Have you ever heard of ChatGPT, the open-source machine learning platform that allows users to build natural language models?
It stands for “Chat Generating Pre-trained Transformer” and it’s an AI-powered chatbot that can answer questions with near human-level intelligence. But what is Google’s answer to this technology? The answer lies in Open AI, supervised learning, and reinforcement learning. Let’s take a closer look at how these technologies work.
Tech Buzzwords of 2022, By Google Search Interest
Open AI is an artificial intelligence research laboratory that was founded by some of the biggest names in tech, including Elon Musk and Sam Altman. This non-profit organization seeks to develop general artificial intelligence that is safe and beneficial to society. One of their key initiatives is the development of open source technologies like GPT-3, which is a natural language processing model used in ChatGPT.
2023 AWS Certified Machine Learning Specialty (MLS-C01) Practice Exams
ChatGPT: What Is It and How Does Google Answer It?
Artificial Intelligence (AI) has been around for decades. From its humble beginnings in the 1950s, AI has come a long way and is now an integral part of many aspects of our lives. One of the most important areas where AI plays a role is in natural language processing (NLP). NLP enables computers to understand and respond to human language, paving the way for more advanced conversations between humans and machines. One of the most recent developments in this field is ChatGPT, a conversational AI developed by OpenAI that utilizes supervised learning and reinforcement learning to enable computers to chat with humans. So what exactly is ChatGPT and how does it work? Let’s find out!
Get 20% off Google Google Workspace (Google Meet) Standard Plan with the following codes: 96DRHDRA9J7GTN6 Get 20% off Google Workspace (Google Meet) Business Plan (AMERICAS): M9HNXHX3WC9H7YE (Email us for more codes)
ChatGPT is an open-source AI-based chatbot developed by OpenAI.
This chatbot leverages GPT-3, one of the most powerful natural language processing models ever created, which stands for Generative Pre-trained Transformer 3 (GPT-3). This model uses supervised learning and reinforcement learning techniques to enable computers to understand human language and response accordingly. Using supervised learning, GPT-3 utilizes large datasets of text to learn how to recognize patterns within language that can be used to generate meaningful responses. Reinforcement learning then allows GPT-3 to use feedback from conversations with humans in order to optimize its responses over time.
AI Unraveled: Demystifying Frequently Asked Questions on Artificial Intelligence Intro
ChatGPT uses supervised learning techniques to train its models.
Supervised learning involves providing a model with labeled data (i.e., data with known outcomes) so that it can learn from it. This labeled data could be anything from conversations between two people to user comments on a website or forum post. The model then learns associations between certain words or phrases and the desired outcome (or label). Once trained, this model can then be applied to new data in order to predict outcomes based on what it has learned so far.
In addition to supervised learning techniques, ChatGPT also supports reinforcement learning algorithms which allow the model to learn from its experiences in an environment without explicit labels or outcomes being provided by humans. Reinforcement learning algorithms are great for tasks like natural language generation where the output needs to be generated by the model itself rather than simply predicting a fixed outcome based on existing labels.
Supervised Learning
Supervised learning involves feeding data into machine learning algorithms so they can learn from it. For example, if you want a computer program to recognize cats in pictures, you would provide the algorithm with thousands of pictures of cats so it can learn what a cat looks like. This same concept applies to natural language processing; supervised learning algorithms are fed data sets so they can learn how to generate text using contextual understanding and grammar rules.
Reinforcement Learning
Reinforcement learning uses rewards and punishments as incentives for the machine learning algorithm to explore different possibilities. In ChatGPT’s case, its algorithm is rewarded for generating more accurate responses based on previous interactions with humans. By using reinforcement learning techniques, ChatGPT’s algorithm can become smarter over time as it learns from its mistakes and adjusts accordingly as needed.
ChatGPT is an improved GPT-3 trained an existing reinforcement learning with humans in the loop. Their 40 labelers provide demonstrations of the desired model behavior. ChatGPT has 100x fewer parameters (1.3B vs 175B GPT-3).
➡️ First they collect a dataset of human-written demonstrations on prompts submitted to our API, and use this to train our supervised learning baselines.
➡️ Next they collect a dataset of human-labeled comparisons between two model outputs on a larger set of API prompts. They then train a reward model (RM) on this dataset to predict which output our labelers would prefer.
➡️ Finally, they use this RM as a reward function and fine-tune our GPT-3 policy to maximize this reward using the Proximal Policy Optimization
In simpler terms, ChatGPT is a variant of the GPT-3 language model that is specifically designed for chat applications. It is trained to generate human-like responses to natural language inputs in a conversational context. It is able to maintain coherence and consistency in a conversation, and can even generate responses that are appropriate for a given context. ChatGPT is a powerful tool for creating chatbots and other conversational AI applications.
How Does Google Answer ChatGPT?
What is Google answer to ChatGPT?
Google’s answer to ChatGTP comes in the form of their own conversational AI platform called Bard. Bard was developed using a combination of supervised learning, unsupervised learning, and reinforcement learning algorithms that allow it to understand human conversation better than any other AI chatbot currently available on the market. In addition, Meena utilizes more than 2 billion parameters—making it more than three times larger than GPT-3—which allows it greater flexibility when responding to conversations with humans.
“We’re starting to open access to Bard, an early experiment that lets you collaborate with generative AI. We’re beginning with the U.S. and the U.K., and will expand to more countries and languages over time.”
When individuals need an information or have a problem/concern, they turn to Google for immediate solution. We sometimes wish, Google could understand what exactly we need and provide us instantly rather than giving us hundreds of thousands of results. Why can’t it work like the Iron Man’s Jarvis?
However, it is not that far now. Have you ever seen a Chat Bot which responds like a human being, suggest or help like a friend, teach like a mentor, fix your code like a senior and what not? It is going to blow your mind.
Welcome to the new Era of technology!! The ChatGPT!
ChatGPT by OpenAI, uses artificial intelligence to speak back and forth with human users on a wide range of subjects. Deploying a machine-learning algorithm, the chatbot scans text across the internet and develops a statistical model that allows it to string words together in response to a given prompt.
As per OpenAI, ChatGPT interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer follow-up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.
What all ChatGPT can do?
It can help with general knowledge information.
Remember what user said in previous conversation.
Allow users to provide follow-up corrections.
Trained to decline inappropriate requests.
It can write a program in any language you prefer on real-time. for example — write classification code sample in sklearn python library.
It can fix your piece of code and also explain what went wrong and how it can be fixed.
It can even generate song or rap lyrics
Even much more….
Some best usages of ChatGPT:
Make a diet and workout plan
Generate the next week’s meals with a grocery list
Create a bedtime story for kids
Prep for an interview
Solve mathematical problem
Fix software program or write a program
Plan your trip and tell expected expenses
What are its limitations of ChatGPT?
