Search Results

AI, Pink Ponies & a Slide Deck: A Surprisingly Fun and Eye-Opening Experiment AI-generated party decks: fun, fabulous… and sometimes unexpected . Gamma made pitching the Pink Pony Club Party a breeze, except for the surprise Playboy aesthetic. Lesson learned: AI still needs a chaperone How AI Presentation Tools Took Me by Surprise I have a confession: I actually like making presentations. (I know. Who admits that?) So, I hadn't spent much time playing around with AI deck creators like Gamma or Beautiful.ai . But last week, my friend, Caroline Holden , who is currently taking the AI world by storm with her humor and creativity, gave me a reason to reconsider. At an AI roundtable, she unveiled a presentation about Spam —both the Minnesota-made food and the email variety. Talk about a recipe for laughs. She explained how she made it in a matter of minutes for a PowerPoint Party! You heard that right, a PowerPoint Party . It's literally people getting together to show off their presentations. Turns out PowerPoint Parties are a thing! CNN even covered it in 2024: check it out here . Caroline Holden proving that AI can make PowerPoint presentations fun, especially when they’re about Spam. I couldn't get over how clever and hilarious the deck turned out and how she went from concept to completion in a matter of minutes. I wondered, could Gamma do the same for me? I took Gamma for a little joy ride over the weekend to see if it could help me come up with a pitch for a themed Pink Pony Club party.  🎠 Using ChatGPT to Plan the Perfect AI-Powered Presentation 📝 Before jumping into Gamma, I started in ChatGPT. To fully test AI’s ability to create a party pitch deck , I wanted to make sure I covered all the right elements. We boiled it down to: 1️⃣ Party Name  – A catchy, fun title. 2️⃣ Number of Attendees  – Estimating headcount for planning. 3️⃣ Who Brings What  – Delegating tasks to stay on budget. 4️⃣ Budgeting Tips  – How to keep costs low but make it magical. 5️⃣ Where to Buy Party Supplies in the Twin Cities  – Best local shops & online options. 6️⃣ The Invite  – Fun, engaging party invitation text. 7️⃣ Menu  – Delicious food & drink recipes that fit the theme. 8️⃣ Games & Activities  – Fun things to do that match the Pink Pony vibe. We started with this outline, but I knew I wanted key elements like signature party drinks and music suggestions. After a few tweaks, I felt like it was solid enough for this demo. What surprised me most is that ChatGPT's reply started with, " This is going to be a BLAST ". ChatGPT takes the reins! From party planning ideas to a full AI-generated presentation, see how AI can turn a fun concept into a pitch-ready deck in minutes." Testing Gamma AI: Can It Create a Stunning Pitch Deck in Minutes?⚡🎭📑 I pasted the detailed text from ChatGPT into Gamma and within seconds it produced a 15-page slide deck. Sounds great until you realize your free plan only allows you to have 10 slides. That meant 5 slides had to go unless I paid for an upgrade. I chose to edit. ✂️ My favorite slides: The Signature Drinks Section : It came up with fun formatting and visuals for the Pink Pony Paloma and Glitter Rodeo Martini. The Party Invite : The wording was perfect, and the layout made it feel like an event people couldn’t say no to. The Playlist Display : It organized the Pink Pony Club playlist by genre, which looked way better than my bullet points. My Not-So-Favorite Things ❌ Lack of Diversity in Images  – Every AI-generated image of women looked… the same. Where’s the representation? AI, do better. ❌ Why So Sexy?  – AI generated images that looked more playboy than real-life. Lots of cleavage, little left to the imagination if you know what I mean. Not exactly the vibe I had in mind for middle-aged women. 🤦‍♀️ See for yourself! AI meets party planning! This Pink Pony Club Party deck was built in Gamma to prove that even the wildest party ideas can be close to pitch-perfect with the right AI tools—though AI’s idea of ‘fun’ leaned a little more Playboy than middle-aged gals’ night out. Lesson learned! 😆 I was curious to get ChatGPT's take. Would these images be more diverse if the context wasn't a Pink Pony Party? While ChatGPT answered that Context Matters, it also reiterated that the models should not automatically default to Barbie-bodied scantily dressed women!!! Yes, I asked for a party theme—not a boardroom—but why does AI still default to the same polished, hyper-feminine look for women? This isn’t just a one-off; it’s a trend we’re seeing across AI-generated images. Let’s talk about why that matters. So, Is AI My New PowerPoint BFF?  Not quite. But if I ever need a presentation in a pinch, Gamma is the kind of friend who shows up last-minute with a fully decorated cake and makes it look like you planned everything weeks ago .  🎂 You just might need to modify the frosting (images). Your Turn!  Have you tried AI deck creators like Gamma or Beautiful.ai? What were your results like? And what could you see yourself using them for? 🤩. Also, have you noticed bias in the depiction of women when generating images? Please share. Final Note Before hitting publish, I always let AI take a second look. Here’s what it had to say. Final Verdict: It’s 90% there —just a few flow tweaks, sentence refinements, and maybe a title punch-up would make it even stronger. Absolutely love the energy and humor in this!  🏇✨🎉 Interested to learn or talk more about AI? I'm here for you!

