Welcome to Now AI,<\/a> your weekly breakdown of the most compelling developments happening in artificial intelligence and your go-to guide for tips and tricks from the experts on how to best use the AI tools that have taken the world by storm. This week we spoke to digital artist ClownVamp about ways to unlock your prompting power in Midjourney, enter the fantastical art and universe of AI-collaborative artist Jenni Pasanen, and talk about the implications behind AI-generative content tools being used by some serious media institutions. <\/p>\n We also touch on the dangers of using AI tools in law enforcement, how brain-to-music models are going to become a reality sooner than you might think, and why AI detection programs just don\u2019t work. Let\u2019s dive in. <\/p>\n Artificial intelligence\u2019s ability to create convincing images isn\u2019t the only thing worrying people about AI\u2019s effect on the information ecosystem these days. While attention-grabbing images of Trump getting arrested<\/a> certainly have their quixotic appeal, for example, just as compelling and thorny a development is media entities utilizing programs to help them pen editorial articles.\u00a0<\/p>\n The idea divides both publishers and audiences. Some news sites have sworn off using the tools entirely; others have begun to approach them cautiously<\/a>. Hell, even here at nft now, we utilize ChatGPT to help us pen news<\/a> stories, and we are well aware of the potential pitfalls of doing so.\u00a0<\/p>\n But it seems that Google has taken that idea and turned it up to 11. This past week, the tech giant has been approaching major media entities, including The New York Times<\/em> and The Wall Street Journal, <\/em>with a product known internally as Google Genesis<\/a>. Billed as a helpmate to journalists, Genesis is said to be able to receive input in the form of details of current events and output it as news stories.<\/p>\n More than one Google executive who saw the pitch reportedly found it unsettling, though the company insists the product is a representation of an initiative to provide AI-based tools to help \u2014 not hinder or replace \u2014 journalists in what they do. <\/p>\n Without seeing the tool in action, it\u2019s difficult to assess its accuracy and potential use cases. News-based outputs from ChatGPT are prone to inaccuracies (i.e., hallucinations). More often than not, they read like a first-year college student doing their best impersonation of a newsroom.<\/p>\n If Google and the media organizations planning to use these tools can work around these issues while staying committed to transparency and accountability (a big ask), they could free up journalists to spend their time on more \u201chuman\u201d tasks. Though, the recent news of National Geographic<\/em> firing its entire team<\/a> of staff writers, while not explicitly tied to AI\u2019s rise in this way, has given the publishing industry serious cause for concern. <\/p>\n The fun part of AI\u2019s rapid rate of development is watching new tools be used in ways that remind you of your favorite sci-fi horror stories. Okay, we\u2019re reaching a bit, but it\u2019s no small thing that last week, it was revealed that police in New York State used AI to catch a drug trafficker<\/a> by analyzing their vehicle movements to make an arrest in 2022. The Westchester County Police Department used AI to search a database of nearly two billion license plate records in the two years prior to the arrest. <\/p>\n In a similar development, it recently came to light that the New York Metropolitan Transit Authority has quietly been using artificial intelligence to catch fare dodgers<\/a>, with the relevant software currently active in seven undisclosed subway stations in the city. Plans are in the works to roll that out to dozens more this year. <\/p>\n If the thought of the authorities tracking your movements with AI is unsettling to you, you\u2019re not alone. \u201cDragnet surveillance,\u201d a term that refers to the broad usage of AI tools across a population (as in the case of the New York State drug trafficker), comes with a slew of ethical (and, in the U.S., Constitutional) questions that nobody quite has the complete answers for yet. As many have observed<\/a> in recent years, without proper oversight, the tools \u2014 rather than the individuals using them \u2014 take on a certain authority, especially when their predictions go unquestioned. <\/p>\n As concerns about these tools\u2019 usage rise, expect to hear the age-old argument and classic misdirection trotted out by organizations, both criminal and civil, that if you have nothing to hide, you have nothing to worry about. <\/p>\n Rounding out the week\u2019s stories, we were pumped