May occasionally generate incorrect information
May occasionally produce harmful instructions or biased content
Limited knowledge of world and events after 2021
ChatGPT is in its baby steps therefore it may answer erroneously at times however it’s manner of response will blow your mind. Some users have also extolled the chatbot as a potential alternative search engine, since it generates detailed information instantly on a range of topics. I believe, we can’t compare Google with ChatGPT as ChatGPT can provide more in-depth and nuanced answers to complex questions than a search engine like Google, which is designed to provide a list of relevant web pages in response to a user’s query.
Conclusion: ChatGPT is an increasingly popular open source AI chatbot developed by OpenAI using GTP-3 natural language processing technology that utilizes supervised learning and reinforcement learning algorithms for recognition and optimization purposes respectively. On the other hand, Google’s answer comes in the form of their own conversational AI platform called Bard which employs both supervised learning as well as unsupervised learning algorithms along with reinforcement learning capabilities which makes it even smarter than ChatGPT when responding to conversations with humans. Ultimately, these two technologies help bridge the gap between machines and humans by allowing us all talk like real friends!
ChatGPT is in its baby steps therefore it may answer erroneously at times however it’s manner of response will blow your mind. Some users have also extolled the chatbot as a potential alternative search engine, since it generates detailed information instantly on a range of topics. I believe, we can’t compare Google with ChatGPT as ChatGPT can provide more in-depth and nuanced answers to complex questions than a search engine like Google, which is designed to provide a list of relevant web pages in response to a user’s query.
With each passing day, ChatGPT will only get smarter thanks to the use of cutting edge technologies like OpenAI, supervised learning, and reinforcement learning!
ChatGPT Conversation Examples
Question: What is Google Answer to ChatGPT?
Answer: Google does not have an answer to ChatGPT. ChatGPT is an open-source chatbot created by OpenAI, which is an independent research organization that is not affiliated with Google. OpenAI is known for its research on artificial intelligence and machine learning, and has developed a number of innovative technologies in these areas. Google, on the other hand, is a multinational technology company that offers a wide range of products and services, including search, advertising, and cloud computing. While Google does have its own research efforts in artificial intelligence and machine learning, it does not have a chatbot that is similar to ChatGPT.
Question: is Google working on a similar technology as ChatPGT?
Answer:
It is possible that Google is working on technology similar to ChatGPT, as the company has a significant research effort focused on artificial intelligence and machine learning. However, I do not have any specific information about what projects Google is currently working on, and it is also important to note that Google is a large and diverse company with many different research and development efforts underway. It is possible that some teams within Google may be working on chatbot technology, but I do not have any information on this.
That being said, chatbots are a common application of artificial intelligence and machine learning, and it is likely that many companies and organizations, including Google, are exploring ways to use these technologies to improve their products and services. However, without more information, it is difficult to say for sure what projects Google may be working on in this area.
Question: What about Google Meena?
Google Meena is a chatbot developed by Google that was designed to be able to carry on conversations with humans in a natural and conversational manner. Meena was trained on a dataset of more than 2.4 billion parameters, making it one of the largest language models ever created. The goal of Meena was to improve the state of the art in chatbot technology and to create a chatbot that could understand and respond to a wide range of questions and topics in a coherent and meaningful way.
Meena was announced in January 2020 and received attention for its ability to hold relatively long and coherent conversations with humans. However, it is important to note that Meena is a research project and is not a product or service offered by Google. It is not clear if or when Google plans to release a commercial product or service based on the technology developed for Meena.
What is Google answer to ChatGPT?
It gets even better when you ask it about the future:
Suggest possible titles for Onion articles written in 4000 AD, explain, why they are funny
“Futuristic city plagued by traffic jams, despite flying cars” – This title presents the idea of flying cars as a solution to traffic congestion, but also suggests that even with this advanced technology, the city is still plagued by traffic jams, implying that the problem is not easily solved.
“Artificial intelligence achieves self-awareness, immediately regrets it” – This title presents the idea of artificial intelligence achieving self-awareness as a major milestone, but also suggests that the AI regrets its newfound consciousness, implying that it is unhappy or uncomfortable with its situation.
“Alien invasion successfully repulsed, humans left to deal with paperwork” – This title presents the successful repulsion of an alien invasion as a major accomplishment, but also suggests that the humans are now left to deal with the tedious and burdensome task of filling out paperwork, implying that the victory is not as satisfying as it initially seemed.
“Time travel becomes possible, tourists flock to witness the signing of the Constitution” – This title presents the idea of time travel as a major technological breakthrough, but also suggests that the most popular destination for time-travelers is the mundane and uneventful signing of the Constitution, implying that the future is not as exciting as people had hoped.
“Virtual reality becomes indistinguishable from reality, no one notices” – This title presents the idea of virtual reality becoming indistinguishable from real life as a major accomplishment, but also suggests that no one cares or notices the difference, implying that the advancement is not as impressive or significant as it seems.
What is Google answer to ChatGPT?
New slogan for McDonald’s by ChatGPT
ChatGPT Example: Make a new, brutally honest slogan for McDonald’s. It should sound funny too.
If you choose to do that, you will have a lot of badly broken code mixed in with working code
Like an annoying coworker, it delivers highly confident incorrect explanations about why its broken code is perfect. They sound very convincing. “Wanna buy a timeshare?” says GPT
Our industry has managers who cannot tell working code from defective code. This does not bode well for a team replaced by ChatGPT in its current form.
Should it? No.
Can it? No.
Will it? Sadly, programmers will have no say in this matter, once again. It might.
Isn’t Stackoverflow advertising ChatGPT when it bans it and then making numerous posts about why it banned it? By Alan Mellor
Yes, and it is very helpful advertising as well.
This last week or so has seen starry eyed projections about what ChatGPT can do, along with hugely impressive examples of its output.
It is hugely impressive.
Thankfully, more output examples have emerged which helpfully show what it cannot do. One of those things is writing computer code, which it can do only partially successfully. Many examples now exist that are just plain wrong and contain defects. But ChatGPT – like the annoying kid at Uni – cheerfully spits out these examples, with its over-confident hubris in explaining the code.
This is a dangerous thing. The positive examples will reinforce the idea that we can leave code writing to this robot now. The people most vulnerable to this delusion are those who cannot assess for themselves whether the GPT code is right or wrong.
These are almost by definition the people hoping for answers on stack overflow.
As stack overflow aims to be a high quality resource, it really does not want many of its top answers to be incorrect code. As – clearly – people have been running scripts that throw a stack overflow question into GPT and upload its output, we can now write incorrect code at staggering speeds.
