today at AI University.
Jordan Wilson [00:42:24]:
Fred said, great session. Y'all, if this was helpful, do me a favor. Right? Sometimes I stay up super late or wake up super early. Right? I think just I've covered about every hour on the overnight clock except, like, 2 to 4 AM. Right? I'm up at all hours researching things so you can be the AI leader at your company. It takes us hours sometimes to do a single episode, y'all. It takes you seconds to go ahead, click that repost button. Alright? So if you're listening on, you know, Twitter or LinkedIn, go ahead retweet this, repost this, tag a friend who needs to hear this.
Jordan Wilson [00:43:04]:
That would be great. If you're listening on the podcast, we appreciate your support. Please, like, subscribe, follow. Can you like? No. Subscribe to the podcast. Leave us a rating if this was helpful. Make sure y'all we're gonna end this probably next week. Alright? Go check out our thanks a million giveaway.
Jordan Wilson [00:43:20]:
Go to your everyday ai.com. You're gonna see a little banner at the top of the website. You sign up for the giveaway. You're going to get a referral link. So if this was helpful, go send that to people because you can, win, either a year long subscription to whatever your favorite large language model is, chat gbt, you know, CoPilot Pro, you know, consumer license, y'all, not paying for your whole company. One consumer license. So, you know, chat gbt, Gemini, Claude, etcetera. And we're also giving away some consulting sessions.
Jordan Wilson [00:43:54]:
So go ahead, get that unique referral link. Go send it to your friends. Go post it on social media. We're wrapping this up soon. We're gonna give one prize away to the winner and then a couple random prizes. So even if you can't catch the winner, all you gotta do is go enter, and then all you gotta do to keep growing is keep tuning in. So go to your everyday ai.com. Thanks for tuning in.
Jordan Wilson [00:44:13]:
We'll see you back tomorrow and every day for more everyday AI. Thanks y'all.