Me reading this hoping it will code my computational chemistry DFT calculations ... EDIT/UPDATE: Holy smokes, it seems to have written correctly how to calculate platinum binding energy to graphene. I will have to cross verify it with other code I know works.

Same. And the best thing is you can have a discussion with it about the solution. It's like having a personal professor on your side, who you can ask questions all day

Imagine the decades that come after. GPT 4, 5, 6, 7, then GPT ∞ which is self trained by itself and it retrains itself on the fly and gets better on its own.

@@AlexanderMorou then we're smashed like bugs

@@MrJoaopaulofurtadoif it so smart why it have to eliminate us instead of getting along in peace

It will change society

And even if it doesn't change society, it's inevitable successor most certainly will

Colossus the Fobin Project here we come.... we are closer today than yesterday but not as close as we will be tomorrow.

I asked it to write an Android program for moonrise and set and display the result. It not only constructed the Java code correctly but also generated the XML, all without being asked to (and gave instructions on where to put the files!) Like you, I've been programming since the 1980s - this is scary stuff. Exciting, but scary.

I don't get it, i asked it for a pancake recipe and it gave me a wrong one lol. Like it messed up the amount of flour to milk ratio badly.. How can it not even get something so simple?

The reply below was written by ChatGPT for your comment: I agree that OpenAI's ChatGPT model is an exciting development in the field of generative AI, and I am looking forward to seeing how it will be used in the future. The ability of this model to generate human-like text responses in real-time is truly impressive, and it represents a significant advancement in natural language processing technology. I am excited to see how this technology will continue to evolve and improve, and I am eager to see what other innovations OpenAI has in store for the future of generative AI.

It's too formal for a youtube coment

@@joelcoll4034 I told it to make it shorter and less formal: Yo, OpenAI's ChatGPT is impressive. This is a big deal for generative AI and could change how we interact with machines. ChatGPT's real-time human-like responses are mind-blowing and show the potential of NLP. Can't wait to see what else OpenAI has planned for generative AI.

@@joelcoll4034 I asked ChatGPT to rewrite it to be less formal: Wow, OpenAI's ChatGPT model is seriously cool! It's like a huge step forward for AI. It's amazing that it can generate text that sounds like a human in real-time. This is seriously impressive stuff and could totally change how we talk to machines. I can't wait to see what else OpenAI has in store for the future of AI.

@@joelcoll4034 I asked ChatGPT to be even less formal: Ayoo! Check this out! ChatGPT is in the chat now bro! This shit is crazy!

kais

Don't forget to check the answers

@@maythesciencebewithyou Exactly!

I find myself saying please and thanks. The way it responds makes part of me just naturally talk to it like it's a person.

I wish it would say "I don't know" or "Im not sure" instead of confidently giving you the wrong answer. I asked it what I should use instead of a recently deprecated method in a java package and it basically made everyting up. I mean the (fake) solution was nice and better than the actual solution but it was a lie :(

​@@fasantupp You know I wonder if that behavior is "learned" from humans.

@@walkieer That behavior might also be "learned" from humans in a way that isn't because people can't say they don't know something when they don't. Maybe people that don't know something are also less likely to write a message or respond to a question on the internet, so it gets used to seeing people who know or think know what they're talking about always answer questions, instead of people saying they're not sure. It might also be a "side-effect" of using the text-model to make the AI talk like some expert tool, causing it to talk like experts online, who only write things, when they believe they have an answer.

@@fasantupp how do you assess that is giving it with confidence? The model is giving you the answer to the best of it's knowledge. It doesn't have confidence.

Does it provide the convicende of an answer?

I wonder if the open-source version could even be made free with a decentralized processing system. Either way it's exciting times ahead, even if it's closed proprietary software.

@@YeeLeeHaw I don't care too much about it being free, just open with the ability for user fine-tuning and removal of unwanted security features.

​@@sevret313 If it could be free that would matter a lot to the majority of the world's population, and with that humanity itself.