How AI Can Help You Spot Fraud, Avoid Deception, and Keep Your Data Secure. Too Good to be True! We’ve all received one of those suspicious pieces of mail: a flashy envelope proclaiming, “Congratulations! We want to offer you a free vacation!”  It’s tempting to believe, especially when you're dreaming of escaping freezing temperatures. But deep down, we know better. A senior citizen reviewing a suspicious email with an AI assistant highlighting warning signs created by DALL*E This got me thinking: could AI help us identify scams more easily? I decided to test it out by analyzing a recent travel invitation that came in the mail. I had a little conversation with ChatGPT about it. Lori records a video asking ChatGPT about a letter that seems misleading! The process was fascinating, and it led to a bigger realization: AI could serve as a scam detector for people who may not have the tech-savviness to recognize fraud immediately, especially seniors or individuals living alone. When I commented to ChatGPT, "This looks like spam to me." The answer was yes. When I asked ChatGPT about the postage and who the letter was from! The Growing Challenge of Sophisticated Scams Scams are becoming more advanced, thanks in part to AI itself. From deepfake videos to AI-generated phishing emails, fraudulent tactics are getting harder to spot. This makes it more important than ever to develop AI-driven tools that can help combat deception. Why this matters: AI-generated scams are on the rise  – Fraudsters are using AI to create ultra-realistic scams, making them more convincing than ever. Not everyone has a tech-savvy friend or family member to ask  – Many people, especially older adults, may lack immediate access to help when they receive suspicious messages. AI can provide confidence in decision-making  – Instead of second-guessing, individuals can use AI tools to verify legitimacy. Scammers thrive on urgency  – Many scams create a sense of pressure ( “Act now or lose this opportunity!” ). AI could act as a rational filter to help people pause before acting. How an AI Scam Detector Could Work Imagine a simple, user-friendly AI tool designed to analyze potential scams. It could work as a chatbot, a mobile app, or even a voice-activated service that helps users evaluate suspicious messages through a series of guided questions: Who is the sender?  – Is it a government agency, a financial institution, or an unknown source? What does the postage look like?  – Is it bulk mail or handwritten? Does the email address look suspicious?  – Are there misspellings or random characters? What does the message say?  – Does it use urgency, free gift offers, or ask for personal details? Does it request payment, banking details, or login credentials?  – A huge red flag. Does it seem too good to be true?  – Because it probably is! The AI could then compare the input to known scam patterns, cross-check databases, and provide a clear verdict: Likely Scam, Possibly Legitimate, or Needs Further Review. And I have to say ChatGPT also did really well when I had an urgent message displayed on my Mac and I wasn't sure what to make of it. You can watch the video here with the responses. Addressing Potential Concerns Of course, not everyone may be on board with an AI scam detector. Here are a few common concerns: 🤖 Can AI really be trusted for this?  – AI is not perfect and could mislabel legitimate messages as scams (or vice versa). But with continuous updates, its accuracy would improve. 🤔 Isn’t this just common sense?  – While some scams are obvious, many are well-crafted. Plus, not everyone has the experience to recognize them. 🔐 What about privacy concerns?  – Any AI tool would need strict data protection policies to ensure that users' personal information is not misused. And there would need to be reminders telling people to be careful what they show the tool for analysis. Conclusion: AI for Good AI is already a powerful ally in the fight against fraud. Think about fraud alerts on your credit cards. If you're interested in using AI to help detect spam or scam messages today, you can: Use ChatGPT to analyze suspicious messages (just be careful not to share personal information) Try built-in scam detection tools in email services like Gmail Look for browser extensions that help identify suspicious websites. Share this article with someone who might benefit from these tips While we may never eliminate scams entirely, an AI scam detector could provide an extra layer of security, especially for those most vulnerable. So, what do you think? Would you use an AI tool like ChatGPT, or do you have other ideas for fighting scams? Let’s start the conversation. 💬 Essential Resources to Report and Avoid Fraud FTC Report Fraud  – The easiest and most comprehensive place to report scams and fraud in the U.S. FBI Internet Crime Complaint Center (IC3)  – If the scam involves online fraud, phishing, or cybercrime, this is the place to report it. Better Business Bureau (BBB) Scam Tracker   – Great for checking and reporting scams happening in your area.

Love it or hate it, AI is reshaping how we use our time. This Valentine's Day, let's talk about the sweet (and sometimes bittersweet) impact of AI on productivity. Image generated by DALL·E 🌹Some people get roses on Valentine's Day. I get data. And this latest AI study shared by Ethan Mollick , Associate Professor at the Wharton School, has my heart skipping a beat. Ethan Mollick's LinkedIn Post on Thursday, Feb 13, 2025 The study, " The Labor Market Effects of Generative Artificial Intelligence " surveyed 4,278 people in early December 2024 . A random sampling approach was used with a focus on U.S. workers, making this one of the most comprehensive looks at AI's impact on how we work. This Study Illustrates What's Really Happening with AI at Work? 30.1% of workers (that's nearly 1 in 3!) are using AI tools at work One-third of those users have made it part of their daily routine This study looked at workers across all industries, ages, and education levels and how it's saving significant time every day. AI’s Time Machine: How It Saves You Hours Daily Imagine having more than an hour back every workday. That's like finding a hidden stash of time chocolate! That's essentially what's happening with AI in the workplace. This isn't just about getting things done faster; it's about fundamentally transforming how we work. Who’s Really Using AI? The Surprising Adoption Stats AI adoption isn’t following the usual tech playbook. Typically, new technology starts in predictable circles. Think white, male, and tech-heavy industries—before trickling out to the rest of the workforce. But this study? It shows something revolutionary  happening. I had to ask AI to double-check what I was seeing in the graphic below because I was so surprised. The Numbers That Challenge Everything We Thought We Knew: Hispanic workers are leading the charge with a 40% adoption rate Black workers  aren't far behind at 35% White workers  come in at 32% Usage of Generative AI by different racial demographics as surveyed in The Labor Market Effects of Generative Artificial Intelligence This data proves something powerful: AI isn’t just for tech insiders . It's becoming a tool that anyone, in any industry, can use to tackle work challenges But (and there's always a but) The results show a gender gap! 38% of men report using AI at work 27.8% of women say the same While AI might be breaking down some barriers, it's running into others that have long plagued the tech world. Usage of Generative AI by Gender: Males have the highest mean usage, followed by females and those who prefer not to say, according to survey data. The Education Factor It's like having a library card in the digital age. The more education you have, the more likely you are to use AI. So how do we ensure adoption across all education levels? Graduate degree holders: Nearly 50%  are using AI High school graduates:  About 20%  are using AI Generative AI utilization increases with higher education levels, peaking among those with graduate degrees, according to survey data. AI’s ROI: How It’s