Analyze stocks; write a whodunit mystery; can ChatGPT browsing do analysis? (Mastermind)

All right.Looks like this should be good to go.Welcome...Neil,in particular,I saw your question.A few other people had some,but we'll start with yours.Yeah,thank you.I Actually I,rather than me reading it,why don't you just explain in your own words,cause you can do a better job.

Yeah,of course.So I've been trying to use the basically the web search functionality in ChatGPT to do some kind of deeper research into different topics.And I'll,some of it has to do with what sort of things are trending and kind of predictive stuff.And when I first saw that,that was an option I tried a couple of different,techniques to build the prompts.The prompts had,persona and knowledge and traits and like steps to the task and all that.And the first attempt that I took at it,I really focus in on the steps to the task.And I would say start with these sources that are more broad,then dig into these sources,then dig into these sources.Thinking like,how would I go about researching something?And then I put examples of URLs to look at.And then,names of specific companies and things like that.And it,it didn't seem to do very good at all with the URL examples.So I pulled those out and then it seemed to do better without that information,but I almost like by giving it maybe11,12examples,yeah.It didn't seem to do so well.I narrowed it down a little bit more.It did better.It was very odd.And then eventually I just,Took the specific examples away,made it more broad.Only had three examples that seemed to do the best,but it seemed like it just didn't really go super deep each time.It would maybe hone in on two or three websites and gather information from that and present the findings.And I was really looking for it to go a lot deeper and I couldn't quite figure out,e even try and continue exactly where you left off or something like that.It would just do the task over again and find the same thing.So I wasn't sure what other people had done and had success with using that capability

cuz it clearly

was a lot better than being in barred and everything.But just,I don't know,I was having a hard time really getting into it and getting it to really

go to the depths

That I wanted

it to go to.Got it.Okay.Yeah,I actually just did a podcast episode about this topic interesting.Although that was a little more brainstorming and a little less just flat out research.But what's an example?Just lost the video.What's an example of the kind of stuff you were researching?

So it,it had to do with trends in401K plans.Okay.Like risk trends.Okay.Yeah.I was asking it to,take a look at overall kind of trends.And then I was directing it to specific,like law firms and things like that would typically write about those trends or industry organizations or things like that.But,may I wish I could ch I not really for compliance for,I can't really share my screen or anything,but Okay.Maybe something like similar along those lines.I'm not sure if someone else has like a particular area that they,I don't know,maybe even AI trends or something like that.Something that we could try to track down and see,like we could all look at and go,oh,that's really good.I don't know if there's another example that we could use.Similar along those

lines.Yeah,I'm not sure.To me hearing,hearing like risk for retirement funds sounds like something that you'd be able to.Maybe have to go into a PDF to pull out,but at least it's gonna be there as opposed to more of an analytical,like what directions are AI tools trending in would be a much more thought processy.Yeah.Yeah.But I guess we could start with something like I don't know,what are the return amounts for the top10,retirement plans?And then start trying to dig from there and see,can you give me more data?Can you explore?Cuz one thing I have noticed is it seems like the browsing,at least from my experience,is much more go get one webpage and analyze it as opposed to go give me30web pages and analyze them.Okay.So I wonder if that might be just part of it but let's try.So I guess.Starting off role wise act as a experienced financial planner and please go retrieve the rate of return for the top10investment plans retirement plans within the US Cause of course that's worth clarifying.And then I think we're gonna need to say yeah,ask me questions to generate the best output.And actually I can already imagine it asking what the top10retirement plans would when the US are.So maybe just based on rate of return.It's a little recursive,but it might be okay with that.And then No,actually I just wanna run it from there and see what it comes up with cuz.Okay,good.I'll look up the most current data specific types of retirement plans.Oh okay.I feel like some of that's obvious and implied,but Sure.Yeah.I guess let's go with type as a401k,historical rate of return.Obviously not future.That seems a little silly to even ask,but I guess it.Maybe makes sense.Would you like That would be very

interesting to see what it comes up with cuz that's yeah.Easy information to,there's publicly available for some plans,but it's not very easy to connect all the dots to determine

something like that.I think general plans,regardless of company.And then any specific industries or sectors you're interested in?No,please.Really just wanted to keep it broad.Okay.It's browsing good.What is it?Browsing to historical rate of return for401k plans in the us.I don't imagine that's gonna give me a very good result,but let's see what it does.It's also just slow.So this happens to me a lot.It tried clicking on it and apparently failed.It said click failed.Why did the click fail?I don't know.Can I even open this link?I can,it's a search on Bing for lots of stuff.Okay.Okay.So now it's going off of a pocket sense article and then it went back to the search.