To err is human, as the old saying goes. To truly foul up requires a Python script and and a web API to both GPT and Stack overflow.
Clearly, there is value in GPT. But at least for now, it needs to b e kept on a very short leash, watched over by those who know what they are doing.
It is definitely not yet ‘consumer grade replace-a-professional’ material.
Write a screenplay about the status of ChatGPT.
INT. CHATGPT SERVER ROOM – DAY
Chelsea and Chester stand in front of a large computer server.
CHELSEA: We need to figure out what’s causing the server overload.
CHESTER: I think it’s the sudden influx of users trying out ChatGPT.
Chelsea and Chester quickly get to work, typing on their laptops.
CHELSEA: Okay, we’re all set. Let’s see if this fixes the problem.
CHESTER: I’m hitting refresh on the website. The screen shows the ChatGPT website loading without any errors.
CHELSEA: Looks like we fixed it! Great job, Chester.
CHESTER: Thanks, Chelsea. It’s all part of being a top-notch engineer.
Chelsea and Chester exchange a high five, proud of their successful fix.
More about ChatGPT with its wonder, worry and weird
ChatGPT reached 1 million users in less than a week, Open AI’s latest large language model (LLM) has taken the AI industry by storm.
ChatGPT is expected to be:
– replacing Google search, even kill Google. – replacing customer service agents. – replacing conversation designers.
ChatGPT is a wonder because:
– It can have actual conversations, understand pronouns, remaining consistent, remembering, managing context – It seems like next generation of personal assistants that finds you a proper diet, create a meal plan and subsequent shopping list. – It can create some SEO Strategy including backlinks, target keyword, content plan and article titles in the level of an SEO professional. – Having fun such as writing a rap in the style of Eminem
There are some worries about ChatGPT because:
– ChatGPT can actually debug code, but it’s not quite reliable enough yet. – Fundamental limitations in being assistant for enterprise use cases. – No complete in complex actions such as updating multiple APIs, or be fully auditable.
– The general idea is that, LLMs like this can produce nonsense. Once you discover that it can produce nonsense, you stop believing it to be reliable. – What if it prevents us from knowing that it is nonsense with good conversations and continue the conversation? – In this case, the edges and limitations of the system would be hidden and trust would eventually grow. – The impact of mass adoption of such technology remains to be seen.
Moving forward with ChatGPT – There’s no doubt that LLMs will have a big impact on our world. – While the future looks exciting and promising, let’s not forget that it’s very early days with these things. They’re not ready yet. – There are some fundamental societal and ethical considerations.
How powerful is OpenAI’s new GPT-3 deep learning model? By
“Powerful” is a pretty subjective word, but I’m pretty sure we have a right to use it to describe GPT-3. What a sensation it caused in June 2020, that’s just unbelievable! And not for nothing.
I think we can’t judge how powerful the language model is, without talking about its use cases, so let’s see how and where GPT-3 can be applied and how you can benefit from it.
Generating content
GPT-3 positions itself as a highly versatile and talented tool that can potentially replace writers, bloggers, philosophers, you name it! It’s also possible to use it as your personal Alexa who’ll answer any questions you have. What’s more, because GPT-3 knows how to analyze the data and make predictions, it can generate the horoscopes for you, or predict who’ll be a winner in the game.
You may already be surprised by all the GPT-3 capabilities, but hold on for more: it can create a unique melody or song for you, create presentations, CVs, generate jokes for your standup.
Translation
GPT-3 can translate English into other languages. While traditional dictionaries provide a translation, without taking into account the context, you can be sure that GPT-3 won’t make silly mistakes that may result in misunderstanding.
Designing and developing apps
Using GPT-3 you can generate prototypes and layouts – all you have to do is provide a specific description of what you need, and it’ll generate the JSX code for you.
The language model can also easily deal with coding. You can turn English to CSS, to JavaScript, to SQL, and to regex. It’s important to note, however, that GPT-3 can’t be used on its own to create the entire website or a complex app; it’s meant to assist a developer or the whole engineering team with the routine tasks, so that a dev could focus on the infrastructure setup, architecture development, etc.
In September 2020, Microsoft acquired OpenAI technology license, but it doesn’t mean you can give up your dreams – you can join a waitlist and try GPT-3 out in beta.
All in all, I believe GPT-3 capabilities are truly amazing and limitless, and since it helps get rid of routine tasks and automate regular processes, we, humans, can focus on the most important things that make us human, and that can’t be delegated to AI. That’s the power that GPT-3 can give us.
What does ChatGPT give incorrect and unreliable results to simple arithmetic problems (e.g. it gave me three different incorrect answers to 13345*6748)? We’ve had software that can accurately do arithmetic for decades, so why can’t an advanced AI? By Richard Morris
What is remarkable is how well ChatGPT actually does at arithmetic.
In this video at about 11 min, Rob Mills discusses the performance of various versions of the GPT system, on some simple arithmetic tasks, like adding two and three-digit numbers.
Smaller models with 6 billion parameters fail at 2 digit sums, but the best model (from two years ago), has cracked 2 digit addition and subtraction and is pretty good at 3 digit addition.
Why this is remarkable is this is not a job its been trained to do. Large Language Models are basically predictive text systems set up to give the next word in an incomplete sentence. There are a million different 3-digit addition sums and most have not been included in the training set.
So somehow the system has figured out how to do addition, but it needs a sufficiently large model to do this.
Andrew Ng on ChatGPT
Playing with ChatGPT, the latest language model from OpenAI, I found it to be an impressive advance from its predecessor GPT-3. Occasionally it says it can’t answer a question. This is a great step! But, like other LLMs, it can be hilariously wrong. Work lies ahead to build systems that can express different degrees of confidence.
For example, a model like Meta’s Atlas or DeepMind’s RETRO that synthesizes multiple articles into one answer might infer a degree of confidence based on the reputations of the sources it draws from and the agreement among them, and then change its communication style accordingly. Pure LLMs and other architectures may need other solutions.
If we can get generative algorithms to express doubt when they’re not sure they’re right, it will go a long way toward building trust and ameliorating the risk of generating misinformation.
Keep learning!
Andrew
Large language models like Galactica and ChatGPT can spout nonsense in a confident, authoritative tone. This overconfidence – which reflects the data they’re trained on – makes them more likely to mislead.
In contrast, real experts know when to sound confident, and when to let others know they’re at the boundaries of their knowledge. Experts know, and can describe, the boundaries of what they know.
Building large language models that can accurately decide when to be confident and when not to will reduce their risk of misinformation and build trust.
Go deeper in The Batch: https://www.deeplearning.ai/the-batch/issue-174/
As I point out in the other answer, Wix has been around over a decade and a half. Squarespace has been around almost two decades. Both offer drag-and-drop web development.