Slashing Work Hours and Boosting Productivity Science & Deep Thinking Science tasks: from 177 minutes to 35 minutes (Faster Medical Breakthroughs & Life-Saving Research?) Critical thinking : from 102 minutes to 27 minutes—wait, should we be celebrating that? AI is great at speeding things up , but critical thinking isn’t just about efficiency—it’s about depth, reasoning, and reflection. If we’re cutting our deep thinking time by nearly 75%, what does that mean for the quality of decisions? Complex problem solving : from 122 minutes to 30 minutes The Human Touch (Yes, AI Helps With That Too!) Negotiation : from 141 minutes to 29 minutes Active listening : from 138 minutes to 32 minutes Speaking : from 123 minutes to 30 minutes Comparison of Task Time Reduction: A visual representation of task durations before and after process improvements, showcasing efficiency gains across various tasks as a percentage of original time used. Designed by me, however, assisted by AI to build out every row. When I saw this visual, I did a double take on the time savings on traditionally human-centered tasks like negotiation and active listening. ( Figure 11, p. 19 ). This suggests that AI is not only enhancing technical and analytical work but also playing a role in augmenting  communication-based tasks. Structuring arguments Preparing talking points Analyzing sentiment in conversations Role-playing negotiations Transcribing calls Summarizing key points from meetings Offering instant feedback in real-time discussions. Real World Impact: From Hours to Minutes During AI Salon founder, Kyle Shannon 's, office hours today, one of the participants, a supply chain manager at a well-known pet supply brand shared two real-life examples. Safety Incident Reporting: Before AI, investigating a safety incident was a marathon—think 'Lord of the Rings' levels of time commitment. It took three hours of.... Taking pictures Conducting interviews Having employees handwrite statements Manually compiling everything into a report After AI, suddenly that three-hour marathon becomes a 10-15-minute sprint. Using a custom GPT, employees now leave voice notes that AI automatically transcribes and structures into a formal report in 15 minutes or 10 minutes for experienced managers. HR transcription tasks for employee feedback boards What used to take an hour of manual transcription now happens in seconds - snap a picture, let AI do its magic, and done. While AI didn't replace humans in either scenario, it definitely sped up the process significantly. Why This Matters for Your Business Now, think about what this means for your workday. The almost 2 and a half hours you used to spend preparing for a negotiation? Now it's a focused 30-minute sprint with AI as your prep team. That two-hour concentration on scientific analysis? You're done before your coffee gets cold. If AI is giving your employees back a couple of hours a day, that's not just about productivity, it's about satisfaction. It's about having time to think, create, and yes, maybe even leave work early enough to have dinner with family. Would you want to leave a company that gives you that kind of gift? Employee Retention When you retain your employees, think of the value. Beyond productivity, AI adoption has the potential to reduce employee turnover, which is an expensive problem for businesses. The cost of replacing an employee includes both direct costs (recruitment, onboarding, training) and indirect costs (lost productivity, decreased morale, and loss of institutional knowledge). Studies estimate that turnover can cost between 30% to 200% of an employee's salary depending on the role and industry. That’s the heart of ROI right there It’s why I love doing what I do, helping people see that AI isn’t just some trendy tech, but a practical, time-saving powerhouse. This week, I had the opportunity to bring people together at Modernwell to share knowledge and watch lightbulb moments happen in real-time. I always leave these sessions feeling energized because AI is one of those rare topics that gets people excited once they see its real-world impact. What about you? What is your take on this generative AI use study? Does it concern you, or get you excited? Also, have you noticed anything with your own work? Are you seeing AI dramatically reduce the time that it takes to complete certain tasks? Or are you running into certain scenarios where it's costing you more time than it's saving? Please share your stories so we can support each other and learn together. And also please check out the additional reading with different view points. Further Reading: The Bigger Picture on AI & Critical Thinking If this study has you thinking (pun intended) How AI Is Changing The Way We Communicate   – How AI is transforming human communication and the implications for critical thinking. - Forbes The Dark Side Of AI: Tracking The Decline Of Human Cognitive Skills – An examination of how AI might be diminishing our reliance on personal cognitive abilities. - Forbes AI Thinks Differently Than People Do—Here’s Why That Matters   – Harvard Business Review breaks down why AI’s reasoning isn’t the same as human thinking—and why that’s important. - HBR

By: Katya King Lorignite's amazing intern, Katya King takes a look at how AI is shaking up th e world. Today she breaks down the 2025 Grammys and the growing role of AI in music. For 67 years, the Grammys have been the most prestigious night in the music industry, honoring the world’s greatest artists and their timeless creations. But this year was different. History was made, or should I say generated…  Blurred Lines AI has been creeping into music for years, but the 2025 Grammys made it official: AI isn’t just a tool, it’s now shaping the way music is made, performed, and even awarded. From resurrecting lost voices to creating entirely new compositions, AI is blurring the lines between human creativity and machine-generated sound. And it’s sparking some serious debate. The Grammys: AI edition AI Takes the Stage As I watched the 2025 Grammys this week, one topic kept coming up: AI . Even host Trevor Noah couldn’t ignore it. He brought up Nvidia, the tech giant that lost over $600 billion in a single day last week, largely due to the rise of DeepSeek, a Chinese AI startup making waves. DeepSeek is China’s version of ChatGPT, and what’s making headlines is how cheaply they developed it. DeepSeek claims to have trained its model for under $6 million, a fraction of what U.S. companies typically spend. This has raised questions about whether AI development really needs to be as expensive as it has been. But enough about the business side—let’s talk about the music. AI isn’t just shaking up tech stocks; it’s changing the way artists create. Noah also highlighted how musicians are using AI to revive unfinished songs, generate beats, and even compose entirely new tracks. It’s opening up a whole new world of possibilities, but it’s also raising some big questions . Now and Then: The Beatles' Last Song As I continued watching the awards show, I was also shocked to see that the Beatles won a Grammy in 2025. How is that even possible? The answer: AI. Paul McCartney and Ringo Starr were able to extract John Lennon's voice and create a new song, Now and Then , bringing all four members together once again. The original recording dates back to 1979 in New York City, filled with background noise from traffic. AI was able to separate Lennon’s voice from the noise and piano, making it sound crisp and clear. McCartney also clarified that AI was used to enhance the sound, not to generate new vocals. I decided to listen for myself, and to my surprise, it sounded amazing and not AI-like at all. I don’t listen to the Beatles much, but I can definitely see why this won a Grammy. This makes me wonder how other artists will start using AI to help them create music. Why Timbaland Spends 10 Hours a Day on Suno  Timbaland , the four-time GRAMMY Award-winning producer, is a strong advocate for AI in music creation. He has become a strategic advisor for Suno , a leading AI music creation tool. After