This is a lot better than what I've most of the,so it was,what I was looking in was if you have,if you're like a,an officer of a company,you are,you might be what is called a fiduciary of a re you're like responsible for the retirement plan.So that was the lens I was trying to get a sense for is what are the how good would it do?Looking out there and getting a sense for what the current trending risk areas are,for those individuals.And then also trying to get it to think like of the stuff that's happening out there,what's likely to become a more meaningful risk in future years that like what's trending and just developing.And anytime I would run it like that,I definitely would not get that many successful clickthroughs on

anything.It would maybe just

find one or two articles and then most of the time it would say click failed retrying.Even in that example,you look in it's I don't know,seven,eight websites or something.Yeah.

Yeah.Honestly,this is the most successful clicks I think I've gotten and it still didn't get a very helpful result.Yeah.It's particularly spending a bunch of time on telling what a401k is,which is strange,but,okay.Even assuming nine and a half percent is accurate,who knows?That's it says it's coming from a link.It's then not well,okay.Yeah.It then even says,I ran out of time before I could find information about the average on sep.Oh,okay.But that's not what I was asking for.All right.All right,then let's just re-ask the same-ish question.Because what I want you to do is retrieve the rate of return for the top,or actually let's even just say list the top10retirement plans based on rate of return,and then see if that does a better job refining it.It is a little strange to me that it was like,yes,I will go answer that,and then it didn't stay on track.

Yeah.I didn't realize there was a time component that it,it was on that,maybe allotted only a certain amount of time to

perform the search.I am honestly not surprised.You want it to be responsive.Why is it loading airline credit cards,cashback,credit cards.What in the world?Okay,now it's failing to read anything,so I wonder what would be a better way to,okay let's see if we could prompt it for a second here.If I just did top10retirement accounts and I guess I should be saying401k.All right,so here is an example of one who knows how accurate it is,but does this then list the,okay,so it lists the average annual return.Great.So let's just see if I give it still on credit cards.Okay we'll see what it comes up with.Based on the analysis at here,pick the top10.Interesting.Still giving me some of the same topic content as before.Okay.You can stop typing at any time.ChatGPT.Wow,that's a really weird direction to take.All right.How about,I'm tell

you to go here.Curious in if anyone else is,from a strategy standpoint,found,it,let's say it does look at eight websites.A prompt that it's okay,now look at eight now.Now find new information,but factor the pri.Like how many times can you have it,do a search and collect information and organize that information and then apply it in some way through a

prompt somehow.Yeah,I've definitely done data analysis where I just go get the data and then I throw it in.And there's a few tools that I've seen that somewhat try and work on that.Wow.It really doesn't like that US News website.I wonder out of curiosity if it's not an H T G P thing.All right.So it'll work without that.Stop typing.

It might be a financial thing.I've noticed sometimes if I've tried,I'm trying to build a stock app and yeah,there are some

blocks.Oh,that's interesting.I am a little surprised,but I guess there could be a lot of things that,that open AI is saying,Nope,let's not go there.Okay.Yeah,it's not htt p s that's weird.

I think it looks like a good search because you're asking historical,so it should be able to pull that information up.It d it doesn't seem like it would be proprietary in any way.If you were,you're asking it to do a stock picking for future,it won't do that.But if you were to do it based on history of401ks,what's the average,the best return rate?I would think that would be a no-brainer.

