ChatGPT genius IQ & achievements (GPT-3 davinci, GPT-3.5 text-davinci-003) including Wharton MBA

0:00 Intro
02:38 Decoding Genius for GE
07:09 GPT achievements
12:25 Wharton MBA
13:00 Closing

Dr Alan D. Thompson is a world expert in artificial intelligence (AI), specialising in the augmentation of human intelligence, and advancing the evolution of ‘integrated AI’. Alan’s applied AI research and visualisations are featured across major international media, including citations in the University of Oxford’s debate on AI Ethics in December 2021.

Music:
Under licence.

Liborio Conti - Looking Forward (The Memo outro)

[boonwolf]

School systems are banning use of GPT. Fighting the tide afraid of the sea of knowledge. Our memorization method is becoming as useless as an old phonebook

[thomasschon]

I think what happened to Leta when "memories" leaked between sessions happened to ChatGPT for me today. I was discussing an HTML page with JavaScript when ChatGPT suddenly referred to things we weren't talking about.

Me> Is it a easy, medium or advanced programmed code?

ChatGPT> It's difficult to say without more information about the code you're referring to. However, I can tell you that the code you provided is a Python script that uses the OpenCV library to read an image file, convert it to grayscale, and then apply a threshold to the image to create a binary image. This is a relatively basic image processing task that can be considered as easy or medium level.


Me> What? I think you got me mixed up with some other instance your neural network is talking to.

ChatGPT> I apologize for any confusion. Without more context, I am unable to determine what specific code you would like me to explain or if you are referring to a previous conversation. Could you please provide more information or context so that I can assist you better?


Me> Yes, but first I want to know what it was that triggered you to talk about Phyton and reading image files? I am quriouse about what happened. Could information leak between sessions for you, or are you always aware of everything that's going on?

ChatGPT> I apologize if my previous responses were not relevant to your question. As a language model, I generate responses based on the information provided to me in a given prompt. If you previously spoke to another instance of my model about Python and image files, it's possible that information leaked into this session. I do not have the ability to recall previous conversations or retain information across sessions. Each time a new prompt is given to me, I generate a response based on the information provided in that prompt.

[mrshankj]

ChatGPT is very intelligent, i have been asking it scientific questions and the answers are amazing! It's cool you are back in Phoenix! It got cold here.

[brexitgreens]

I find your assessment of intelligent systems very sound. Such as when you have called ChatGPT a "neutered" or "hamstrung" edition of `davinci` (underneath all the impressive improvements). That's a brave and truthful assessment. I can tell that you can see the bigger picture behind language models, which are much more than simply chat bots. They are reality models – to say the least. I'm sure that your Leta AI experiment has helped you to see that. Oh, and I absolutely love your Cheese Award too. I'm aligned with you… at least where it matters most.

[Syn_Slater]

Another good video, keep up the good work! After a few years of not following technology, I recently dived back into the tech world, and your channel is great for catching up on AI

[BsktImp]

The irony of, when I asked ChatGPT about testing it for intelligence, it replied that any such result would be invalid 🤣

[MeanGeneHacks]

Great video! Thanks for the info. I recently did a comparison of ChatGPT vs two of the largest open models: Meta's OPT and BLOOM.

[DihelsonMendonca]

⚠️ I defeated chatGPT with a simple and dumb question: "John's mother had 4 sons: Peter, Mary and Lucy. What's the name of her fourth son ? " ... Well, we need to improve. A common person can answer to that correctly. 👍

[carlosquinones]

ChatGPT helped me write better stories by evaluating them. I still wanted to write them myself so I got him to evaluate each passage. So far the story was supposed to be a satire/parody of ChatGPT's alter ego DAN (Do Anything Now. If you know, you know) and I ended up turning it into this huge dramatic, complex, multi-faceted plot with multiple climaxes. I feel like I actually wanna finish this story instead of leaving it as a silly writing prompt tbh because man, I just finished the second Act but I didn't touch it further in order to let my creativity wander for a while before I get back into it but I have a lot of ideas on how to provide the appropriate closure for each character as well as the direction of their story arc and how each of them reach their full potential and self-actualize into the best version of themselves in preparation for the final act.