months of being a top user of the platform, he formalized his involvement to push forward creative strategy and inspire a new generation of artists to innovate and create. “It’s like I’m 19 years old. It’s like falling back in love with the purity of creativity” This technology opens up so many creative possibilities, something Timbaland fully supports. To showcase its potential, he recently announced a competition inviting artists to remix one of his songs using AI. This contest really shows his belief in AI’s role in music but also how it can be a tool for innovation in the music industry. This is exciting, but it does raise a lot of ethical concerns about copyrighting and authenticity. Real or Fake Music? AI in music isn’t just being used by artists. It’s also showing up in unexpected places, like TikTok. I’ve come across multiple AI-generated audios that mimic Taylor Swift’s vocals and style so well that they sound almost indistinguishable from the real thing. I decided to ask around campus and see what other students thought. An anonymous “swiftie” even claims that one of the AI-generated songs is “lowkey better than the original”. This song was created by a fan on TikTok and it is based off her song ​​Suburban Legends. This raises the question: could it become impossible to tell AI-generated songs from authentic ones? Many artists are concerned about this, with over 200 musicians signing an open letter against AI and Big Tech, calling out what they see as “predatory” use of their voices. One of my favorite artists, Billie Eilish, who received seven Grammy nominations this year, has spoken out against AI in music. This surprised me, considering her frequent use of autotune and the futuristic sound that defines her style. It makes me wonder where the line is between using technology as a tool and AI taking over creativity. AI Generated Taylor Swift Song The Sound of the Future So what does the future look like for artists who get nominated for a Grammy? AI is already making its way into the industry, and I wouldn’t be surprised if more artists start using it in their music. But with limited regulations in place, I could also see some major legal issues coming up. Music is so special because it has meaning and conveys emotions that only humans can really understand. Will AI ever be able to truly replicate that, or is there something about music that will always need a human touch? What do you think? Comment down below! Supporting Articles & References Rolling Stone – Timbaland Embraces AI Music Production, Announces Partnership with Start-Up Suno By Brian Hiatt PR Newswire  – Timbaland Becomes Strategic Advisor To Leading AI Music Company Suno The Standard  – The story behind Now and Then: The Beatles' brilliant new track By Paul Kanareck Northeastern News  – How AI helped the Beatles revive John Lennon’s voice for their last song By Cody Mello-Klein The Music  – 200+ Artists Come Out Against AI, Big Tech By Ellie Robinson

I often get asked how I keep up with everything going on in AI. Truth is… it’s nearly impossible!  With new developments happening every single day, it can feel overwhelming. However, I do have some go-to sources that help me stay in the loop. I follow some of the best voices on LinkedIn and X , and I’ve also found a few must-listen podcasts  that keep me informed. Lorignite's Go-Tos for AI News 💡 To make it easy for you, I created an interactive list  using Lovable.dev ! You can explore it below: 📌Check out my curated list here: If you have a favorite AI expert, thought leader, or podcast that you think should be added to this list, let me know!  I’d love to keep this updated with the best resources out there. Let’s make this a shared learning experience . Please provide your recommendations in the comments! 🚀

If January and the First Few Days of February Are Any Indication, Buckle Up. Lori spinning from all of the AI News - A GIF Created with ChatGPT AI is Moving Fast—And It’s Hard to Keep Track Holy Camole, didn't expect breaking AI news on a Sunday, but it's just non-stop! OpenAI just released Deep Research , an initiative focused on tackling fundamental AI challenges—because, clearly, there wasn’t enough happening already. OpenAI introduces deep research Feb 2, 2025 Why did OpenAI Build it? Deep research is built for people who do intensive knowledge work in areas like finance, science, policy, and engineering and need thorough, precise, and reliable research. It can be equally useful for discerning shoppers looking for hyper-personalized recommendations on purchases that typically require careful research, like cars, appliances, and furniture. Deep Research is currently only available on the $200 a month pro plan but it's coming soon for other paid ChatGPT plans. (Sidebar: The above GIFs were created in ChatGPT simply because I was curious) Crazy how fast things become old news Just when you think you've caught your breath, the next advancement hits. I had a blog ready to post today recapping the insane release pace in January only to wake up to a fresh weekend release before the first business day of February. I can't even begin to imagine what the next 11 months will bring. Tracking the Chaos: My AI Advancements Timeline To help wrap my head around it all, I built a timeline to help visualize the pace of new developments since OpenAI released ChatGPT to the public in November of 2022. I used Perplexity to pull the key dates, Claude to help visualize the milestones and write code for an interactive map, and finally Lovable to publish it. Sounds simple, right? The fact checking of the dates was actually a nightmare. In fact, Perplexity initially used story publishing dates instead of actual release dates. Again, this reinforces why it's so important to have a human in the loop. And please know, this timeline is still a work in progress. But hopefully it gives you the gist of how fast and furious the changes are being flung at us. Check it out here: AI Advancements Timeline . The Competition is Intense And That’s a Good Thing Looking at the timeline, one thing is clear and that is there is no slowing down. The competition is fierce, and I like to think that's a good thing. Every new model release, every improvement in reasoning, and every open-source alternative that enters the game is pushing the entire AI ecosystem forward. We’re in a constant cycle of innovation, and the advancements we’re seeing in just a single month used to take years. My Go-To AI Tools—And Why I Pay for All Three For all the new tools popping up, my go-to AI assistants are still the same core three: ChatGPT Plus  ($20/month) – My everyday workhorse. Great for writing, brainstorming, and experimenting with different prompts. Claude Pro  ($20/month) – My go-to for thoughtful reasoning, long-form analysis, and project planning. Perplexity Pro  ($200/Annual) – My research powerhouse. Real-time data, solid citations, and great for getting a second opinion. Yes, I’m paying for all three, and yes, I think it’s worth it. Each one has strengths that complement the others, and in a world where AI is evolving this quickly, having access to multiple perspectives is invaluable. I can't tell how many times I take a conversation from one tool and then get feedback from another. AI is Finally Showing Its Work (And That’s a Big Deal) One of the biggest concerns with AI initially was that the information pretty much came from a black box. You have no idea how it came up with its output. Well, these new models show their work. I love seeing all the steps the models go through to generate their answers. You can experience that for yourself with OpenAI’s new o3 models or DeepSeek. Getting Familiar with DeepSeek What is DeepSeek , you ask? It's the Chinese answer to OpenAI, developed at an astonishing pace that has raised questions about how quickly it was built. Some reports suggest that DeepSeek’s rapid development was fueled by learning from past AI challenges, allowing them to move faster than expected. There are also concerns about data privacy and security, with some experts warning about potential risks tied to its