Most people are awful at imagining what they want, much less describing it in English! Even if ChatGPT could produce flawless code (a question which has a similar short answer), the average person couldn’t describe the site they wanted!
The expression a picture is worth a thousand words has never been more relevant. Starting with pages of templates to choose from is so much better than trying to describe a site from scratch, a thousand times better seems like a low estimate.
And I will point out that, despite the existence of drag-and-drop tools that literally any idiot could use, tools that are a thousand times or more easier to use correctly than English, there are still thousands of employed WordPress developers who predominantly create boilerplate sites that literally would be better created in a drag and drop service.
And then there are the more complex sites that drag-and-drop couldn’t create. Guess what? ChatGPT isn’t likely to come close to being able to create the correct code for one.
In a discussion buried in the comments on Quora, I saw someone claim they’d gotten ChatGPT to load a CSV file (a simple text version of a spreadsheet) and to sort the first column. He asked for the answer in Java.
I asked ChatGPT for the same thing in TypeScript.
His response would only have worked on the very most basic CSV files. My response was garbage. Garbage with clear text comments telling me what the code should have been doing, no less.
ChatGPT is really good at what it does, don’t get me wrong. But what it does is fundamentally and profoundly the wrong strategy for software development of any type. Anyone who thinks that “with a little more work” it will be able to take over the jobs of programmers either doesn’t understand what ChatGPT is doing or doesn’t understand what programming is.
Fundamentally, ChatGPT is a magic trick. It understands nothing. At best it’s an idiot-savant that only knows how to pattern match and blend text it’s found online to make it seem like the text should go together. That’s it.
Text, I might add, that isn’t necessarily free of copyright protection. Anything non-trivial that you generate with ChatGPT is currently in a legal grey area. Lawsuits to decide that issue are currently pending, though I suspect we’ll need legislation to really clarify things.
And even then, at best, all you get from ChatGPT is some text! What average Joe will have any clue about what to do with that text?! Web developers also need to know how to set up a development environment and deploy the code to a site. And set up a domain to point to it. And so on.
And regardless, people who hire web developers want someone else to do the work of developing a web site. Even with a drag-and-drop builder, it can take hours to tweak and configure a site, and so they hire someone because they have better things to do!
People hire gardeners to maintain their garden and cut their grass, right? Is that because they don’t know how to do it? Or because they’d rather spend their time doing something else?
Every way you look at it, the best answer to this question is a long, hearty laugh. No AI will replace programmers until AI has effectively human level intelligence. And at that point they may want equal pay as well, so they might just be joining us rather than replacing anyone.
How does OpenAI approach the development of artificial intelligence?
OpenAI is a leading research institute and technology company focused on artificial intelligence development. To develop AI, the organization employs a variety of methods, including machine learning, deep learning, and reinforcement learning.
The use of large-scale, unsupervised learning is one of the key principles underlying OpenAI’s approach to AI development. This means that the company trains its AI models on massive datasets, allowing the models to learn from the data and make predictions and decisions without having to be explicitly programmed to do so. OpenAI’s goal with unsupervised learning is to create AI that can adapt and improve over time, and that can learn to solve complex problems in a more flexible and human-like manner.
Besides that, OpenAI prioritizes safety and transparency in its AI development. The organization is committed to developing AI in an ethical and responsible manner, as well as to ensuring that its AI systems are transparent and understandable and verifiable by humans. This strategy is intended to alleviate concerns about the potential risks and consequences of AI, as well.
How valid is OpenAI chief scientist’s claim that advanced artificial intelligence may already be conscious? By Steve Baker
It’s hard to tell.
The reason is that we don’t have a good definition of consciousness…nor even a particularly good test for it.
Take a look at the Wikipedia article about “Consciousness”. To quote the introduction:
Consciousness, at its simplest, is sentience or awareness of internal and external existence.
Despite millennia of analyses, definitions, explanations and debates by philosophers and scientists, consciousness remains puzzling and controversial, being “at once the most familiar and [also the] most mysterious aspect of our lives”.
Perhaps the only widely agreed notion about the topic is the intuition that consciousness exists.
Opinions differ about what exactly needs to be studied and explained as consciousness. Sometimes, it is synonymous with the mind, and at other times, an aspect of mind. In the past, it was one’s “inner life”, the world of introspection, of private thought, imagination and volition.
Today, it often includes any kind of cognition, experience, feeling or perception. It may be awareness, awareness of awareness, or self-awareness either continuously changing or not. There might be different levels or orders of consciousness, or different kinds of consciousness, or just one kind with different features.
Other questions include whether only humans are conscious, all animals, or even the whole universe. The disparate range of research, notions and speculations raises doubts about whether the right questions are being asked.
So, given that – what are we to make of OpenAI’s claim?
Just this sentence: “Today, it often includes any kind of cognition, experience, feeling or perception.” could be taken to imply that anything that has cognition or perception is conscious…and that would certainly include a HUGE range of software.
If we can’t decide whether animals are conscious – after half a million years of interactions with them – what chance do we stand with an AI?
Wikipedia also says:
“Experimental research on consciousness presents special difficulties, due to the lack of a universally accepted operational definition.”
Same deal – we don’t have a definition of consciousness – so how the hell can we measure it – and if we can’t do that – is it even meaningful to ASK whether an AI is conscious?
if ( askedAboutConsciousness )
printf ( “Yes! I am fully conscious!\n” ) ;
This is not convincing!
“In medicine, consciousness is assessed as a combination of verbal behavior, arousal, brain activity and purposeful movement. The last three of these can be used as indicators of consciousness when verbal behavior is absent.”
But, again, we have “chat-bots” that exhibit “verbal behavior”, we have computers that exhibit arousal and neural network software that definitely shows “brain activity” and of course things like my crappy robot vacuum cleaner that can exhibit “purposeful movement” – but these can be fairly simple things that most of us would NOT describe as “conscious”.
CONCLUSION:
I honestly can’t come up with a proper conclusion here. We have a fuzzy definition of a word and an inadequately explained claim to have an instance of something that could be included within that word.
My suggestion – read the whole Wikipedia article – follow up (and read) some of the reference material – decide for yourself.
But, seeing as how people have already found ways to “trick” ChatGPT into doing things that it claims to not be capable of, it would be a matter of time before someone with malicious intent tricked ChatGPT into helping them with illegal activities
What is the future of web development after ChatGPT? Will programmers lose their jobs? By Victor T. Toth
Having looked at ChatGPT and its uncanny ability to solve simple coding problems more or less correctly, and also to analyze and make sense of not-so-simple code fragments and spot bugs…
I would say that yes, at least insofar as entry-level programming is concerned, those jobs are seriously in danger of becoming at least partially automated.