to see Google researchers release a paper<\/a> describing their \u201cBrain2Music\u201d model, in which they reconstructed musical outputs from fMRI readings. This follows in the footsteps of a recent study that proposed Mind-Video<\/a>, a similarly themed AI approach to reconstructing video from brain readings after combining them with a custom model of Stable Diffusion. Brain-to-X functionality may sound like a distant possibility, but its foundations are being laid now. <\/p>\n And for those of you hoping that the swell of AI-generated content could be kept in check by AI detection tools<\/a>, we have bad news for you \u2014 they\u2019re kind of terrible at their job. So terrible, in fact, that OpenAI recently shuttered<\/a> its own detection tool, AI Classifier. <\/p>\n Launched in January, the company wrote as an addendum to the blog post announcing the tool\u2019s launch that \u201cthe AI classifier is no longer available due to its low rate of accuracy. We are working to incorporate feedback and are currently researching more effective provenance techniques for text, and have made a commitment to develop and deploy mechanisms that enable users to understand if audio or visual content is AI-generated.\u201d Sorry teachers, your next-level \u201cplagiarism\u201d detector will have to wait. <\/p>\n And in a surprising (but perhaps cosmetic) display of adherence to some form of oversight and transparency in the AI world, President Biden managed to get Google, Amazon, Meta, OpenAI, and three other companies to agree to voluntary safeguards<\/a> in the race to develop the technology. The companies involved made their commitment to the guardrails, which include a pledge to transparency, fighting against bias, and \u201cwatermarking\u201d AI-generated content, during a meeting at the White House on July 21. <\/p>\n If you\u2019ve heard of AI image generators, you\u2019ve heard of Midjourney. Since its debut in July of 2022, the text-to-image model has become one of the most popular programs for AI-collaborative creation in existence. With well over 13 million active users in its Discord server (a million of which are online at any given time) and new updates rolling out regularly<\/a>, Midjourney is unlikely to lose steam anytime soon. <\/p>\n But, despite the popular misconception that programs like Midjourney simply require you to lazily type a few words to obtain an incredible result, prompt craft \u2014 the art of refining the input a user gives to an AI model \u2014 is no easy task. This is compounded by the fact that, with every new update, there are even more tools to incorporate into your prompts to get a desired image output. <\/p>\n For this week\u2019s \/Promptly,<\/em> we spoke to the inimitable AI-collaborative artist ClownVamp<\/a> about some of the most overlooked and powerful prompting techniques<\/strong> Midjourney users should know to up their creative game. <\/p>\n ClownVamp: <\/strong>One of my favorite prompt techniques is the dial prompt. This is where you break up your prompt into many small tokens with custom weighting, also known as Multi Prompts<\/a>. Let\u2019s start with an example.<\/p>\n Prompt: grainy photo of a happy man in the 1970s. \u2013q 2 \u2013style raw<\/em><\/p>\n I almost always use style raw to reduce the \u201cMidjourney look.\u201d When you prompt this, you get a result that matches the prompt but can be a bit repetitive.\u00a0<\/p>\n Let\u2019s see how multi-prompting can make this better. To do this, simply separate each concept by a double colon (::). It will look like this:<\/p>\n Prompt: grainy photo:: happy:: man:: 1970s:: \u2013q 2 \u2013style raw<\/em><\/p>\n This on its own won\u2019t give you good results, as it\u2019s forcing Midjourney to evenly weight each concept (e.g., \u201chappy\u201d as much as \u201cman\u201d). You will likely get outputs that are somewhat nonsensical:<\/p>\n The real power comes when you start to weigh each concept separately.\u00a0The default weight is 1, and you can weight each phrase anywhere between 0-2. I\u2019ve found below .25 isn\u2019t very noticeable, and above 1.5 is often overpowering, so I tend to spend most of my time between .25-1. <\/p>\n As an aside, putting a weight below 1 <\/strong>does not constitute a negative prompt. If you put it below 1, Midjourney still adds that aspect to the output, just to a lesser degree. If you want your prompt to reduce<\/em> something, make the number negative.\u00a0Let\u2019s give our new approach a try.<\/p>\n Prompt: grainy photo::1.5 happy::.25 man::1 1970s::1.5 \u2013q 2 \u2013style raw<\/em><\/p>\n Voil\u00e0! We get much more interesting results with substantially more variety. Some won\u2019t be a perfect fit, but that\u2019s an okay price to pay:<\/p>\n Why does this work to give us better, more interesting results?