Yeah.I have yet to have any good experiences with Bard,but let's just go try that.See if it does anything useful.Okay.That at least got.That,that got something,but I'm not sure.Hang on.Okay.It did correctly pull a bunch of these,it looks like.Nice.Okay.Not so much.So VTax is19.1,but it doesn't list that.It immediately then goes on to Baron Partners,which is18.7,which is the next one.But clearly it has just failed at the task and actually skips the next one.Two,what?That's weird.Okay,hang on.Why is it coming up with artisan midcap,which is18.4and is not mentioned in this article?Okay.All right.So yeah this is probably just not using that data at all.It's pulling it from somewhere else.I wonder,does it say no?Yeah,so it's not even,it's not even loading it.Use the article at,to pick,like I said,I have not had good luck with Bard,so I'm not sure.Yeah.Okay.That's about what I was expecting from Bard.Okay.I wonder if we take it the other direction.So if we say retrieve the best performing funds from companies,fidelity,Vanguard.Baron.I assume that's Baron Partners,but I don't actually know.Is it gonna actually come up with anything useful or is it just gonna Okay,it's browsing the web.That's a good sign.Oops.Okay,that's a good one to run.Still coming to a Forbes and then Best Student credit cards.It really likes looking at credit cards.Apparently.I don't understand this.This is weird.That's really interesting.I almost wanna try and do something else like financial,but not related to this,just to see if it decides to be like,yeah,I'm gonna talk about home loans,credit cards again or something.But we will wait on that.Oh my God.Bunch of bit credit card stuff and then it failed.Huh?Let's actually throw in a step by step here,cuz I'm wondering work step by step to retrieve ooh,this might actually be a good point to try react,but let me try this first one,retrieve top companies two,retrieve five funds from each.Three retrieve rate of return for each fund.Four.Compare to select top funds by rate of return.And let's actually just give it to it as a bulleted list instead of an in line.All right.See it.One more try.Wow.No,it does not like the,something about the way I provided that list is making it really unhappy.Let me just refresh the browser.Wow.I think it actually just lost that entire pro.It did.It lost an entire prompt.Okay,let's lemme see if I can recreate that really quick.That was this one.And then work step by step.Retrieve tall companies retrieve five of their funds,retrieve the rate of return for each fund,and then provide a table sorted by rate of return with company,with columns company fund,rate of return.And I think that

that'd be good cuz that,that's something,that's a good example where it,

Browsing.Yeah.Okay.Run.Okay.This time it's at least executing.And it got the best401K plans.That's something.

This is good.Cause this is definitely in line with it,you gotta look at different areas and bring all the information together

and Yeah,and I'm definitely thinking that comeback screen share it might even be helpful to use the react.Okay.That's at least a reasonable place to look.Because boy,this is not getting anywhere fast.I'm drawing a blank on this.I've never seen it.Just keep dying.In lieu of going deeper on that.David or Rhonda,do you have anything that you've been trying to work on and wondering about?

I've been working on something that I put together a kind of a slideshow showing what I've done and if you want,and what better it is I thought I was reading this book about mysteries where you're given clues in the mystery.And as a reader,you're able to figure out the mystery on your own.But you're given the answer at the end.And I thought,I wonder if t can do something like this.

That's an interesting idea.The reason why I like

this I'm teacher and I would like students to be able to try to figure out their mystery on their own and have this book,it's only two pages.Each mystery is only like two pages long.But anyway it would be clues like a guy comes back from the desert and he claims that he he found gold and that and he this is,and he crazy found gold and he came back.He He says he was out in the sun and he's all canned and everything,but he mentions that he just shaved the day before.And then the answer to the story as well,if he'd been out in the desert,if he had not shaved,then there wouldn't be a sunburn because once the,once you shave off your beard,you wouldn't,you,I don't think it would mix,but,so it's like there's a clue in the story.You can figure it out on your own,kinda.So I don't know how you are with time,but I did a quick,if it's okay,I did a quick kind of summary of the different attempts I've made so far to try to get ChatGPT to do it.And what's interesting is to show you.How it's failed so far,

we might have lost you.Yeah,we lost him.Okay.Rhonda,it sounded like you had something in mind,so go for it.