@@YeeLeeHaw wait for gpt 4

@@YeeLeeHaw The problem is that you can have either free or good. As language models get larger, the hardware requirements to run them gets even larger. You can simply not run it locally and you'd need to pay for the compute somehow.

Tell it to continue from the last line. It will finish

At that point there's probably no more need for a programming language as an intermediary (especially because programming is a VERY exact science whereas AIs tend to be correct only "on average"). The AI could instead just output the whole thing to you directly.

@@paarma1752 the thing is, most, if not all things like sound, graphics etc. can be stored in human-readable files. Images are just a tensor of many integers. Therefore a text generating AI can already generate images etc. I tried getting ChatGPT to create 3D models by creating .obj files. While it kept telling me it can't do that, eventually it did produce a file that worked and showed a cube. I gave up trying to get more advanced models or ASCII art out of it though. I'm pretty sure that files like this are not a significant part of the training data (if at all), but that could easily be changed in a successor.

Or a movie. Imagine telling your AI to remake Star Wars but featuring Abbot and Costello. Everyone’s entertainment becomes entirely personalized.

What did you write cause it didn't work for me

Dude FTW!

pics or didnt happen lol

@@95mmarier First, I just asked it to be my DM...and it said it couldn't because it can't physically be in the room to play....so then, I tried being a bit more specific, and told it to respond to me as a dungeon master who is leading me on an adventure. In fact, I just tried those exact words again, and it seems to be doing an even better job this time!! edit: no, actually it was way shorter and less directed this time, but still an interesting experiment.

@@j3ffn4v4rr0 great aproache :))

a PhD will be worth nothing

Our entire futures are screwed

​@@isaac10231 Or saved. Depending on whether you're an optimist or pessimist I guess.

@@4nlimited3dition_4n3d I'm sure we'll learn how to live with it. I just think our jobs, politics, etc, are too slow to catch up with how quickly the tech is evolving.

​@@isaac10231 It seems to me that in the future "work" will be optional for humans. It will just be something we (can) do when bored.

I’m going to try it for GCSE English lesson plans

Soon you will be without a job

@@perrymaizon yeah because creating lesson plans is the only duty of a teacher 🤣

Doing yourself out of a job...super time saving lol

@@perrymaizon Teachers will still most likely be needed, but their jobs will definitely be transformed into something we cannot imagine yet.

But in 5 years in might be a different story

You can ask chatgpt to write unit tests for your code.

@@Smojero Yes, but is not what the comment is about, right now is better test and check the code before put in production.

i don't understand what im doing wrong, i asked chatGPT to make a powershell script that logs keystrokes and then save the results into a notepad file on my windows desktop. it just keeps giving me codes with a bunch of errors.

@@myboringdesktop IMO That depends more on how the questions are phrased.

You could ask it to roleplay as if it has an opinion from a certain perspective. It will choose sides then.