\u00a0To over-simplify, rather than the model finding the nearest match in the latent space (and continue revisiting that exact space and the resulting repetitive images), this approach is looking at the intersection of these concepts with the relative weightings we\u2019ve provided, seemingly putting them in tension with each other.\u00a0<\/p>\n You can combine this approach with other tools.\u00a0Let\u2019s look more closely at the negative prompting we mentioned earlier. Let\u2019s say I get annoyed at the model producing all these 70s-era jackets. I could add the following to my prompt:<\/p>\n Prompt: grainy photo::1.5 happy::.25 man::1 1970s::1.5 jacket::-.25<\/strong> \u2013q 2<\/em><\/p>\n Now we get more images sans all those jackets!<\/p>\n One of the best things about the dial prompt is that you can combine this with conditional prompting to quickly discover new aspects of the latent space. Conditional prompts allow you to generate multiple prompts in one go by putting variables in brackets.\u00a0For example:<\/p>\n Prompt: grainy photo::1.5 happy::{.25,.75} man::{1,1.25} 1970s::1.5 \u2013q 2 \u2013style raw<\/em><\/p>\n This would create four outputs that test two different weights for the two categories with conditional prompts. This burns through credits, though, so be careful about doing this in credit mode.<\/p>\n There you have it \u2014 power prompting with dials. Start exploring the latent space with more control, and have fun.<\/p>\n \u201cCreating in the new era of art, where creativity and technology merge as one,\u201d reads a pinned tweet on AI-collaborative artist Jenni Pasanen<\/a>\u2018s page. There could hardly be a more apt way to frame her stamp on the art world; the Finland-based creative\u2019s work deals in the fantastical and tangibly felt, able to transport even the most cynical viewer to a place of strange (and sometimes unnerving) everyday enchantment.<\/p>\n Pasanen\u2019s background is in design and animation, and she has been experimenting with digital painting for the better part of the last two decades. She began teaching herself about the world of crypto and NFTs in 2020 and minted her first collection in March 2021.<\/p>\n \u201cI was mesmerized by the endless possibilities [AI] could offer, and it immediately resonated with me,\u201d Pasanen said in an interview with nft now<\/a> this spring. \u201cI knew I had finally found my home in art. From that moment on, I have been using AI as a part of my craft. It was the missing piece I had always been looking for.\u201d<\/p>\n Few have blended the more traditional aspects of digital art with AI as well or as beautifully as Pasanen, who uses Photoshop and Artbreeder in a workflow she describes as a \u201clayer cake\u201d approach to creation. On July 18, Pasanen released Lope, a long-form generative art collection of 101 pieces that invite the viewer to consider the relationship between the rational and the emotional. <\/p>\n There is no shortage of incredible images and videos being created with AI these days, especially at the intersection<\/a> of Midjourney and Runway Gen 2. Here are some visually compelling videos that caught our eye this week. <\/p>\nIn the Know: The Week\u2019s Top AI Stories<\/h2>\n
Google\u2019s News-Writing AI Tool Causes a Stir<\/h3>\n
Police Use AI to Catch Drug Trafficker, Transit Fare Dodgers<\/h3>\n
![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/asael-pena-OfYuB4Aby1M-unsplash-min-1200x800.jpg\")
AI Detection Tools Suck, Biden Forces AI Guardrails, Brain-to-Music Is Now a Thing<\/h3>\n
![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/Brain2Music-1200x564.png\")
<\/a>
\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/06\/Detective-Jack-1200x850.png\")
\/Promptly: Midjourney Multi-Prompts With ClownVamp<\/h2>\n
Discovering the Dial Prompt<\/h3>\n
![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/CV1.png\")
<\/figure>\n<\/div>\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/CV2.png\")
<\/figure>\n<\/div>\n<\/div>\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/CV3.png\")
<\/figure>\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/CV4.png\")
<\/figure>\n<\/div>\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/CV5.png\")
<\/figure>\n<\/div>\n<\/div>\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/CV6-min.png\")
<\/figure>\n
\n![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/Jenni-Pasanen-Golden-Ratio.png\")
Against the Grain: Jenni Pasanen<\/h2>\n
![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/Pasanen-Reflection-1200x1496.png\")
![\"\"](\"https:\/\/nftnow.com\/wp-content\/uploads\/2023\/07\/Lope-1200x673.png\")
\nAI Candy<\/h2>\n