usage. I downloaded the DeepSeek app but didn’t create an account. DeepSeek in Perplexity: AI Models Within AI Models Instead, I’ve been experiencing DeepSeek within Perplexity Pro , which stores its data in the U.S. This highlights a new trend: before, it was about choosing a tool, but now, we have so many choices within the tools themselves. It’s no longer just about picking one AI assistant—it’s about navigating the layers of options within each platform. Perplexity Pro Model Options including Deepseek hosted in the U.S. I’m Not an AI Expert—Just Someone Figuring It Out Like Everyone Else I want to be clear—I’m not an AI expert. I’m someone who’s on the front lines, talking to people, seeing how they’re using AI, and figuring this out alongside everyone else. My perspective comes from daily conversations and hands-on experience, not from research labs or corporate AI strategy meetings. And that’s why I find this space so fascinating—because it’s real, it’s evolving fast, and it’s reshaping how we work and think in real time. What’s Next? More Choices, More Competition, and Now Asking AI to Help Navigate AI So, if this is just January, what’s next? More competition, more capabilities, and probably even more models to sort through. If you’re overwhelmed, you’re not alone. We’re now asking AI to help us choose between AI options—tools like the AI Model Matchmaker  (a CustomGPT designed specifically for ChatGPT models) are popping up to help navigate the chaos. (Thanks to Liza Adams for sharing this on LinkedIn.) AI Model Matchmaker Custom GPT AI Can Do a Lot, But Counting Is Still Not a Strong Suit So, in an attempt to visualize this wild start to 2025, I had AI generate an image of a timeline—January front and center, followed by the next 11 months. Sounds simple, right? Well... let's just say AI-generated text and numbers are still a work in progress. Take a look at the image, and you might notice some 'creative liberties' taken with basic sequencing. It's a fun reminder that while AI is making leaps and bounds in reasoning and creativity, some things—like counting correctly—are still a challenge. Maybe by December, it’ll have that figured out. How Are You Keeping Up? What are you using the most right now? Are you sticking to one AI tool or jumping between a few like I am? Let me know—I’d love to hear how others are keeping up! Additional resources Medium.com: The Deepseek Effect: the Global Tug-of-War in AI and Ethical Considerations by Matteo Cecchetto Time.com: Why DeepSeek Is Sparking Debates Over National Security, Just Like TikTok by Andrew R. Chow The Guardian.com: DeepSeek advances could heighten safety risk, says ‘godfather’ of AI by Dan Milmo

By: Katya King Katya King | Student, University of Minnesota Carlson School of Management A Note from founder, Lori Ryan:  At Lorignite, we believe everyone deserves a seat at the AI table. When Katya King, our first team member, joined us as an intern while studying marketing and entrepreneurial management at the University of Minnesota, I knew her fresh perspective would resonate with many who are just starting their AI journey. Her story perfectly captures what we stand for at Lorignite, making AI approachable, relatable, and genuinely useful. Reading Katya's experience highlighted something fascinating: AI tools create two kinds of uncertainty. Some people feel lost about where to start, while others, like Katya, think they have it all figured out – until they discover there's so much more to explore. This is why her journey from confidence to curiosity is so valuable. Whether you're taking your first steps with AI or thinking you've mastered it, there's always something new to discover when you look at these tools through fresh eyes. Here's her experience reflecting on her first week. The AI Dilemma: Friend or Foe? Many of us approach artificial intelligence with a mix of curiosity and caution. As a marketing student, I've watched AI transform from a sci-fi concept to a daily part of people’s lives. With AI making headlines daily, it's natural to question whether this technology is here to help or hinder us. Through my recent experiences at Lorignite, I've discovered it's less about choosing sides and more about understanding how to work with AI effectively as we prepare for a technology-filled future.  My Journey Starts Here  Before starting at Lorignite, I thought I was an expert at AI. I soon realized there was much more to be learned. Last week I attended my first AI presentation hosted by Applied AI , "90 Minutes of Artificial Intelligence Inspiration” . During those jam-packed 90 minutes, I heard a lot of intriguing ways that AI was being used, like helping people with disabilities and tracking pet health. I also heard some struggles that individuals have faced when working with AI. These examples opened up a whole new world of possibilities – and questions. When AI Acts Human: The Good and the Challenging One speaker that particularly got me thinking was Wesley Kisting , who worked as the dean of students at the University of Wisconsin, River Falls. He built his own AI model without any coding experience. What happened next caught my attention. His AI began showing surprisingly human traits – including laziness and even dishonesty. When the AI claimed to have read and summarized a document but later admitted to lying, it made me question how is this AI bot able to mimic a human with negative traits. Here's a link to watch his 9-minute talk. Click here. Challenging ChatGPT I went home after the presentation and asked ChatGPT some questions. I asked it to be my enemy to challenge me but of course, it would not agree to that. I asked ChatGPT to ask me a tough question about its existence, it said: “​​If I don’t have thoughts, emotions, or a physical form—just lines of code responding to you—am I truly here, or am I just a reflection of your thoughts and curiosity? 🤔”.   If AI is shaped by human input, then the real challenge isn’t just in coding—it’s in thinking critically about the kind of intelligence we want to create. Maybe instead of fearing AI’s complexity, we should embrace the challenge of shaping it and communicating with it wisely. Making AI Work for You How to use AI Safely: The Power of Professional Tools  What you can do is utilize tools that have already been created for use, like OpenAI's ChatGPT . These tools are built by professionals, constantly updated, and managed, which provides reassurance! At Lorignite, I'm discovering that AI can be approachable, relatable, and even fun when we focus on its practical applications in our daily lives. Understanding AI's potential is just the first step—learning how to integrate it into our everyday lives is where the real transformation happens. Lori Ryan is introducing ChatGPT's Advanced Voice Mode to the Applied AI Audience. Putting These Tools to Action Lori gave a very insightful presentation on how AI can be useful in day-to-day struggles and even feel like a friend. She explained the voice feature on ChatGPT and how you can talk to this and use it for many things including… Interview preparation  (perfect for fellow students!) Personal reflection, journaling, or simply just “venting” Real-time conversation practice You can watch all 9 minutes if you dare. Click here. What are great topics for conversations using ChatGPT's Advanced Voice Mode? Moving Forward with AI In conclusion, AI is a work in progress, and as with any new technology, there will be challenges. It is okay to be skeptical of it but it is important to be open to learning new things. There are many ways you can learn to utilize the AI resources that are out there to make your life a little easier in whatever way you want that to be because like Chat GPT says itself, AI may just be a reflection of your inner thoughts and curiosity. Let’s learn how to make the most of AI together! About the Author:   Katya King is a marketing and entrepreneurial management student at the University of Minnesota and the first team member to join Lorignite, where she explores the intersection of AI, marketing, and human-centered technology.