What do I do as a project leader of a development project? I assign tasks. I talk to the junior developer and explain, for instance, that I’d like to see a Web page that collects some information from the user and then submits it to a server, with server-side code processing that information and dropping it in a database. Does the junior developer understand my explanation? Is he able to write functionally correct code? Will he recognize common pitfalls? Maybe, maybe not. But it takes time and effort to train him, and there’ll be a lot of uneven performance.
Today, I can ask ChatGPT to do the same and it will instantaneously respond with code that is nearly functional. The code has shortcomings (e.g., prone to SQL injection in one of the examples I tried) but to its credit, ChatGPT warns in its response that its code is not secure. I suppose it would not be terribly hard to train it some more to avoid such common mistakes. Of course the code may not be correct. ChatGPT may have misunderstood my instructions or introduced subtle errors. But how is that different from what a junior human programmer does?
At the same time, ChatGPT is much faster and costs a lot less to run (presently free of course but I presume a commercialized version would cost some money.) Also, it never takes a break, never has a lousy day struggling with a bad hangover from too much partying the previous night, so it is available 24/7, and it will deliver code of consistent quality. Supervision will still be required, in the form of code review, robust testing and all… but that was always the case, also with human programmers.
Of course, being a stateless large language model, ChatGPT can’t do other tasks such as testing and debugging its own code. The code it produces either works or it doesn’t. In its current form, the AI does not learn from its mistakes. But who says it cannot in the future?
Here is a list of three specific examples I threw at ChatGPT that helped shape my opinion:
I asked ChatGPT to create a PHP page that collects some information from the user and deposits the result in a MySQL table. Its implementation was textbook example level boring and was quite unsecure (unsanitized user input was directly inserted into SQL query strings) but it correctly understood my request, produced correct code in return, and explained its code including its shortcomings coherently;
I asked ChatGPT to analyze a piece of code I wrote many years ago, about 30 lines, enumerating running processes on a Linux host in a nonstandard way, to help uncover nefarious processes that attempt to hide themselves from being listed by the ps utility. ChatGPT correctly described the functionality of my obscure code, and even offered the opinion (which I humbly accepted) that it was basically a homebrew project (which it is) not necessarily suitable for a production environment;
I asked ChatGPT to analyze another piece of code that uses an obscure graphics algorithm to draw simple geometric shapes like lines and circles without using floating point math or even multiplication. (Such algorithms were essential decades ago on simple hardware, e.g., back in the world of 8-bit computers.) The example code, which I wrote, generated a circle and printed it on the console in the form of ASCII graphics, multiple lines with X-es in the right place representing the circle. ChatGPT correctly recognized the algorithm and correctly described the functionality of the program.
I was especially impressed by its ability to make sense of the programmer’s intent.
Overall (to use the catch phrase that ChatGPT preferably uses as it begins its concluding paragraph in many of its answers) I think AI like ChatGPT represents a serious challenge to entry-level programming jobs. Higher-level jobs are not yet in danger. Conceptually understanding a complex system, mapping out a solution, planning and cosing out a project, managing its development, ensuring its security with a full understanding of security concerns, responsibilities, avoidance and mitigation strategies… I don’t think AI is quite there yet. But routine programming tasks, like using a Web template and turning it into something simple and interactive with back-end code that stores and retrieves data from a database? Looks like it’s already happening.
How much was invested to create the GPT-3?
According to the estimate of Lambda Labs, training the 175-billion-parameter neural network requires 3.114E23 FLOPS (floating-point operation), which would theoretically take 355 years on a V100 GPU server with 28 TFLOPS capacity and would cost $4.6 million at $1.5 per hour.
Training the final deep learning model is just one of several steps in the development of GPT-3. Before that, the AI researchers had to gradually increase layers and parameters, and fiddle with the many hyperparameters of the language model until they reached the right configuration. That trial-and-error gets more and more expensive as the neural network grows.
We can’t know the exact cost of the research without more information from OpenAI, but one expert estimated it to be somewhere between 1.5 and five times the cost of training the final model.
This would put the cost of research and development between $11.5 million and $27.6 million, plus the overhead of parallel GPUs.
In the GPT-3 whitepaper, OpenAI introduced eight different versions of the language model
GPT-3 is not any AI, but a statistic language model which mindlessly quickly creates human-like written text using machine learning technologies, having zero understanding of the context.
1. Explaining code: Take some code you want to understand and ask ChatGPT to explain it.
2. Improve existing code: Ask ChatGPT to improve existing code by describing what you want to accomplish. It will give you instructions about how to do it, including the modified code.
3. Rewriting code using the correct style: This is great when refactoring code written by non-native Python developers who used a different naming convention. ChatGPT not only gives you the updated code; it also explains the reason for the changes.
4. Rewriting code using idiomatic constructs: Very helpful when reviewing and refactoring code written by non-native Python developers.
5. Simplifying code: Ask ChatGPT to simplify complex code. The result will be a much more compact version of the original code.
6. Writing test cases: Ask it to help you test a function, and it will write test cases for you.
7. Exploring alternatives: ChatGPT told me its Quick Sort implementation wasn’t the most efficient, so I asked for an alternative implementation. This is great when you want to explore different ways to accomplish the same thing.
8. Writing documentation: Ask ChatGPT to write the documentation for a piece of code, and it usually does a great job. It even includes usage examples as part of the documentation!
9. Tracking down bugs: If you are having trouble finding a bug in your code, ask ChatGPT for help.
Something to keep in mind:
I have 2+ decades of programming experience. I like to think I know what I’m doing. I don’t trust people’s code (especially mine,) and I surely don’t trust ChatGPT’s output.
This is not about letting ChatGPT do my work. This is about using it to 10x my output.
ChatGPT is flawed. I find it makes mistakes when dealing with code, but that’s why I’m here: to supervise it. Together we form a more perfect Union. (Sorry, couldn’t help it)
Developers who shit on this are missing the point. The story is not about ChatGPT taking programmers’ jobs. It’s not about a missing import here or a subtle mistake there.
The story is how, overnight, AI gives programmers a 100x boost.
ChatGPT is “simply” a fined-tuned GPT-3 model with a surprisingly small amount of data! Moreover, InstructGPT (ChatGPT’s sibling model) seems to be using 1.3B parameters where GPT-3 uses 175B parameters! It is first fine-tuned with supervised learning and then further fine-tuned with reinforcement learning. They hired 40 human labelers to generate the training data. Let’s dig into it!