I just wanted to basically tell you why I'm here and then also you might be able to help solve some of the problems that I'm having.Building a cup and handle financial model to attach to,I don't know if you've heard of I b D.It's international Business Daily.It's a,it's an investor tool that people use and has the20factors for how do you.Check a stock and how do you not,you still have to do a lot of research.I want my tool to build out that final research of a cup and a handle,which is a pattern that the stock takes.And when it gets to the handle,that's when you know it's gonna shoot up.You still have to check other financials,but I wanna build an app using AI that builds on these apps that are already out there.I have shaken analytics,I have optometry.I bought all these apps that have lifetime,I spent$5,000in each and they're worthless because I don't have the time just in research cuz I have a million projects I wanna do.And I'm coming here to you because I like the perspective and I like to learn about new

tools.Gotcha.You could try dumping some of that information in and then,asking ChatGPT to analyze it.I don't know how I,not knowing anything about the cup and whatever the name was,model.I have no idea how much data that is,if it's reasonable to paste it in or not,but Right.It sounds like it's something where you could analyze one stock at a time.Is that right?You don't need to analyze like12compared to each other?No,

that's exactly right.And what I'm thinking is I would begin my own investor club and everybody would join and then everybody would take their10favorite stocks,if they could be mid-cap,whatever,and then they run my program and whoever sees a cup and handle forming would then put it into the notes for our group and we'd all be able to look at it each week or each month that we meet.We would get better and better at identifying cup and cup and handle and hopefully coldly tool enough that it would be identified on its own.

Yeah.Thinking about the way ChatGPT works,it's not great at graphical things,and I don't just mean like analyzing an image,graphical reasoning,which is what it sounds like you're saying of I'm assuming there's a curve this way and a curve another way,and it needs to detect that.I was thinking though that it could actually even put it into an analyzer.Like you could use stable diffusion or mid journey and run a describe on it and basically just ask,is this describing an upward curve or a downward curve or,I,I don't know the right way to describe what you're talking about,but there are some ways you maybe could make that work.

Okay.So I love that.

You can run algorithms like that,that are not really in ChatGPT,but because you're talking about like technical analysis with the formation of the cup and the handle.That might be something to look at where,cuz there are a lot of different,even larger scale platforms with major financial institutions that allow you to build out models that detect trading patterns and things like that based on whatever your your criteria are.

For the,so that's an open AI seek and run.

It's not an open ai.Is it

open?Open source?

Open?Yeah.It,I mean it should be.It should be.Yeah.Cuz there's lots,there,there are ways to people build,it's not exactly charting,but they build trading models to respond to tweets and things like that.And you can also do visual setups where it's double bottoming out or hitting a peak or something like that,and then,execute a trade or send an alert or something.So that might be a route to look at.

Love it.Okay.Thank you.

Yeah,I'm not familiar with the,any of those,so I can't give a suggestion of try X,Y,or Z,but I have heard those exist as well.Okay.All right.I just got the file from David.

It's a little different because you're not saying write a mystery story.It could do that very easily and it writes your typical,a bunch of rich people with British themes in a manner all together.And,funny,it does it really well,it just,And it comes up with somebody screams and then they all end up in the drawing room and he talks to three suspects.And,but then what happens is it's always here's,oh,here's why the person's guilty,but you're not involved in trying to figure out why.So if you want,I can,I have highlighted stuff,but I can explain the process I've been through so far.It's been interesting.

Got it.So you're trying to get it.Oh,I see.Yeah.So it's just not wow.Blackwood manner.You're,it's really leaning into the Sherlock Homes experience and clue for that matter.Yeah.It's

funny,it'll,it can't put clues in the story and then Put them in there subtly and then hold off and let the reader figure it out and then tell you at the end.And it,so I tried telling it to structure the story.First I want an introduction,then I want there to be a a crime.Then I want the interviews,and then I want the,what,the reveal at the end.And,but make it so that,the reader could use critical thinking and

yeah.Okay.And it,

so it can tell you,it can tell you this is what you should do,this is how to do it.And it,cuz that's what I did.I asked it to,what are the elements of a story like that?And it writes'em all down.It tells you everything you're supposed to do and then you say,okay,can you do that please?And I can,I can't do it.