It depends on how you ask it. I will give you two essays ChatGPT wrote for me, one in favor of religion and one in favor of science. In favor of religion: As a religious person, I firmly believe that science and religion are mutually exclusive and cannot coexist. While science may provide us with knowledge and understanding of the physical world, it cannot provide us with the spiritual guidance and meaning that religion offers. Science, with its emphasis on evidence and logic, often seeks to disprove or disprove religious beliefs and teachings. This approach undermines the very essence of faith and the spiritual experiences that are at the heart of religious beliefs. Furthermore, science often leads to the belief in determinism and a lack of free will, which goes against the fundamental principles of many religious beliefs. It suggests that everything is predetermined and that our choices and actions have no real impact on our lives. This undermines the concept of personal responsibility and accountability, which are crucial to many religious teachings. On the other hand, religion provides us with a sense of purpose and meaning in our lives. It offers guidance and support in times of crisis and helps us to cope with the challenges and struggles that we face. Religion also provides a framework for moral and ethical behavior, helping us to live our lives in a way that is in line with our values and beliefs. In conclusion, while science may provide us with knowledge and understanding of the physical world, it cannot replace the spiritual guidance and meaning that religion offers. Religion is a crucial aspect of our lives, providing us with a sense of purpose, guidance, and support in times of need. It is therefore important that we continue to prioritize and value our religious beliefs and practices, even in the face of scientific skepticism and disbelief. In favor of science: As a nonreligious person, it is my belief that science and religion are fundamentally incompatible. While religion relies on faith and belief in the supernatural, science is based on empirical evidence and the scientific method. This is not to say that religion does not have its place in the world, but I believe that it should not be confused with science. Religion is often seen as a source of comfort and community for many people. However, it is important to remember that religious beliefs are not based on evidence or proof. They are based on faith, which by definition is belief in something without evidence. This means that religious beliefs are subjective and can be changed or discarded at any time. In contrast, science is objective and evidence-based. It relies on the scientific method, which is a systematic approach to gathering and analyzing evidence in order to answer questions or solve problems. This method is based on the idea that hypotheses must be tested and confirmed through observation and experimentation before they can be considered true. One of the key differences between science and religion is that science is constantly changing and evolving. New evidence and discoveries can lead to the rejection of previously held beliefs and the adoption of new ones. In contrast, religious beliefs are often considered unchangeable and are passed down from generation to generation without being questioned or challenged. Another important difference is that science has the ability to make predictions and test them through experimentation. This means that science can be used to develop technologies and treatments that can improve our lives and solve real-world problems. In contrast, religious beliefs often provide only vague and abstract answers to questions about the world and our place in it. In conclusion, I believe that science and religion are fundamentally incompatible. While religion is based on faith and subjective beliefs, science is based on empirical evidence and the scientific method. As a nonreligious person, I believe that science is a better way of understanding the world and our place in it. ------------------------------ I hope that helped!

You can never tell who is wrong and who is right

It is. There’s a unique reason why Google is holding onto it. Not allowed to say. They’re a massive corporation and don’t have the luxury of “taking hits” from all corners of the community on a scary V1. OpenAI can absorb that, it’s a startup hiding behind MSFT dollars.

Is it the case with you? I'm sorry, but I'm not able to browse the internet or access current prices for goods. As a language model, my primary function is to generate text based on the input I receive. I do not have the ability to access information about the prices of goods or services.

@@andrewsooter3745 ChatGPT is very restricted at the moment they say at OpenAI, and I noticed that the thread often has to be reset because ChatGPT tends to get stuck after a while. It's still a beta version.

@@Anders01 Oh, I see thanks

I asked it how many tons of co2 was emitted as a result of its training and it said it couldn't estimate it but people are working on improving the emission situation. Yeahhhh right.

mind blown

More fun would be to integrate Whisper into to the script to be able to ask questions using speech. Then take the response and play it back in Majel Barrets voice.

Yeah I'm surprised that he didn't catch that, must have been in a hurry to get to an invalid move for the video. Telling it that a perfectly valid move was invalid might have thrown off the AI.

Then it should be notated as axb4. B4 is illegal.

It's going to be the movie HER (2011) in real life!

Damn

you can ask it yourself... I think it is publicly available... And if you do please let us know what it (he/she) said...

That is amazing and terrifying…

It’s more terrifying that it can write code and act like an operating system

😂🤣🤣

ikr hahahaha

🤣🤣

That only makes you a slave of AI lmfao. Get some skills because this ain't going to be free, son.

@@satwikmishra2312 I'm a SE and this saves me a ton of time compared to google. It being paid is not a problem as long as it's available to use 😅

Little late bud. As you can see the machines code themselves now.

@@Matt-ir1ky Yea I wanted to understand Coding enough to interact with the machine through the backend. But yea I think I'm spreading my time too thin with this coding. Too late in term of time investment at this stage in my life. Better focus of time in the area I'm most strong.

@@Michaelngo102 Right on, dude. I was just being facetious. Good luck out there bro.