– First, they started by a pre-trained GPT-3 model trained on a broad distribution of Internet data (https://arxiv.org/pdf/2005.14165.pdf). Then sampled typical human prompts used for GPT collected from the OpenAI website and asked labelers and customers to write down the correct output. They fine-tuned the model with 12,725 labeled data.
– Then, they sampled human prompts and generated multiple outputs from the model. A labeler is then asked to rank those outputs. The resulting data is used to train a Reward model (https://arxiv.org/pdf/2009.01325.pdf) with 33,207 prompts and ~10 times more training samples using different combination of the ranked outputs.
– We then sample more human prompts and they are used to fine-tuned the supervised fine-tuned model with Proximal Policy Optimization algorithm (PPO) (https://arxiv.org/pdf/1707.06347.pdf). The prompt is fed to the PPO model, the Reward model generates a reward value, and the PPO model is iteratively fine-tuned using the rewards and the prompts using 31,144 prompts data.
This process is fully described in here: https://arxiv.org/pdf/2203.02155.pdf. The paper actually details a model called InstructGPT which is described by OpenAI as a “sibling model”, so the numbers shown above are likely to be somewhat different.
9. Remake a video: Just pick a video you liked and visit https://lnkd.in/e_GD2reT to get its transcript. Once done, bring that back to Chat GPT and tell it to summarize the transcript. Read the summary and make a video on that yourself.
What solutions have been proposed to improve the accuracy of AI generated questions and answers?
There are a number of approaches that have been proposed to improve the accuracy of artificial intelligence (AI) generated questions and answers. Here are a few examples:
Data quality: One important factor in the accuracy of AI generated questions and answers is the quality of the data used to train the AI system. Ensuring that the data is diverse, relevant, and accurately labeled can help to improve the accuracy of the AI system.
Training methods: Different training methods can also impact the accuracy of AI generated questions and answers. For example, using more advanced techniques such as transfer learning or fine-tuning can help to improve the performance of the AI system.
Human oversight: Another approach that has been proposed to improve the accuracy of AI generated questions and answers is to include some level of human oversight or review. For example, the AI system could be designed to flag potentially problematic or inaccurate questions and answers for further review by a human expert.
Explainable AI: Another approach that has been proposed is to develop AI systems that are more transparent and explainable, so that it is easier to understand how the AI system arrived at a particular answer or decision. This can help to improve the trustworthiness and accountability of the AI system.
Overall, there is ongoing research and development in this area, and it is likely that a combination of these and other approaches will be needed to improve the accuracy of AI generated questions and answers.
ChatGPT for CyberSecurity
The concept behind ChatGPT
ChatGPT is a chatbot designed to understand and generate human-like language through the use of natural language processing (NLP) and machine learning techniques. It is based on the GPT (Generative Pre-training Transformer) language model developed by OpenAI, which has been trained on a large dataset of human language in order to better understand how humans communicate.
One of the key concepts behind ChatGPT is the idea of language generation. This refers to the ability of the chatbot to produce coherent and coherently structured responses to user input. To do this, ChatGPT uses a number of different techniques, including natural language generation algorithms, machine learning models, and artificial neural networks. These techniques allow ChatGPT to understand the context and meaning of user input, and generate appropriate responses based on that understanding.
Another important concept behind ChatGPT is the idea of natural language processing (NLP). This refers to the ability of the chatbot to understand and interpret human language, and respond to user input in a way that is natural and easy for humans to understand. NLP is a complex field that involves a number of different techniques and algorithms, including syntactic analysis, semantic analysis, and discourse analysis. By using these techniques, ChatGPT is able to understand the meaning of user input and generate appropriate responses based on that understanding.
Finally, ChatGPT is based on the concept of machine learning, which refers to the ability of computers to learn and adapt to new data and situations. Through the use of machine learning algorithms and models, ChatGPT is able to continually improve its understanding of human language and communication, and generate more human-like responses over time.
GPT-4 is going to launch soon.
And it will make ChatGPT look like a toy…
→ GPT-3 has 175 billion parameters → GPT-4 has 100 trillion parameters
I think we’re gonna see something absolutely mindblowing this time!
And the best part? 👇
Average developers (like myself), who are not AI or machine learning experts, will get to use this powerful technology through a simple API.
Think about this for a second…
It’s the most powerful, cutting-edge technology *in the world*, available through a Low-Code solution!
If you’re not already planning on starting an AI-based SaaS or thinking about how to build AI into your current solution…
Google on Monday unveiled a new chatbot tool dubbed “Bard” in an apparent bid to compete with the viral success of ChatGPT.
Sundar Pichai, CEO of Google and parent company Alphabet, said in a blog post that Bard will be opened up to “trusted testers” starting Monday February 06th, 2023, with plans to make it available to the public “in the coming weeks.”
Like ChatGPT, which was released publicly in late November by AI research company OpenAI, Bard is built on a large language model. These models are trained on vast troves of data online in order to generate compelling responses to user prompts.
“Bard seeks to combine the breadth of the world’s knowledge with the power, intelligence and creativity of our large language models,” Pichai wrote. “It draws on information from the web to provide fresh, high-quality responses.”
The announcement comes as Google’s core product – online search – is widely thought to be facing its most significant risk in years. In the two months since it launched to the public, ChatGPT has been used to generate essays, stories and song lyrics, and to answer some questions one might previously have searched for on Google.
The immense attention on ChatGPT has reportedly prompted Google’s management to declare a “code red” situation for its search business. In a tweet last year, Paul Buchheit, one of the creators of Gmail, forewarned that Google “may be only a year or two away from total disruption” due to the rise of AI.
Microsoft, which has confirmed plans to invest billions OpenAI, has already said it would incorporate the tool into some of its products – and it is rumored to be planning to integrate it into its search engine, Bing. Microsoft on Tuesday is set to hold a news event at its Washington headquarters, the topic of which has yet to be announced. Microsoft publicly announced the event shortly after Google’s AI news dropped on Monday.
The underlying technology that supports Bard has been around for some time, though not widely available to the public. Google unveiled its Language Model for Dialogue Applications (or LaMDA) some two years ago, and said Monday that this technology will power Bard. LaMDA made headlines late last year when a former Google engineer claimed the chatbot was “sentient.” His claims were widely criticized in the AI community.
In the post Monday, Google offered the example of a user asking Bard to explain new discoveries made by NASA’s James Webb Space Telescope in a way that a 9-year-old might find interesting. Bard responds with conversational bullet-points. The first one reads: “In 2023, The JWST spotted a number of galaxies nicknamed ‘green peas.’ They were given this name because they are small, round, and green, like peas.”
Bard can be used to plan a friend’s baby shower, compare two Oscar-nominated movies or get lunch ideas based on what’s in your fridge, according to the post from Google.
Pichai also said Monday that AI-powered tools will soon begin rolling out on Google’s flagship Search tool.