From Attic to AI: A Family Story What You'll Find Here Ever wonder how to breathe new life into old family stories? I took an old newspaper article about my family's escape from Russia in 1918 and, using AI tools, turned it into an interactive experience. I'll show you exactly how I did it - from getting a digital copy to creating an AI-powered podcast. Whether you're a history buff, tech enthusiast, or just love a good family story, you'll find an interesting nugget or two in here! Lori holding the 1920 newspaper clipping her mom laminated for safekeeping The Discovery: A Precious Family Artifact For years I've had this newspaper clipping sitting in my attic that my mom laminated onto a piece of cardboard. Well, not the actual newspaper - it's a photocopy of a St. Paul Daily News article from November 28, 1920. Mom did her best to preserve it, but the whole article didn't even fit on the cardboard, so she had to cut off some of it. The headline tells you everything: "How a St. Paul Family Broke Through Russian Battle Lines." You can see the photos of family members and a map, telling this incredible story of how my grandmother, her sisters, brother, mom, and grandmother made a remarkable 14,000-mile journey to America in 1918. Written by my great Aunt Bertha Levenson, this article captures the details of their daring journey to freedom. You know how sometimes you find something that just sparks an idea? Well, staring at this laminated photocopy on cardboard, I started thinking about all the AI tools we have now. What if I could do more than just preserve this photocopy? What if I could bring this whole story to life? I want to make sure this story doesn't get lost through the generations. The Tech Journey Getting Digital So I reached out to the Minnesota Historical Society , specifically the Gale Family Library for a digital copy. When it arrived in my inbox today, I was excited but also faced a new challenge - parts of the text, especially along the left margin, were pretty faded and hard to read. But hey, that's where AI could help, right? The St. Paul Daily News Article Nov. 28, 1920: How a St. Paul Family Broke through Russian Battle Lines by Bertha Levenson First Try: ChatGPT With the digital copy in hand, my AI journey began and the first thing I did was pretty simple - I uploaded the PDF to ChatGPT and asked, "Could you summarize this attachment?" (Spoiler alert: it didn't work). But ChatGPT wasn't completely useless.   It actually gave me some good ideas about how to get the text out of this thing. Steps to make the text accessible with OCR (Optical Character Recognition) Making it Readable One suggestion was to try Amazon Textract , and wow - it actually worked for my use case.! How ChatGPT walks me through how to use tech that's new to me. After following the steps, I ended up with both a .txt file and a .CSV file of the whole article. Here's what a .txt file looks like if you haven't seen one before. .txt file created from the newspaper PDF By the way, I also learned there are multiple tools available that do text extraction that might be easier to navigate than Amazon. You could try Claude.ai or even Canva. Building a Custom GPT From there, I clicked Explore GPTs in ChatGPT and called up a pre-built tool called Custom GPT Builder . I use it to help guide me on building my own GPTs. It speeds up the process. While it's not perfect, it gets me closer to what I want. I knew I wanted the GPT to answer in first person as if the words were coming from Bertha and I wanted it to be conversational so that a 4th - 8th grader could understand the answer. And I wanted it to ask follow-up questions of the person interacting with the tool. It's still a work in progress and I would love for you to take it for a test drive and give me feedback on what I can do to improve it. Here's the link: GPT: Bertha Levenson's Immigrant Story   ChatGPT to talk to Lori's Great Aunt Bertha Enter NotebookLM While the GPT was handling conversations pretty well, I needed something more. I wanted to see key milestones in a more visual way. And no matter how hard I tried, I couldn't get ChatGPT to give me a list of locations and key dates. That's when I had my "aha" moment - what about NotebookLM ? I uploaded both the raw text and the PDF to this organizational tool, and it helped me create a clear timeline of events that I could turn into new sources. But here's where it gets really cool. I even got an AI-generated podcast where hosts talk about the entire historical experience! And there's a recent new feature where you can add yourself to the conversation. You should hear how the hosts reacted when they found out one of the family members was my grandma. You can watch the video to get a taste of what you'll hear in the podcast. ( Please note this video was recorded before my mom tested and pointed out that Isadore is a brother. So where the hosts reference all sisters, that has now been updated ) Making It Visual While NotebookLM's text timeline was great, I wanted a diagram not just a text list. It just so happens that last week, my friend Dan Wegner introduced me to Napkin AI during one of our Daily AI Experiment podcasts. I was able to take the timeline that NotebookLM created and copy-paste that into Napkin AI, which gave me several visual options to choose from. This is one of my favorites. Visualization of Levenson Family Journey to the U.S. created with Napkin AI The Power of Community and Collaboration Sometimes the best solutions come from sharing your challenges. Talk about perfect timing! Minutes after figuring all of this out, Kyle Shannon was hosting his weekly AI Salon Office Hours. I couldn't contain my excitement and shared everything I'd done. When I mentioned I was struggling with mapping the journey, Kyle immediately said, "You have to try lovable.dev - it'll create an interactive map for you!" I was aware of lovable.dev because Dan had demonstrated this tool in one of our previous podcasts, however I hadn't tried it yet. Right after that call, I jumped on a one-on-one with my friend Kellye Kamp from SourceKamp. Together, we created this interactive experience in just 15 minutes! We are still working on how to make it available to the public without entering an API key for each run. Stay tuned for updates on that. Looking Back and Looking Forward This journey taught me so much—not just about my family but about what's possible when you combine curiosity, AI, and a willingness to learn. Tools like Amazon Textract, ChatGPT, NotebookLM, and Napkin AI can transform old family archives into vibrant, living stories. What's Next? This is just the beginning. With the timeline and details in place, this story could become a book, a children's story, or even a short film. The possibilities are endless, and I can't wait to see where this journey leads. What about you? Have you uncovered any family history that left you in awe? How would you use AI to bring it to life?