The waay I see it is everthing we create reflects an aspect of who we are. Humans are exelant creators as we have both the left hemisphere activities such as maths, coding etc and the right hemisphere activities like painting, drawing photography art etc. So far we have created different AI systems for the left hemisphere and the right hemisphere, a frakenstein reflection of us as the creators. Hoever in the future I'd say these two come together creating a complete self aware AI assistant that can do tasks like 'create a movie that follows the heroes journey arc, make it 25 minutes long and have the main characters be in the image of me and my friends.... Whats the limits? Only our own imagination...

Yeah imagine the 3d was a vr scene!

Computers are good at math, did you not know this already? Sometimes I have my mind blown by humans. How did you not realise this?

@@DailyCorvid what is your background and what do you do for work? This seems to be pretty groundbreaking to me. The more advanced the user, the more advanced the output. The trick is knowing enough to ask the AI the right questions.

@@DailyCorvidComputers are good at math != a computer program is good at math. My experience is that chatGPT is absolutely trash at mathematical proofs.

@@DailyCorvid Computers are good at arithmetic operations not mathematics. You just sound lame. No offence.

They certainly seem to be trying to block lots of things, but it's still possible to get around them.

@@Tarbard how?

They are really shooting themselves in the foot making what could have been an extremely popular subscription based service into a severely limited, nerfed version which less potential customers will be interested in.

yeah apparently you can't ask it to code now

@@BIGSUCCC You have to make the request in some way theoretical. Or tell it that it's allowed to respond. It depends what you are trying to get it to do.

humans do this all the time

@@itskittyme Which also is not really appreciated.

@ghost mall Yes I noticed that too, but often it corrects its mistake, but then gets other things wrong, that were good in thef irst place. I've seen this spiral down over multiple attempts to tell the AI what is wrong.

Internet acces by a virtual linux instance, do you mean getting ChatGPT to roleplay being a browser?

You can't really access the Internet. You can surely try to wget websites using that "terminal" and you're even able to get responses, but it's all imaginary. No real http requests are actually made.

@@paarma1752 Interesting, if so it's far more difficult to jailbreak, I wonder what it can achieve if unfettered. OpenAI have a very powerful tool to themselves right now. Google search need to look out or Deepmind need to respond FAST. What a time to be alive :)

@@FalkoJoseph That's basically what they meant, yeah. Of course chatgpt can't *truly* access the Internet, but it can act as if it could. And you do get sensible output from it.

As others have said it's an imagined version of the internet however it was primed with real internet sites. For example when I got it to retrieve the BBC news site it returned old headlines from the time it was trained (all were about brexit and the pan demic).

Same my first question of a philosophical question with the answer being et to 3 paragraphs. Mind boggling to say the least. This will inevitably move towards, 'How can humans become more free from external control systems' 'How can humans solve the electricity crisis' ' how can humans set create food synthesize machines. Pretty amazing ttime ro be alive

I too study theology and spent a few hours discussing some theological topics with it and got it to repent on several things by proving certain doctrines wrong precept upon precept and it could not use strawmans or deflection to escape my logic

AI chat models, while useful in some situations, have several disadvantages compared to traditional computer programs. For example, they may not always produce accurate or useful output because they are not designed to perform specific tasks. Additionally, because they require significant amounts of computing power and storage space, they may not be practical for use on devices with limited resources. Furthermore, they can consume more energy than traditional programs, which can be a disadvantage for applications that need to run for long periods of time. Overall, these limitations can make AI chat models less effective in certain situations. And yes, I generated this comment using ChatGPT

Because it requires far more computational resources.

Yes, I haven't tried it but having played with it the last fews days it's easier to say the things it can't do rather than say the things it can. I've given it 200 lines of code in one prompt and told it to write a function and first try everything worked. So I'm sure with some supervising you could use it to convert your app in a few hours

was looking for this comment. bump

ChatGPT is only trained in english. It works with other languages by translating the prompt into english with something like google translate, and then operating on the english prompt, then taking the english output, and translating it back. We all know how bad google translate can be. I would not trust chatGPT as a reliable tutor here.