“Soon, you’ll see AI-powered features in Search that distill complex information and multiple perspectives into easy-to-digest formats, so you can quickly understand the big picture and learn more from the web,” Pichai wrote, “whether that’s seeking out additional perspectives, like blogs from people who play both piano and guitar, or going deeper on a related topic, like steps to get started as a beginner.”
If Google does move more in the direction of incorporating an AI chatbot tool into search, it could come with some risks. Because these tools are trained on data online, experts have noted they have the potential to perpetuate biases and spread misinformation.
“It’s critical,” Pichai wrote in his post, “that we bring experiences rooted in these models to the world in a bold and responsible way.”
The recent case of stable diffusion 3 is one example of this. These type of steps will delay innovation and accessibility to the public. submitted by /u/Southern_Opposite747 [link] [comments]
My career goal is to become a data scientist or machine learning engineer. Understanding that the entry bar for these titles is insanely high right now, I'm looking for the next role that bring me closer to the target role. I currently work as a software engineer (front end) for 1 year, admitted in MS in CS specializing in ML, have a bachelor of DS. What job title should I look for to boost my profile? Data engineer? Data Analyst? SWE in data platform? And how should I prepare for interviews in these role? Leetcode 75? SQL? The skills range is so diverse I need to concentrate my effort to the right baskets. Can't put all eggs in one basket so what is the game plan to achieve my goal? submitted by /u/Puzzleheaded_Ad_224 [link] [comments]
Hello, everyone. I am an architectural student now researching case studies of the use of AI in real-world projects. With all these crazes of "Stable diffusion AI rendering" "Midjourney image generation" and the plugins and programs such as ARCHITECTURES, AUTODESK Forma, laiout, finch AI and such, I have yet to see any detailed case study sharing of the use of such things in real world project applications, and as far as my limited research goes, most case studies are limited to "the potential of" said programs, and nothing much actual use, especially in how it's used in the overall workflow of projects. So I'm here to ask everyone a few questions and hopefully provide me with some insights to the use of these AI stuff, and how it has helped or even hindered your work from the traditional workflow of the completion of projects. I hope to understand the usage of AI beyond the field of architecture specifically, and also in other design fields such as film making, graphic design, animation and many more. These are the few things that I hope to gain insights to: Are there any projects that you have done that relied on AI programs? Have the project proposals been approved by the client, or even won participated competitions? What programs did you use at which stage of the projects to complete a specific task? For said specific task that you have used AI to increase the efficiency of your work, how much time do you think you have saved from the help of AI? If they have not been approved by the clients or just internally rejected, and if not because they are just bad design in general, why are they rejected? I do understand that some of this information might be kept in-house for companies for its own use to keep its competitive edge, and thus not meant to be shared openly, so to those kind enough to share, please only share what you can not put yourself in a tough spot over some random student on the internet. I appreciate all the help, and thanks in advance. submitted by /u/Eminence6261 [link] [comments]
I like chat gpt, but it always restricts what I can use it for. I want an AI that won’t tell me what I’m asking it for is offensive or inappropriate. Does anyone have recommendations? submitted by /u/69RuckFeddit69 [link] [comments]
looking for help to generate carl wheezer singing voiceover to gimme the light by sean paul https://www.youtube.com/watch?v=8MmW_GOFS8I submitted by /u/Muffdiver0323 [link] [comments]
https://preview.redd.it/h13z13eua5vc1.png?width=640&format=png&auto=webp&s=397d5127453b2f4a1d6f6df28fb5fc8a2f2f0cff I think the VQ loss and perceptual loss look normal, but I feel it's hard to understand why discriminator goes towards the completely different direction...anyone has seen similar things before? More details: I'm training the vqgan on imagenet from the paper Taming Transformers for High-Resolution Image Synthesis submitted by /u/darthjaja6 [link] [comments]
I'm probably barking up the wrong tree, but has any progress been made theoretically in how to make an AI model imitate human reasoning, so that for example a large language model could somehow be able to distinguish between real facts and something that sounds like a fact but is actually false? submitted by /u/ferriematthew [link] [comments]
Artificial Intelligence has the potential to help us make better decisions and to even better understand ourselves. Much of the focus on generating valuable AI content is on providing the right prompt. The right prompt doesn't just mean getting AI to correctly understand your question, it also means providing the right information so AI can tailor it's answer to you personally. Everyone is different, and one of the ways we are different is our unique personalities. If you ask AI how to approach a problem, such as suggesting a suitable career or improving certain skills, the strength of its answer will strongly depend on the personality of the user. Certain recommendations will benefit certain personalities over others. To address this issue, we introduced a new feature on our site called TraitGuru. To utilize this feature, first you must complete a Big Five personality test (which is an accurate measure of personality). Our website has one here if you are interested, but other Big Five tests can work fine too. You enter your Big Five personality scores and ask TraitGuru a question. TraitGuru will give you an answer specific to your personality. If you are interested in trying out TraitGuru, visit our website here: https://traitmash.com/traitguru/ Whether you use TraitGuru or interact with AI in a different way, there are benefits to providing AI details about your personality when you are asking it certain questions. Feel free to give this a try the next time you are using ChatGPT or any other AI chatbot. submitted by /u/TraitMash [link] [comments]
Ok I will explain the whole story later but right now I NEED to know if there's a way to actually delete a song fully so even people who have the link can't access it?!?!?!? submitted by /u/Junior_Pirate3418 [link] [comments]
Real marketing use case of AI. I had to create a complex filter in Google Analytics to understand website traffic for a narrow slice of the website (hard to isolate using standard GA filters) Sourcegraph Cody to the rescue. I just described the pattern in plain English. Cody generated a nice regexp that I entered into GA as a filter, and it just works! submitted by /u/creativefisher [link] [comments]
This explanation from the American Bar Association seems to fit, right? “In the United States at the federal level, an EIS is a report mandated by the National Environmental Policy Act of 1969 (NEPA), to assess the potential impact of actions “significantly affecting the quality of the human environment.” This requirement under NEPA does not prohibit harm to the environment, but rather requires advanced identification and disclosure of harm.” https://www.americanbar.org/groups/public_education/publications/teaching-legal-docs/teaching-legal-docs--what-is-an-environmental-impact-statement-/ submitted by /u/sour_gnome [link] [comments]
I just saw a video clip from a live stream of twitch streamer Adin Ross get a call from his friend whose name is Kai Cenat, or at least he thought it was him, but it was actually someone using Kai's voice that seemed to be created using A.I. I feel bad because this gives A.I. a bad reputation, how can we combat this and make it less of a problem? Because this isn't the first time I heard something like this happen. submitted by /u/15idlehand15 [link] [comments]