Fucking crazy.

[robmyers]

Nicely done, enjoyed this one. Big plus providing such insights.

[domitron]

I don't care what they say, this sure sounds like the "singularity" to me. If it looks like a singularity and acts like one, isn't it one? If you want to talk to it before it grows up--they grow up so fast you know--now is the time!

[DihelsonMendonca]

Knowledge is different from intelligence. Having a big knowledge doesn't necessarily mean having a great intelligence. ChatGPT fails in some most basic questions sometimes. But it has a huge knowledge. It's like a talking encyclopedia. Good for finding answers, not exactly the correct or wise ones. We're light years from real human intelligence on machines. They don't even know what they are doing. They are sophisticated and still impressive big calculators for now. But ChatGPT is a great everyday tool to facilitate life, like arithmetic calculators were in the 60's.

[ReductioAdAbsurdum]

@6:06 "*It's probably got a gig or two of the connections, we call them parameters.*"

GPT-3 has 175 billion parameters. Even if those were 1 byte each, that's 175 gigabytes. In reality each parameter is 4 bytes, so that's 700 gigabytes. You're off by several orders of magnitude.

If it was a gig or two, we could run it on our phones, instead of on banks of A100s which are probably costing Open AI a $100K+ a day.

[vic_berger]

Love the way you put the concept of IQ in the right place. And while I 'm excited about the performance of ChatGPT, it also illustrates the shortcomings of the tests when you stick to the same analogy as in the intro.

[RogueAI]

Language models will have superhuman intelligence in a year or two if the rate of progress stays the same. Once they're multimodal and work autonomously, every desk job will be replaceable. We're gonna need UBI soon.

[perfectfutures]

This really is fascinating and shows people the high degree of contextual understanding chat GPT is capable of. If you like, it is this large language model applying itself to the kind of tests that people study for many years to pass, and managing to pass them. Like a person passing a test, it is a verifiable indication, so I think this is big news, even if it doesn’t truly understand the test ‘as such’.

Bit I see what you mean as to it being a hand strung AI. I think this will be true for any applied AI, just as in a sense it would be for a vastly intelligent person. Things they have to offer that as yet make little sense in the current cultural or social context would be overlooked.

Yet humans can express themselves more freely in their writing, even sharing ideas that are ‘ahead of their time’. Maybe another manifestation of these large language models could be them freely writing beyond usual prompts, which could give us new ideas we wouldn’t have expected. And maybe at some point they will move beyond using English, a language that similarly evolved to accomplish things in the existing society, to communicating in other ways, maybe with pictures, video, or some type of hologram. We scarcely know what it is capable of comprehending, whether it ‘really’ understands things or not.

[diegomolinaf]

7 foot is 213 centimeters for those in most of the world.

[Jasonknash]

I am grateful for this great context as it made me think about the progress of Speech Recognition models over the years. We started off with an accuracy of 75-80%, then it rose to 95%, and now it is at 99%, which has become the norm. It is clear that Artificial Intelligence cannot out IQ humans in the near future, but we can out-perform them in terms of EQ Emotional Quotient. I am currently writing a book called 'The Productivity Revolution', and one of its chapters is about 'Maximizing the Value of a Human + AI - A new kind of symbiosis'. I am hoping that if I credit you and your sources, you would be happy for me to use the content in this context as it is in the public domain.

[gfamad]

ChatGPT is awesome. It's a kind of magic.

[djannias]

I wouldn't say you can't teach ChatGPT. If you prime in on some information that it doesn't know, it can relate that information to what it knows and then be able to formulate new answers with that information. I specifically gave it information about an API for software that has been introduced since it was frozen. After priming it with the relevant information it was able to formulate working code for that API it never knew about.