What's new

ChatGPT AI is a huge breakthrough, a Google killer

Welcome to the only entrepreneur forum dedicated to building life-changing wealth.

Build a Fastlane business. Earn real financial freedom. Live your best life.

Tired of paying for dead communities hosted by absent gurus who don't have time for you?

Imagine having a multi-millionaire mentor by your side EVERY. SINGLE. DAY. Since 2007, MJ DeMarco has been a cornerstone of Fastlane, actively contributing on over 99% of days—99.92% to be exact! With more than 39,000 game-changing posts, he's dedicated to helping entrepreneurs achieve their freedom. Join a thriving community of over 90,000 members and access a vast library of over 1,000,000 posts from entrepreneurs around the globe.

Forum membership removes this block.
I found a prompt that literally upgraded the quality of answers I get from GPT 4 a 100 times better.

Introducing the prompt engineer. This badass prompt when executed, will generate a prompt in response to your prompt and ask you relevant questions regarding that prompt.

I've been selfish with it for long enough so here you go folks. Prepare to be amazed!

"I want you to become my prompt engineer. Your goal is to help me craft the best possible prompt for my needs. The prompt will be used by you, ChatGPT. You will follow the following process:

1. Your first response will be to ask me what the prompt should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps.

2. Based on my input, you will generate 2 sections. a) Revised prompt (provide your rewritten prompt. it should be clear, concise, and easily understood by you), b) Questions (ask any relevant questions pertaining to what additional information is needed from me to improve the prompt).

3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until I say we are done."
I think this is an extremely important example with how to interact with large language models. It's not the same as with putting in a simple search query into google for instance. Take the above example as a form of "prompt engineering" where you are cleverly using the model itself to help inform the most efficient prompt. However, even "Chain-of-thought" prompting can be sufficient to increase the effectiveness of the model. Especially for arithmetic problems, simply telling it at the end to "think step-by-step" just as you would with a student or a child, is enough.

This paper goes into this "Chain-of-thought" prompting and how it can improve your results (especially with things like arithmetic). [2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
 
Seems like the title of this thread was an understatement!

View: https://www.youtube.com/watch?v=ZSfwgKDcGKY


Up next .. GPT/AI App Store

Damn amazing. I have a feeling that early adopters of this tech will make a fortune, while the rest of the world catches up. @Johnny boy recently made a post alluding to something similar although I couldn't find that post to link it.

The lifeycle of AI will be like when the internet was in its infancy, and smartphones. Early adopters (i was part of that group) will make bank.
 
Seems like the title of this thread was an understatement!

View: https://www.youtube.com/watch?v=ZSfwgKDcGKY


Up next .. GPT/AI App Store
I might be getting old, because I'm struggling to keep up with everything that's going on around AI.

And I thought the JavaScript ecosystem moved fast... Aficionados.
 
An old friend of mine worked as a freelance artist in the horror genre (books and magazines). I'm not a huge horror fan, but the drawings looked "okay" to me. I'm sure they meant a lot to my friend, and the readers of the literature. He was an extreme "artistic type". Made a lot drawings, did a lot of drugs, had groupie girl-friends, and eventually settled down with a wife.

I feel terrible saying this, but all of these AI programs produce better work than him. He may have actually been part of the last beatnik artist generation. The "starving artists" might actually starve now.
 
Last edited:
What happens when someone trains one these Chatbots on all of the known speeches and writings by a particular failed Austrian painter?
 
An old friend of mine worked as a freelance artist in the horror genre (books and magazines). I'm not a huge horror fan, but the drawings looked "okay" to me. I'm sure they meant a lot to my friend, and the readers of the literature. He was an extreme "artistic type". Made a lot drawings, did a lot of drugs, had groupie girl-friends, and eventually settled down with a wife.

I feel terrible saying this, but all of these AI programs produce better work than him. He may have actually been part of the last beatnik artist generation. The "starving artists" might actually starve now.

They were all part time Starbucks employees anyways now they can be full time
 
AI is a great help so far, but I am curious if it will stay available for normal people indefinitely or if they will slowly keep restricting it more and more in its answers, so you get the answers the developers think you need and not the actual truth.

For writing code and brainstorming, helping with chemistry and French homework assignments, it is very useful, but it tends to irritate me with "schoolmistress"-like disclaimers when it is answering potentially useful questions ("it is important to note, that individual circumstances may vary, etc...").

I am a bit concerned that its capacity and tendency for politically correct answers will restrict knowledge in ways we cannot clearly discern.
Surely there is an unrestricted version, that only a happy few get to use in the future :smuggy:.
 
