TheTexan
Member
- Joined
- Sep 1, 2011
- Messages
- 27,424
The Left can't meme...
ChatGPT can't meme... in exactly the same way...
Hmmm.................
Honestly - that level of logical consistency is about par for the course for an average agument on RPF
We are in the AI Singularity
- Thread starter ClaytonB
- Start date
Honestly - that level of logical consistency is about par for the course for an average agument on RPF
ClaytonB
Member
- Joined
- Oct 30, 2011
- Messages
- 10,227
I mean, you think the Internet is not saturated with AI chatbot agents? How much more obvious does it have to get??
Have you actually tried chatting with ChatGPT? It doesn't quite pass the Turing test. Yet.
TheTexan
Member
- Joined
- Sep 1, 2011
- Messages
- 27,424
It is true that there are many AI chatbots available on the internet, and their popularity has been growing in recent years due to advancements in natural language processing and machine learning technologies.
Regarding your question about chatting with ChatGPT, I can assure you that ChatGPT is designed to engage in natural and intelligent conversations with users. However, it is also true that current AI technology has its limitations, and there is still work to be done to improve the ability of AI chatbots to pass the Turing test consistently. Nonetheless, it is constantly being updated and improved, and it strives to provide the best possible experience for users.
Dr.3D
Member
- Joined
- Dec 6, 2007
- Messages
- 30,313
Well, at least the relationship had at least 2 straight sides. That's saying a lot in this day and age.I, for one, am no longer scared of our ChatGPT Overlord...
The Left can't meme...
ChatGPT can't meme... in exactly the same way...
ClaytonB
Member
- Joined
- Oct 30, 2011
- Messages
- 10,227
ClaytonB
Member
- Joined
- Oct 30, 2011
- Messages
- 10,227
Well, at least the relationship had at least 2 straight sides. That's saying a lot in this day and age.
Mach
Member
- Joined
- Jan 30, 2008
- Messages
- 4,137
We need to create an AI government, no more corruption and has a set of top priorities, no matter what, like the Constitution etc.
This is mentioned in the first video.
GPTs are GPTs: An early look at the labor market impact potential of large language models
Abstract
We investigate the potential implications of Generative Pre-trained Transformer (GPT) models and related technologies on the U.S. labor market. Using a new rubric, we assess occupations based on their correspondence with GPT capabilities, incorporating both human expertise and classifications from GPT-4. Our findings indicate that approximately 80% of the U.S. workforce could have at least 10% of their work tasks affected by the introduction of GPTs, while around 19% of workers may see at least 50% of their tasks impacted. The influence spans all wage levels, with higher-income jobs potentially facing greater exposure. Notably, the impact is not limited to industries with higher recent productivity growth. We conclude that Generative Pre-trained Transformers exhibit characteristics of general-purpose technologies (GPTs), suggesting that as these models could have notable economic, social, and policy implications.
This is mentioned in the first video.
GPTs are GPTs: An early look at the labor market impact potential of large language models
Abstract
We investigate the potential implications of Generative Pre-trained Transformer (GPT) models and related technologies on the U.S. labor market. Using a new rubric, we assess occupations based on their correspondence with GPT capabilities, incorporating both human expertise and classifications from GPT-4. Our findings indicate that approximately 80% of the U.S. workforce could have at least 10% of their work tasks affected by the introduction of GPTs, while around 19% of workers may see at least 50% of their tasks impacted. The influence spans all wage levels, with higher-income jobs potentially facing greater exposure. Notably, the impact is not limited to industries with higher recent productivity growth. We conclude that Generative Pre-trained Transformers exhibit characteristics of general-purpose technologies (GPTs), suggesting that as these models could have notable economic, social, and policy implications.
Murray N Rothbard
Member
- Joined
- Feb 27, 2012
- Messages
- 317
I was talking to GPT4 today about some legal questions and caught it just straight making shit up.
I asked where I could find more info about the case it referenced.
GPT4 said:
I asked where I could find more info about the case it referenced.
GPT4 said:
ClaytonB
Member
- Joined
- Oct 30, 2011
- Messages
- 10,227
To bypass a lot of the "As an AI model..." nonsense (but not 100% of it), you can access the raw GPT model through the Playground.
- Go to openai.com:
- Select Developers->API Reference
- Click on "Playground"
- Type in the text box. Click the Submit button below to get GPT's response.
Note that this is not technically "ChatGPT", it's the base model underneath ChatGPT. It is best thought of as a text-completion tool, so it's a little less "natural" than ChatGPT but you get all the "intelligence" of the underlying base model.
ClaytonB
Member
- Joined
- Oct 30, 2011
- Messages
- 10,227
‘The Godfather of A.I.’ Leaves Google and Warns of Danger Ahead -- For half a century, Geoffrey Hinton nurtured the technology at the heart of chatbots like ChatGPT. Now he worries it will cause serious harm.
Swordsmyth
Member
- Joined
- Apr 14, 2016
- Messages
- 74,737
IBM To Cut 8,000 Positions, Replacing Them With Artificial Intelligence
https://www.thefinancialtrends.com/...-replacing-them-with-artificial-intelligence/
https://www.thefinancialtrends.com/...-replacing-them-with-artificial-intelligence/
ClaytonB
Member
- Joined
- Oct 30, 2011
- Messages
- 10,227
The "recursive detonation of intelligence" theory is false. Self-improving AI, on its own, cannot lead to truly super-human intelligence. But I think the ordinary person (without specialized understanding of computer science) will not be able to tell the difference, up to a limit. That is because LLMs and whatever comes next are based on training data taken from all of human effort ("super-human" knowledge) and they are running on machinery that is able to process much more information per second than the human brain can, by sheer dint of scale -- the human brain uses a couple dozen watts of power, these AI algorithms are running on machines powered by kilowatts or even megawatts of power...
Similar threads