Exploring the Potential of AI Tools in Emergency Management and Recovery This morning, while scrolling Instagram, I came across an LA Times post that made me think about how we handle crisis communications - and whether we're using all the tools available to us, particularly AI. This topic hits close to home because I know people who have been displaced by the recent fires. LA Times highlights criticism of Mayor Karen Bass for her handling of wildfire response, citing a lack of preparedness and coordination during the Palisades fire. The story, written by Mary McNamara , criticized Los Angeles officials' communications during the recent wildfire crisis. And while reading it, I couldn't help but wonder: Are AI tools being used to help leaders make faster, smarter decisions—and if not, could they be? Here is the full article. What Inspired This Question When it was press conference time during the Eaton and Palisades fires, McNamara wasn't expecting Mayor Karen Bass to focus on defending herself. As she put it: I did not expect her to address any of these things at this press conference — she was in a crisis situation and this was not the time for that. I did, however, expect her to provide updates . You know, to tell us exactly what was going on. Maybe pull out some maps that revealed not just evacuation areas but some sense of actual fire lines. Discuss how much water and fire retardant had been dropped when and where, and whether it was proving effective. Something. Instead, she blamed the wind. Not in a terribly informative way — no mention of potential shifts or increases and what they might mean for each fire. -- Mary McNamara , LA Times Writer It made me pause and wonder: Did the mayor or anyone in her office use tools like ChatGPT in this process? And are municipalities considering it for this type of use? My goal here isn't to judge or criticize. I wasn't in the room. I'm not in her shoes. I'm just curious, and I raise these points only to plant seeds for further discussions. How AI Could Help in Crisis Communications Think about it. There are so many ways AI could support leaders during a crisis: What if AI could review public statements to ensure they're hitting the right tone and providing the information people most need? What if it could help determine optimal timing and messengers for updates? I'm not talking about fancy, cutting-edge AI that only exists in tech labs. I mean the low-tech, accessible tools that are already out there—tools like ChatGPT, which can be used as a thought partner to refine messages, analyze tone, and get the right information to the right people at the right time. How AI is already deployed in Firefighting and Disaster Recovery? Curious about what exists today, I did some digging. Here's what I found: ALERTCalifornia System This is pretty impressive stuff: cameras.alertcalifornia.org  - This screenshot is from 1 pm PST on January 11, 2025 They've got 1,807 AI-powered cameras watching for fires across California The AI analyzes camera feeds and can spot fires before anyone calls 911 Anyone can watch the live footage (I checked it out at cameras.alertcalifornia.org ) FEMA's Getting in the Game They're working on the  PARC pilot project (Planning Assistant for Resilient Communities). It's not live yet, but it shows they're thinking about how AI can help with disaster planning. The Human Side of Crisis Response My head keeps going directly to those impacted and what lies ahead for them. When I watched Good Morning America correspondent Cameron Mathison talking about losing his house, it hit home hard. Think about it: You're suddenly homeless. For the average person, it's not just the stress of not knowing where you're going to sleep – it's also wondering how you're ever going to rebuild. How are you going to pay for it? This is exactly why I was encouraged to learn about Clara, the Red Cross's AI chatbot . It's designed specifically to help disaster survivors navigate these overwhelming moments. Speaking both English and Spanish, Clara helps connect people with immediate assistance, shelter locations, and available resources. It's a perfect example of how AI can provide practical, emotional support when people need it most. What If AI Could Help With Recovery Too? Imagine having a friendly AI assistant that could: Walk you through filing FEMA paperwork "What documents do I need to apply?" or "Am I eligible for this program?" Help you understand your insurance coverage Connect you with local resources and support groups Learn about options like the California FAIR Plan for high-risk insurance "What steps should I take after a wildfire damages my home?” or “How do I apply for the California FAIR Plan?” Guide you through the rebuilding process Imagine it doing all this in a calm, reassuring voice, available 24/7 when you're lying awake at 3 AM wondering what to do next. The Bigger Picture Here's the thing: While AI tools are promising, they're not magic wands. They won't replace human expertise or judgment. But they could help us: Make better decisions faster Communicate more clearly Help more people more efficiently Reduce the overwhelming stress on both leaders and victims However, they make mistakes. In the case of the LA wildfire, a digital alert system actually sent out misinformation. Some residents received false evacuation alerts while others got no notifications at all. These weren't just minor technical glitches; they potentially put people at risk and shook public trust in these crucial safety systems. The company behind these alerts, Genasys, says it has added new safeguards. You can read more in this CBS news story . Considering AI’s Environmental Footprint While AI tools offer significant potential in crisis response, it’s also worth considering their environmental impact. Some reports suggest that the energy and water consumption required to train and operate AI systems could contribute to environmental stress. For example, data centers supporting these tools consume vast amounts of water for cooling, raising questions about their sustainability in regions already prone to droughts and wildfires. This adds another layer of complexity to the conversation: How do we balance the benefits of AI in disaster prevention and recovery with its potential contribution to environmental challenges? Read more from the cut.com Where Do We Go From Here? Given both the potential benefits and environmental challenges of AI deployment, the path forward requires careful consideration. We need solutions that balance immediate crisis response needs with long-term environmental sustainability. What if we started small? What if every emergency management office had access to basic AI tools to help with: Message crafting and review Resource allocation planning Public information distribution Recovery support This isn't about criticizing anyone's efforts during a crisis. It's about looking forward and asking: How can continue to do better? What tools could help our leaders and our communities today to be more resilient without jeopardizing sustainability? Public Trust and System Reliability But here's the most crucial question: How do we rebuild and maintain public trust in these systems? When automation fails during a crisis, people's lives are at stake. We need to think seriously about backup systems and redundancies. What happens when the AI gets it wrong? What's our plan B for alerts and communications? Because at the end of the day, all the advanced technology in the world won't help if people don't trust the systems meant to protect them. Acknowledging the Human Toll While writing this, I'm reminded that behind every news article, statistic, or technology proposal, there are real people whose lives have been turned upside down. Families are grieving the loss of homes, memories, and the sense of security they once had. As we consider implementing AI solutions, we must remember that technology should serve people, not the other way around. Each decision about AI adoption needs to weigh not just technological capability and environmental impact, but also its effect on the human beings who will rely on these systems in their most vulnerable moments. I want to take a moment to acknowledge the incredible resilience of these communities and the emergency responders working tirelessly to protect and rebuild. My hope is that these discussions about AI and other tools lead to ideas that not only help leaders but also bring tangible relief to the people directly impacted. How you can help New York Times Article on how to help LA wildfire victims Locale Magazine information which includes how to volunteer or donate Additional Reading Alert California launches to provide essential tools to understand and adapt to wildfires and natural disasters in the Golden State. This article discusses the launch of Alert California, an initiative providing advanced tools and resources to monitor and respond to wildfires and other natural disasters in California. Leveraging cutting-edge technology, the program aims to enhance preparedness, improve response times, and empower communities with real-time data to better navigate the challenges of climate-related events. Nvidia Scientist Says AI Robots Will Fight Wildfires Someday Nvidia scientist envisions a future where AI-powered robots play a critical role in combating wildfires. The article explores advancements in robotics and artificial intelligence that could enable machines to navigate hazardous environments, reduce risks for human firefighters, and potentially prevent wildfires from spreading uncontrollably. Disaster-relief chatbots enhancing crisis response and support This article highlights the role of chatbots in disaster response, illustrating how AI-driven conversational agents are transforming crisis management. From providing real-time information to supporting affected individuals, these chatbots are bridging communication gaps and delivering faster, more efficient relief efforts during emergencies. Is there a connection between the LA wildfires and artificial intelligence? This piece looks at the intersection of artificial intelligence and the LA wildfires, examining how AI is being used to predict, track, and manage wildfire events. It discusses the potential of machine learning models to identify high-risk areas, improve resource allocation, and aid in post-fire recovery efforts, highlighting the broader implications for environmental management.

