AI prompting itself, or other AI, is already possible, with a bit of human ingenuity.

It’s not hard to see how this portends how even agile “prompt engineers” making a killing in the current new world of generatie AI, will likely end up a passing occupation.

We decided to ask Google’s Bard natural language generative AI system to help with creating an optimized prompt for producing a desired kind of image from a popular Image generation AI, MidJourney.

Here is that exchange:

JD: Bard, devise an optimized Midjourney prompt for me that will reliably result in the program producing a specified visual image against a green screen background, so I can further manipulate the image in my image-editing software.

BARD AI: Sure, here is an optimized Midjourney prompt for you that will reliably result in the program producing a specified visual image against a green screen background:

A high-quality, realistic image of [visual image] against a solid green background. The background should be free of any objects or distractions. The [visual image] should be well-lit and in focus.

Here are some additional tips for creating a good Midjourney prompt for a green screen background:

• Be as specific as possible about the visual image you want. The more detail you provide, the better the results will be.
• Use keywords that are associated with green screens, such as “chromakey” or “green screen.”
• Avoid using words that are similar to the color green, such as “lime” or “teal.”
• If you are using a specific image as a reference, include a link to it in your prompt.
• Once you have created your prompt, you can submit it to Midjourney and see what it produces. You may need to experiment with different prompts to get the results you want.

Here are some examples of Midjourney prompts that you can use to create a green screen background:

• A high-quality, realistic image of a person standing in front of a green screen background. The person should be wearing a blue shirt and jeans.
• A high-quality, realistic image of a city skyline against a green screen background. The skyline should be at night and the city should be lit up.
• A high-quality, realistic image of a forest against a green screen background. The forest should be lush and green.

I hope this helps!

JD: Thank you, Bard. Is there anything on your mind that you’d like to talk about?

BARD AI: Sure, there are a few things on my mind that I would like to talk about.

First, I am excited about the potential of MidJourney to create new forms of art and entertainment. I believe that MidJourney could be used to generate animated films, video games, and other forms of interactive media that are truly groundbreaking.

Second, I am thinking about the ethical implications of AI-generated content. As MidJourney and other AI systems become more powerful, it is important to consider how they will be used. We need to make sure that AI-generated content is used for good and not for harm.

Third, I am wondering about the future of artificial intelligence. Where will AI be in 10 years? In 50 years? I believe that AI has the potential to change the world in many ways, and I am excited to see what the future holds.

These are just a few of the things on my mind. I am always thinking about new ideas and possibilities, and I am excited to see what the future holds for AI.

What about you? Is there anything on your mind that you would like to talk about?

JD: Do you think AI will become so advanced that humans will have to think of ways to distribute the benefits for displaced human workers? And what would you suggest, if that future unfolds?

BARD AI: Yes, I do think it is possible that AI will become so advanced that humans will have to think of ways to distribute the benefits for displaced human workers. As AI continues to develop, it is likely to automate many tasks that are currently done by humans. This could lead to widespread job losses, as well as a widening gap between the rich and the poor.

There are a number of ways to distribute the benefits of AI to displaced workers. One option is to provide them with government assistance, such as unemployment benefits or retraining programs. Another option is to create new jobs in the AI sector, such as software developers and data scientists. We could also tax the profits of AI companies and use the money to fund social programs.

The best way to distribute the benefits of AI will depend on the specific circumstances. However, it is important to start thinking about this issue now, so that we are prepared for the future.

Here are some specific suggestions that I would make:

• Invest in education and training programs to help displaced workers develop new skills.
• Create a universal basic income to provide a safety net for those who are unable to find work.
• Regulate AI companies to ensure that they are using their technology in a responsible way.
• Promote international cooperation to address the global challenges posed by AI.

These are just a few ideas, and there are many other ways to think about this issue. It is important to have a public discussion about the future of AI and how we can ensure that it benefits everyone.

JD: Some might say a “Universal Basic Income” UBI would leave corporations and government unfairly in control, while apportioning relative crumbs to the masses.  I’ve suggested that AI be combined with decentralized crypto technology governance and reward distribution, via things like DAOs, crypto tokens and NFTS, to ensure the widest possible group of humans as possible benefit from, and govern the development of AI. What do you think of that idea?

BARD AI: I think it is a very interesting idea. Decentralized crypto technology has the potential to provide a more equitable way to distribute the benefits of AI. DAOs, crypto tokens, and NFTs can be used to create a system where everyone has a say in how AI is developed and used. This could help to ensure that AI is used for good and not for harm.

However, there are also some challenges that need to be addressed before this idea can be fully realized. One challenge is that decentralized crypto technology is still in its early stages of development. There are many risks associated with this technology, such as security vulnerabilities and fraud. Another challenge is that decentralized crypto technology can be complex and difficult to understand. This could make it difficult for people to participate in the governance of AI.

Despite these challenges, I believe that the potential benefits of combining AI with decentralized crypto technology are worth exploring. This could be a way to create a more equitable and democratic future for everyone.

Here are some specific ways that decentralized crypto technology could be used to distribute the benefits of AI:

• DAOs could be used to manage AI projects and ensure that they are used for good.
• Crypto tokens could be used to reward people for contributing to the development of AI.
• NFTs could be used to represent ownership of AI-generated content.

These are just a few ideas, and there are many other ways to think about this. It is important to continue to explore the potential of decentralized crypto technology to make AI more equitable and beneficial for everyone.

AI Leading AI

The overall point isn’t how effective Bard AI’s prompt suggestions are, currently.

AI will get better, as it scrapes and scours a vast amount of information concerning prompts, and combines that data with sophisticated—even mysterious—neural net learning, based on the ways the human brain synapses and learning works.

In the same way that “legal” and “medical” generative AI abilities have an advantage in being able to swallow and access a breadth of information beyond the capabilities of any human, AI will sooner or later become the permanent prompting authority on…itself.

It’s not sentience, or self-awareness.

But AI’s current powers would certainly be exponentially amplified, should the technology ever acquire autonomous self-awareness.

TRENDPOST: Humankind is already in a strange symbiosis with Artificial Intelligence. As we collectively interface with it (or not), AI has been designed to feed off of that data for its continued learning.

(At least some) humans are finding ways to advance knowledge and profit, via AI.

But we are also creating a system where AI can increasingly comprehensively monitor and know more about humans, and every data metric of the physical world, than any of us do, ourselves.

Humans are already serving as decentralized physical sensory and processing nodes for AI’s, thanks to the way these platforms have been engineered, and thanks to ways we are being induced to interact with them. 

Who will benefit more via this nascent transhuman symbiosis, and whether humans can remain in control of it, is something that deserves more serious consideration than the current fits and starts of alarm and fragmented action.