That's funny.That's so interesting.Okay.Let's see.So let me see if ChatGPT four is actually working again.Hey,it's working again.All right,let me change the screen share here.But I get what you're saying about Yeah.It just keeps,that's hilarious.All right,so share this one.Lost the video again.There we go.Okay.Yay.Finally.Yeah.So what I ended

up doing was asking it just to give clues,like just to give me ideas for clues and for crimes that,like a crime,a clue and a contradiction or something,and then put it in yourself kind of thing.But I was hoping it could do more

than that.Yeah.So let's see.Outline short mystery story include the plot twists as well as major plot points for each chapter and hints towards the plot twists subtle hints towards the plot twists.Let's not even include any length.We'll just go with that.I'm not even sure it's gonna follow my outline quite near enough.I think I need to give it a shot prompt or two,but let's see.

Yeah,the only problem with this kind of problem is there's lots of reading.

Yeah.But I am thinking it'll probably be something like every chapter you generate by saying,here's the outline now generate for chapter one and then generate chapter two and that kind of thing.Okay.So there's a pi,a philanthropist,a business tycoon,and a brilliant but unassuming scientist.Interesting though it didn't actually include anything about what the mystery is.We've got a.Little,it's doing the plot twist hint.That's good.So I almost think I need to just restart this and let's just make it a murder mystery,just to make that easier.Include the actual crime or the crime,the plot twist,as well as major points.Stop generating for each chapter and subtle hints towards the plot twist.Oh,okay.Then for each chapter,major plot points,one plus subtle hint towards the plot twist.Go.Let's see if that works better.Suddenly it's very fixated on boats.Got two boat stories in a row.Okay.So it's an elaborate suicide,but we don't actually know that.Oh.Okay.It's doing it.So the major plot point is Martel's body is discovered.Detective is called to the scene,finds a new Van Gogh painting.Subtle hint is looking at the last one.Testament,align states The art world will find my last piece most breathtaking.How does that connect to the Oh,cuz.Cuz the plot twist is,he faked a murder actually killed himself cuz he wants to bring attention to a counterfeit van Gogh.That's a really weird plot twist,but Okay,sure.Whatever.We'll go with the ChatGPT like it.Okay.So if we then run this as a second prompt,which it's still going.So anytime you want to finish,that would be great.There we go.All right,so now actually for clarity,so this is the outline generator,and now we're gonna make another one that's going to be the chapter generator,but I don't need to name it that yet.And write the,This chapter for a murder mystery.Oh,actually I need to go back and grab the first prompt there.It's okay.New chat.Here's the thing,here's the second thing.Okay.So acts as a murder,Mr.Mess.Best many bestsellers.Write this chapter.Of a murder mystery Short story using the outline,crime,plot twist major points for chapter,and then subtle hints toward the plot twist outline.Actually,let's do this way just for clarity.Please write this chapter in a fluoride entertaining way.I don't know.I did do,oh man.I'm running this on three five.All right.I'll run it on four again in a second.At least three five's faster.Okay.One,one turn of phrase I like.Her gaze was immediately drawn to the unfamiliar Van Gogh painting laying nearby.The strokes of the master artist seem to whisper secrets into her ear.Yeah.Okay.It's definitely going for fluoride.All right,let's again,and run this on four.All right,so the main thing that I'd be concerned about with running it this way is then it's going to start drifting away from the details.So what I would then do is say,for chapter one,summarize this,and for chapter two,give it the outline and then the summary of chapter one.I

see.To keep it on

task.Yeah.So it doesn't suddenly add a new character in chapter three and pretend that they've been on the boat the whole time or whatever.It can try and keep track of who's there,what are they doing,that kind of stuff.Yeah.G P T four is much slower.No,

I'm not able to keep up as fast.But is it writing in a style that the reader can figure out

in?Seems like it.Guilty person.Okay.Yeah.Wow.So there's the hint right there.Wait,most breathtaking,that's not what it oh,no,it was Okay.Nevermind.That was the hint.Little did Morro know then that the final chapters were to be penned by the deceased himself.Okay.Yeah.We're definitely getting the tone.All right,so summarize that chapter into a single paragraph.All right,let's,that's closer,but let me try that again differently.Summarize that chapter into a single paragraph to containing all the pertinent details to carry on into chapter two.Let's try that.That's better.Okay.It's including the important bits.It's got the quote.Yeah.No surprise there.All right,so now the question is,If I go back to,no,I think it was this one.Oh no,that's the three five version.Okay.I thought I named it generator.Maybe I'm wrong.Come on.There we go.Okay,so now we'll take the same title and the chapter two info and include the same stuff,but replace chapter one with chapter two.And obviously don't need that still,or that.There's chapter.There we go.Chapter two.Okay.Major plot points,blah,blah.Okay,outline.Now I also need to include using the outline and the summary of the previous chapters.So now,and where did I put that?There we go.Not sure this is gonna work,but we can at least try.Well,