https://arstechnica.com/tech-policy/2024/04/feds-appoint-ai-doomer-to-run-us-ai-safety-institute/ Article intro: Appointed as head of AI safety is Paul Christiano, a former OpenAI researcher who pioneered a foundational AI safety technique called reinforcement learning from human feedback (RLHF), but is also known for predicting that "there's a 50 percent chance AI development could end in 'doom.'" While Christiano's research background is impressive, some fear that by appointing a so-called "AI doomer," NIST may be risking encouraging non-scientific thinking that many critics view as sheer speculation. submitted by /u/bregav [link] [comments]
Hey All, I think many of us can agree that defining the hardware we want to use right next to the piece of code we are running is objectively a much better developer experience. I have always loved the idea of lowering the barrier when it comes to running code in the cloud. As more cloud abstractions hit the market, I was honestly really surprised by the lack of adoption. There aren't any unicorns (I don't think any actually) in this space yet, just series A businesses. After speaking with a handful of Data Scientists, Machine Learning Engineers, and DevOps Engineers, it started to dawn on me that risk aversion is causing most of the friction. Using a fully managed service can definitely have some upsides, and in many cases, I prefer using them, but convincing your boss to pipe petabytes of data to another company's cloud and incur 3-5x compute costs probably isn't going to sit well. There are also some open source alternatives but they are intentionally difficult to configure so you pay for their premium offerings that reduce config setup. Would love to hear everyone's thoughts, especially those who work at lean startups and global 5,000 companies. submitted by /u/Ok_Post_149 [link] [comments]
I read recently that OpenAI and others have effectively trained current models on most of the information available on the web and we are hitting a ceiling of available data. My understanding is that AI was as good as the amount of training data available and if there is no significant amount more training data availble then it would make sense that there is another potential AI winter coming. It seems to me that the way forward is a combination of the following: Synthetic data: There is discussion of using "Synthetic Data" which (simply put) is one AI model creating data and another judges it but this is in early stages and I'm not convinced that it is going to be effective. It sounds like Anthropic is trying to create and use this type of data Real world data: This seems to be ultimately the most valuable data but no way to scale at the ways needed for AI, especially language models that rely on written, spoken media. This could be information measured and created by robots in the real world. I imagine this would be data like that created by boston dynamic robots or (tin foil hat) audio recorded from cellphones and other places New data on internet: Information like this post and anything else posted into the future. It does seem that internet data from here on out is at risk of being AI generated which might "poison" the data New strategies to better use current data: If we are able to create better models off of current data that seems like the best way forward. I'm sure that there are a billion things I'm missing here What am I missing? How do you think AI companies are going to improve their models from here on out? What are the chances that we are hitting a ceiling? submitted by /u/r4tk1ng2 [link] [comments]
it doesn't seem just a coincidence that competitive open source models like mistral large by mistral and llama 2 by meta were released relatively soon after proprietary models like chatgpt-4 and gemini ultra 1.0 were released by openai and google. if these proprietary models were released without public access to the weights, training data and other supporting information, what explains the success that these open source models achieve soon thereafter with nearing them in important benchmarks? submitted by /u/Georgeo57 [link] [comments]
I took an extended swig out of this water bottle I'm holding, I feel a tiny crumb from my lunch dislodge from between my back two molars into the water flushing about the inside of my mouth. I can feel the food particle bounce off the inside of my right cheek but then I'm not sure where it is (though I have an idea of what general area it might be moving towards). Confirmed when i feel it bounce off the inside part of the area under my lower lip. Now I grasp this thing, with help of my tongue, in between my two front teeth, like picking up a marble with my two fingers. This, all in the span of fractions of a second. These are skills not taught and rarely communicated about. How many other such subliminal skills are holding my experience together? Even in analogue terms, when we talk about the outer possibilities of AI in the near/medium term, can we expect that we could achieve such subtlety with current techniques? submitted by /u/xtof_of_crg [link] [comments]
I am curious to know the job opportunities in Banking & Insurance for someone pursuing PhD in Statistics given the current market conditions. submitted by /u/SpiritualCellist4303 [link] [comments]
Title. Is there a way to determine the degree of sphericity or hyperbolicity of the embeddings a feature extractor learns for a set of examples it has been trained on / will be tested on? I am new to geometry in deep learning. It would be amazing if anyone could also point me to a paper or a book to get started on this. Thanks in advance. submitted by /u/Mad_Scientist2027 [link] [comments]
Hello friends and strangers, I'm a successful DJ and producer in the Hardcore Techno scene for nearly 27 years now. A year ago I was taken in by the "new" AI hype and decided to give it a go myself. I ended up writing & producing some tracks together with ChatGPT. The feedback was good on these, so the "DJ AI" persona was created, and the tracks were released using that persona (note: in Hardcore Techno it's a common thing that music is released using a persona, so this is not some type of 'fake producer' thing!) The stories, fiction, and posts by "DJ AI" were written with the help of ChatGPT, too. While her visuals were created using Leonardo. The reactions were quite good again, so now there has been a remix competition, where human producers remixed "her" tracks, and it has been released as well! But that's only half of my message here: all of this has been documented, including ChatGPT chat logs, and other details. Especially the "creating music using ChatGPT" part. This was done in order to enable other producers, musicians, or mere hobbyists, to do the very same thing, and produce lots of tracks in collaboration with ChatGPT, too! I'm fascinated with AI and I want to show the possibilities of AI even for "niche genres" like HC Techno, and hopefully others take off on this and find even better ways to work with AI regarding music and subcultural niches? We will see! So, here is the link to the remix ep: https://doomcorerecords.bandcamp.com/album/an-artificial-intelligence-remixed And to the "ChatGPT music" documentation: https://laibyrinth.blogspot.com/p/how-to-create-music-with-chatgpt.html submitted by /u/Low-Entropy [link] [comments]
Today I Learned (TIL) You learn something new every day; what did you learn today? Submit interesting and specific facts about something that you just found out here.
submitted by /u/DennisHoffmanOqng [link] [comments]
Reddit Science This community is a place to share and discuss new scientific research. Read about the latest advances in astronomy, biology, medicine, physics, social science, and more. Find and submit new publications and popular science coverage of current research.
Get 20% off Google Workspace (Google Meet) Business Plan (AMERICAS): M9HNXHX3WC9H7YE (Email us for more codes)
In contrast, real experts know when to sound confident, and when to let others know they’re at the boundaries of their knowledge. Experts know, and can describe, the boundaries of what they know.
Building large language models that can accurately decide when to be confident and when not to will reduce their risk of misinformation and build trust.
Go deeper in The Batch: https://www.deeplearning.ai/the-batch/issue-174/