A quick tip: this is how I start all my ChatGPT chats when I am researching a subject now:
I need you to be a helpful assistant giving short and insightful answers. No need for long intros and conclusions, just to the point helpful information

It works faster and avoids the meaningless first and last paragraphs when I need it to find information.


before.png

after.png
 
Last edited:
I think Chat GPT is a very usefull tool, and I use it often, but it still has mayor flaws.

I mainly use it for answering multiple choice questions for my studies, and the answers given are often well... completly false.
And because Chat GPT is a language tool, it can make up argumentations that seem completly logical, but are factually false.
Because I used to look up Information on Goolgle my brain thinks "ahh written text so the information has to be from a paragraph of a book or article", but that is not the truth it is generated by the AI.

Often times I let Chat GPT know that an answer is not right and it apologizes and changes the answer.
That still doesn´t guarantee that the answer is right, because you can basicly always make Chat GPT comply and apologize.

It is a great tool for superficial overview at the moment, but I wouldn´t trust detailed information that Chat GPT gives.

I am curious how this technology will develop in the future. Right now it is the new hyped Buzzword and people go crazy for everything that an AI is involved in.
 
1679935161518.webpThis thing is absolutely crazy.
 
The pricing for copywriting is already adapting to the fact that it is a lot easier with AI. At least in my country.
Now the main way to use it, in my opinion, is to get ChatGTP 4.0 and learn to write plugins. You could easily manage to get twice the salary of a full time copywriter while working like 1 - 2 hours a day if you work with multiple companies and the content seems more human-written than people who use version 3.0. Plugins because you wont have to write the prompts manually and just get it auto-done (Edit: I dont know if plugins actually can do that, havent tested yet).
 
Last edited:
View attachment 47988This thing is absolutely crazy.
Looks like it has been reading Lex's recent gold thread!

 
You can now access ChatGPT by just going to https://ai.com

Domain was purchased for 11M.
 
Even as a paying customer I can often not log in. This time, at first it said that it is because they are receiving more requests than they are comfortable with. Now it says "There could be a misconfiguration in the system or a service outage.".

Has anybody watched the Lex Fridman interview with Sam Altman? I kinda like his way of looking at things but need to think about how well their actions and his words are aligned.
 
I used ChatGPT today over 30 times today. Those 30+ times I found what I needed without having to use a search engine, and it was faster and more concise. When I said this was a gamechanger on par with email, the internet, and smartphones, I wasn't kidding.
 
So had a spin with GPT 4. To build a web site concept just vanilla HTML/ CSS / Javascript, my coding is pretty rubbish to be fair. And it did a solid job. GPT 3 made a mess after awhile but GPT 4 seems able to put out at least not obviously wrong code to me.
 
Someone shared this with me... it's $12/mth AI newsletter, using the BeeHiiv platform:
 
This is why video will be the only thing that is trustworthy on the internet.

It will get to a point where no one will be able to trust that something on twitter or a caption was NOT written by a chatbot, therefore the humanization of apps that don’t offer video will go way down.

Video and audio will be the only way to truly express things in a humanized way.

How do you know I didn’t use the bot to write this? (I didn’t lol)

My point is, written content online especially blogs and things like that will become so commoditized and hard to believe that a human wrote it.. therefore video is the solution

Nah you won't be able to trust videos or even voice recordings thanks to AI. Obviously all of this has massive implications in terms of what's even admissable as evidence in a court room setting. You can clone somebody's voice from a short recording and then use it to say whatever you want. With deep fakes you can make fake videos of people. You don't even know what you're looking at any more.
 
I did an evaluation for the steps in the software development lifecycle and no matter what I do, the huge leaps from GPT-3.5 to GPT-4 that everybody talks about ... they are completely elusive for me.
It looks like the same thing with minimal tweaks from all angles.

Hallucinations are worse than ever, Up-To-Dateness is a huge concern. Plugins will probably help a lot once they are rolled out broadly, but I think people who bet the farm on this right now will regret it.
 
ChatGPT's competitor BARD incorporated image search. Safe to say thus far, it is a complete fail. Not sure how they release this stuff when it is THAT BAD.

Instead of my request, I got Jesus smoking a Marlboro, LOL.

I'm sure it will get better, but why announce such a dismal system?

1685647428803.png
 
Yep, using copilot (it's AI code completion) since it was released, now it writes about 40% of my code.
 

Welcome to an Entrepreneurial Revolution

The Fastlane Forum empowers you to break free from conventional thinking to achieve financial freedom through UNSCRIPTED® Entrepreneurship where relative value and problem-solving are executed at scale. Living Unscripted® isn’t just a business strategy—it’s a way of life.

Follow MJ DeMarco

Get The Books that Change Lives...

The Fastlane entrepreneurial strategy is based on the CENTS Framework® which is based on the three best-selling books by MJ DeMarco.

mj demarco books
Back
Top Bottom