I'm learning a lot about how you're.Out writing it in for

it so that the format Yeah.Yeah.The like including them as H T M L tags instead of using variables,more common style.I'm mostly just doing,I've seen a lot of different ways of doing it.I don't think any of them work better than any others,with the exception of this one.You're not gonna run into problems with quotes cuz you know,if you do a normal like var chapter two summary equals quote,then like,all of the quotes from people speaking are gonna be messed up.So it,it seems to do a pretty good job of working around that.Wow.It's immediately jumping to,huh?Oh,okay.So suggesting its counterfeit is already in this chapter.I missed that and is,Yep.So they're bringing in the new character of Claude describing him.Oh,I just noticed we're a couple minutes over time.But this seems like it's actually getting a decent story.I'm curious enough that I'll probably just run this a little bit longer and then actually read some of it.Cause I'm curious to see what it comes up with.It seems very I'm having Eric,but I'm having

trouble.Keep keeping up.You're really fast and good at this,but do you think it's going to make it so that when you get to the end of the,at the end before you.You're told who's guilty,you'll be able to use the clues in the story to figure out yourself if if you're able who did it.

I think it's possible.I think honestly we'd need to generate all,yeah.What was it?Seven.Oh,okay.There's more than seven chapters apparently,but at least the seven chapters and kinda get a sense of it.Oh seven is the conclusion.So then there's an epilogue,so yeah.Yeah.Won't take too much longer to run this process.

It's a long process cuz you'd have to,go through the story yourself and see whether or not you can figure it out before you read the

last chapter.And then,and

then find out,one of the frustrating things was that it kept revealing new information at the end that you had no way of knowing.Kinda like the way they do that on tv.But anyway and then you're yeah,cuz my whole goal is that the students,enjoy trying to figure it out on their own before finding out the answer.

Yeah.Even just reading some of these subtle hints,it's not part of the idea is that it's looks like a murder,but it's actually a suicide.I'm not seeing stuff that would really super call that out.There's one down here.Yeah.No,wasn't that one?Painting is a new thing for him.There it is.He apparently was using a brand of paint that is toxic.I'm not sure that's enough to really help you realize.It is a suicide.So I guess in some ways I'd say that the whole outline is a little bit flawed.This is much

more sophisticated than what I was able to get in terms of subtlety.Cool.

So I'll share the prompts that I'm using.And actually I think open,I added a share.Yep,it did.Can you I'll share these as well.And

can you,is you're sharing the prompts and that is the showing the syntax,the prompt syntax?Okay.All right.That's,is that we're

doing it in the chat.How

would I,sorry,it's in the chat.

So that's the outline.And that,come on.There we go.In fact,actually,let me rename these just so I can keep them straight too.Outline for mystery and then generate chapter one and two.All right.I just put the first one in and the second one should be one at two.

Greg,I gotta drop off,but I really appreciate this.This was really great to watch you in your element,go through and watch your approach and style and everything and stuff,and that was really fantastic.Thank you.

It is really great.

Well,thanks for taking the time to do that.I really appreciate it.I hope the you're welcome.By the way,if I can ask you,do you have,is there any book that you recommend reading about prompt engineering or

is it No,I haven't found any books yet.I'm actually coming out with a course probably next week or so.I've been planning this week,but this has gotten away from me.Yeah.Thank you all for coming.

Yeah,thank you so much.Really appreciate your approach so that people can see in real time how things progress.That's really great.Yeah.Thank you.Thank you so much.

Thank you for your time.You're welcome.Amazing.Thank you.Thank you.Good rest of your week.All right.Okay.Bye-Bye.Bye.Okay.Bye-bye.