Behold the plight of the author who “completes” a book about Artificial Intelligence, sends it to the editor as a finished manuscript, but wakes up each day to new and relevant information that is pertinent to the subject of the book.
So, grateful to this blog that will allow for updates such as the one this weekend, where I make references to a development using GPT-4, and the results of a research study touching upon the subject of AI, creativity and the human/robot dance.
What’s new with GPT-4?
For those of us already engaging with ChatGPT through word prompts, now there is another way to establish communication with the bot to get results.
OpenAI now offers GPT-4, a large multimodal model (accepting image and text inputs, emitting text outputs) that, “while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks.”
This means that you can now input an image into the prompt to get responses. You can read all about it here.
Visual inputs
From OpenAI
GPT-4 can accept a prompt of text and images, which—parallel to the text-only setting—lets the user specify any vision or language task. Specifically, it generates text outputs (natural language, code, etc.) given inputs consisting of interspersed text and images. Over a range of domains—including documents with text and photographs, diagrams, or screenshots—GPT-4 exhibits similar capabilities as it does on text-only inputs. Furthermore, it can be augmented with test-time techniques that were developed for text-only language models, including few-shot and chain-of-thought prompting. Image inputs are still a research preview and not publicly available.
What does GPT-4 do? In one of my practice sessions, I used the following prompt and an image depicting a vision of what the newsroom of the future might look like when AI becomes a more widely utilized tool. The image was created using Midjourney, a program for illustration creation
My initial prompt to GPT-4:
Do you see this image as a true representation of the newsroom of the future when Artificial Intelligence will play a key role in how content is created and presented?
The response from GPT-4:
The image you provided does convey a futuristic, tech-intensive setting that could be interpreted as a possible vision for a newsroom of the future. Here are some observations and points to consider:
- Integration of Advanced Technology: The multiple holographic displays and augmented reality interfaces suggest an environment where technology plays a significant role in content creation and presentation.
- Human-AI Collaboration: The presence of human characters alongside advanced tech might indicate a collaborative approach where humans and AI work in tandem. This aligns with many predictions that AI will not replace humans in creative endeavors but will rather augment their capabilities.
- Diverse Information Streams: The multitude of screens and displays suggests access to a vast amount of information in real-time, which AI could help curate, verify, and present in a meaningful way.
- Adaptable Workspaces: The flexible and dynamic nature of the workstations (with holograms and adjustable screens) hints at a future where newsrooms can rapidly adapt to changing situations or breaking news.
However, while the image provides a vision of what might be possible, predicting the exact nature of future newsrooms is challenging. The role of AI will undoubtedly grow, but its integration will depend on technological advancements, ethical considerations, and the evolving needs of news consumers.
In summary, while the image is a compelling representation, it’s just one of many potential visions for the future of newsrooms. Actual future developments will be influenced by a myriad of factors beyond just technological advancements.
Why this matters?
Perhaps we could have gotten a similar list from a word-only prompt, but with GPT-4 we may add another layer to content creation by having AI help us analyze an image. I find that, while some of the AI comments about the image represent the obvious, there is always content that we may have not thought about. In this example, I liked to read this AI assessment:
In this example, I liked to read this AI assessment:
The presence of human characters alongside advanced tech might indicate a collaborative approach where humans and AI work in tandem. This aligns with many predictions that AI will not replace humans in creative endeavors but will rather augment their capabilities.
The importance of the prompt
Just as word prompts with substance lead to more intelligent responses, the same applies to the use of an illustration to generate a response. In the example above, my prompt was longer and more explanatory.
But here I tried a simple one after inputting the image:
What is going on in this image of a newsroom of the future?ChatGPT
Here is the GPT-4 response
This artwork portrays a dynamic and technologically advanced setting that could be interpreted as a vision of a future newsroom. Here’s a breakdown of what seems to be happening:
- Central Character: At the forefront, a man is intently focused on a piece of paper or a digital tablet, perhaps jotting down notes, sketching, or editing a piece of content. His concentration suggests the importance of his task.
- Holographic and Augmented Displays: Numerous holographic screens float around, displaying different types of content—from text articles to maps and visual data. This suggests a highly digitalized workspace where vast amounts of information can be accessed and manipulated in real-time.
- Collaborative Environment: To the left, a person wearing a virtual reality (VR) headset gestures towards a display, indicating a collaborative discussion or analysis of the content. This could be a representation of future tools that journalists might use to immerse themselves in stories or data.
- Mature Figure: To the right, there’s a large, almost ethereal figure of an older individual overlooking the scene. This could symbolize the wisdom and experience of past journalism or perhaps represent a significant figure in the news or media industry.
- Background Activity: Other individuals are seen working at their stations, each engaged in different tasks, emphasizing the bustling nature of a newsroom. Some are at computers, while others seem to be in discussions.