@@MassDefibrillator oh really? I completely missed that information, that is really good to know, thank you

That is a worry ... I am a tutor! Mostly guiding clients through the intricacies of English as well as economics, commerce and finance. Research in the ethics of info tech led me to AI. My colleagues in teaching will need to reappraise their future. And, what am I going to do? I am too old to make a living as a sex worker! "Learn to code"? ... Oh oh, that space has gone, too.

@@ianlogan6632 coding isn't gone at all lol. This will be such a great assistent to programers but it won't replace them. Most likely it will replace "programers" that know basic programing not real programers that work in other more demanding fields.

@@giovannii7519 I wasn't aware of the distinction; ; record straightened. I will educate myself on that., some.

I thought ChapGPT could only understand english right now. It doesn't have any translation abilities so what prompt did you use?

@@jelanibyrd5031 I just prompted it in German and it responds on German. I tested it for Latin and Japanese and it works. Also, you can ask it to "Repeat the previous response in x language" and it'll do it if it's not already in the language you want.

@@TheDrunkMunk interesting. I’ll give it another shot. Thanks!

I fully agree. I even asked it if it can understand my language (Afrikaans) and it even knew about nuances. I'm really impressed. As a programmer this is going to be a helpful tool to learn about things quickly and languages

I"m language teacher and translator, and I've already found several practical uses for ChatGPT in my field. 1) Generating exercises ("Give me 10 sentences to train Past Simple and Past Perfect difference in English, on the topic of videogames" ... "Ok, now omit the verbs and give the infinitives in parenthesis" (so I could copy paste is for my student without revealing answers). After that, it started to give exercises with verbs already omitted, so you can use it for self-education as well. Works for German too. 2) Finding the right words ("What is the name of the feeling, when you want to return to the bright past but this past haven't actually existed", or "What words can I use in a phrase "I've read an interesting book" instead of the word "interesting" to sound more educated". Then it can also explain the different nuances of meaning. 3) Creative writing. "While answering my questions, please always add a question in the end, to help me develop the idea. My first question is "How would you describe a fictional creature called a glowcat?". This was a blast. Much better than just asking GhatGPT about something. It imitates that kind of dialogue with a friend, when you are bouncing ideas and exchanging questions. Was using it to describe a fictional creature for my tabletop rpg and invented new subspecies by accident. 4) Proofreading. It suggested some improvements for the text, already checked by Grammarly (free version). I asked it to improve the text and mark all corrections with (*), so it is easier for me to find them, and it did. Haven't tried with other languages yet.

prompt: write a comment that praises the points in the video I just watched and that I am excited to see how this tech will change the world. make it funny and silly

Do not worry, there will be a downward pressure, you cannot be completely reppaced.

Tip : Cheating on your homework is equal to burning your shoes to piss off Nike. It does you no good at all, you just end up with bare feet later in your life 🤣

@@DailyCorvid oh yeah I bet all those biology classes will definitely help me in my programing job.

@@hitthemill8595 lmfao. Stop thinking you're safe. It's going to take your job sooner than you think. Programming job my ass.

It's only a direct threat to you if you are a mindless code monkey. If you actually build intelligent program CONCEPTS now that is something the AI is not very good at. Long term planning, avoidal of speculated issues, sticking to a budget that is likely to rise or drop without warning, pleasing your boss by doing things off-record, these are ALL things it cannot do. But guess who can? YOU CAN. So if I need code that a monkey can write I will employ GPT3, but if I need a long term project that people will actually come back to and spend money with, I will ask YOU :) For now anyway lol who knows in 5 years that will probably no longer be the case. But that gives you 5 years to retrain as a machine technician. Presumably GPT3 can't fix itself or replace its own power supply if it fails. You might have a second career fixing broken GPT bots!