- Tech-Heavy Environment: The presence of various tech gadgets, cables, and advanced computer setups underscores the tech-driven nature of this envisioned newsroom.
- Global Connectivity: The large globe hologram in the middle might signify the global reach of news and the interconnectedness of the world.
- Diverse Information Streams: The multiple screens and displays showcase a variety of content, from cityscapes to written articles, suggesting the wide range of topics covered in the newsroom.
In summary, this image paints a picture of a future newsroom teeming with advanced technology, where human journalists leverage tools like AR, VR, and holography to curate, analyze, and present news in innovative ways.
How to do it
Open your ChatGPT as you normally do, but make sure you check GPT-4 at the top of the screen. Simply drag the illustration that you wish to prompt the bot with and write your prompt. Hit enter. And remember that practice makes perfect here too. Have fun.
Insightful AI research
One of the most fascinating aspects when studying and discussing Artificial Intelligence is that of how humans and robots interact. In my new book, AI: The Next Revolution for Content Creation, I devote much thought to what I refer to as the “dance” that takes place when humans and robots come near each other. That is why I found this new study from the Boston Consulting Group (BCG) so insightful, starting with the title—How People Can Create—and Destroy—Value with Generative AI .
Go here to read the complete study:
https://www.bcg.com/publications/2023/how-people-create-and-destroy-value-with-gen-ai
Key Takeaways
A first-of-its-kind scientific experiment finds that people mistrust generative AI in areas where it can contribute tremendous value and trust it too much where the technology isn’t competent.
- Around 90% of participants improved their performance when using GenAI for creative ideation. People did best when they did not attempt to edit GPT-4’s output.
- When working on business problem solving, a task outside the tool’s current competence, many participants took GPT-4’s misleading output at face value. Their performance was 23% worse than those who didn’t use the tool at all.
- Adopting generative AI is a massive change management effort. The job of the leader is to help people use the new technology in the right way, for the right tasks and to continually adjust and adapt in the face of GenAI’s ever-expanding frontier.
- Conclusion: Generative AI will likely change much of what we do and how we do it, and it will do so in ways that no one can anticipate. Success in the age of AI will largely depend on an organization’s ability to learn and change faster than it ever has before.
My take:
I found this study to reinforce what my own informal research for my book reveals: the process of using AI for our work as content creators begins by adopting an open mind attitude. As the study authors suggest, “people need to radically revise their mindset and their approach to work. Instead of the default assumption that technology creates a helpful first draft that requires revision, people should regard the output as a plausible final draft that they should check against firm-established guardrails but otherwise largely leave as is.”
Perhaps the most significant takeaway from this study: AI can help with the creative process, especially when humans come to AI with definitive ideas and thoughts. That’s when the real effective dance begins.
Pre-order my new AI book here
Here is a chance to pre-order my new book about Artificial Intelligence and content creation. The first 25 copies sold will be signed! Order here:
https://thaneandprose.com/…/preorder-ai-what-to-expect…
Pre-publication reviews here!
AI front and center
As I put finishing touches on the manuscript of my new book, AI: The Next Revolution for Content Creation, I am aware that the number of AI-related headlines that appear in my mailbox daily is on the increase, frustrating the author of a book that must have a date of completion, and realizing that in today’s fast paced technological advance environment, books must have websites created for updates.
For more about my new AI book, go here:
Other AI-related blog posts
ChatGPT gets competition–say hello to Claude 2
https://garciamedia.com/wp-admin/post.php?post=21948&action=edit
Of related interest
https://newspaperdesign.in/ai-is-the-next-big-media-revolutionmario-garcia/
Newsrooms around the planet have gone mobile-first after a Garcia Media workshop!
Our Garcia Media Mobile Storytelling workshops are proven to introduce your editorial team to the way we write, edit and design for mobile platforms. It is a one-day program that involves a presentation (where I summarize my Columbia University class content), and follow it with a hands on workshop.
Did you read The Story yet?
I urge you to consult my latest book, The Story, a trilogy full of tips and explanations about mobile storytelling, which represents the latest genre for journalists to explore. See information below:
The full trilogy of The Story now available–3 books to guide you through a mobile first strategy. Whether you’re a reporter, editor, designer, publisher, corporate communicator, The Story is for you! https://amazon
Volume 1: Transformation
https://books.apple.com/us/book/the-story-volume-i/id1480169411
Volume Two: Storytelling
https://books.apple.com/us/book/the-story-volume-ii/id1484581220
Volume Three: Design
https://books.apple.com/us/book/the-story-volume-iii/id1497049918
Order the print edition of The Story, from Amazon, here:
The Story, en español:
TheMarioBlog post #3377