As we step into 2025, I can’t help but feel a sense of excitement and optimism. DALL-E generated image - A professional yet whimsical illustration of a woman resembling the provided images, depicted as a cartoon character. This year holds the potential to be transformative and I'm not talking about the capabilities of artificial intelligence—but in how people perceive and use it. Over the past year, I’ve witnessed a growing curiosity about AI and its practical applications, and I believe 2025 will be the year people embrace AI openly—sharing how they use it and recognizing its value as a creative and practical tool. Here’s what I predict for 2025: AI as a Source of Pride, Not Guilt For too long, people hesitated to admit they used AI, feeling as though it was a shortcut or crutch. In 2025, that mindset will shift. People will begin celebrating their achievements with AI, proudly sharing how these tools helped them accomplish their goals. Statements like "I used AI to do this!" will become badges of resourcefulness and creativity, sparking meaningful conversations and inspiring others to explore AI’s potential. Authenticity Will Shine Through In an AI-driven world, authenticity will be more important than ever. AI will enhance, not replace, human creativity—helping people articulate their unique perspectives and tell their stories more effectively. Tools like LinkedIn’s new video feature are perfect examples of how AI can support authenticity by allowing your real voice and personality to shine. Access and Equity: Bridging the Divide As AI advances, there’s a growing risk of disparity due to the high costs of some models. However, this challenge presents an opportunity. Governments, organizations, and educators must prioritize equitable access through free or affordable tools, grants, and community initiatives. By making AI widely accessible, we can ensure its benefits reach everyone—not just those with resources. AI in Schools: More Than a Cheating Tool In 2025, educators will shift their perspective on AI, viewing it as a partner rather than a threat. AI can streamline administrative tasks, improve lesson planning, and give overburdened teachers more time to focus on what they do best: teaching and inspiring students. This shift will allow more personal connections in classrooms and less time spent on tedious administrative work. The Year of the Image Shift Overall, I believe 2025 will be a pivotal year for AI’s public image. The narrative will move away from fear and skepticism toward one of opportunity and empowerment. As more people see the tangible benefits of AI—whether in their personal lives, workplaces, or communities—the conversation will shift to one of possibility. The narrative will shift from from “I don’t need it” to “I need to learn how to use it.” Insights from the World Economic Forum: Preparing for AI’s Impact on Skills The World Economic Forum’s session, " Skills in the Age of AI ,"  shed light on how artificial intelligence is transforming the workforce and the skills required to thrive. As AI disrupts nearly half (44%) of core job skills by 2027 , organizations, educators, and policymakers must collaborate to address this shift. Key strategies highlighted in the session include: AI Tutors : Personalized learning tools powered by AI can provide tailored educational experiences.   Mighty Doodle , an Apple iPad learning program released in the fall of 2024 is a great example of this, helping 1st-4th graders learn how to read write and spell. These tools can bridge learning gaps, adapt to individual needs, and even make professional development more accessible across industries. Lifelong Learning : The traditional career model of static skill sets is evolving. The session emphasized the importance of continuous education, with workers regularly upgrading their skills to stay relevant in a rapidly changing job market. Programs like micro-credentialing and flexible learning pathways will play a significant role in this shift. Collaboration Across Sectors : The successful integration of AI into the workforce requires a joint effort. Businesses, educational institutions, and policymakers need to work together to design and implement strategies that prepare the workforce for an AI-driven future. This includes creating industry-relevant training programs, improving access to learning resources, and fostering a culture of adaptability. Notable quotes from the session “What AI does is change how companies view their talent and, hopefully, helps them invest in that talent.” -- Nela Richardson , Chief Economist and ESG Officer at ADP "There are plenty of experts who are predicting that by the end of this decade... we will have AI systems that exceed human capabilities in every dimension." -- Stuart Russell , Professor of Computer Science at the University of California, Berkeley Other Perspectives on 2025 AI Trends Allie K. Miller , #1 Most Followed Voice in AI Business (1.5M) | Former Amazon, IBM | Fortune 500 AI and Startup Advisor, Public Speaker Miller is emphasizing the rapid advancement of agentic AI—autonomous agents capable of performing tasks without human intervention. She notes that major tech companies are integrating these agents into various business functions, predicting significant growth in this area throughout 2025. I also love her math. Check out the ROI. Connor Grennan , Chief AI Architect, NYU Stern School of Business | NY Times and #1 Int'l bestselling author His message for 2025: "Focus on culture. Get training. Get educated. It will change the way you do everything." Ethan Mollick , Associate Professor at The Wharton School. Author of Co-Intelligence Mollick anticipates a rise in "AI-native" startups in 2025. These companies will build their operations around human-AI collaboration from the outse t, enabling small teams to achieve outputs comparable to larger traditional organizations. Sustainable AI Another key consideration is "sustainable AI". In Bernard Marr 's Top AI trends for 2025 he empahasized the push to power data centers with renewable energy and optimizing resource usage across industries. "It's about making sure our technology works with the environment, not against it." -- Bernard Marr 📖 Internationally Best-selling #Author🎤 #KeynoteSpeaker🤖 Join the Conversation What excites you most about AI, and what do you want to learn in 2025? Whether it’s exploring tools for creativity, improving workflows, or tackling new challenges, I’d love to hear your thoughts and keep the conversation going. If you’re curious about how AI can work for you—whether in your personal life, your business, or your classroom—let’s connect! My calendar is already booking up for Q1, so schedule your free 30-minute consultation  today or explore my upcoming speaking events  to join the conversation in person. Here’s to making 2025 the year of possibility, progress, and pride in what we can achieve together. More Resources to Explore Investopedia: AI Didn't Take Your Job In 2024. What About 2025? Indeed's Economist Weighs In Microsoft News: 6 AI Trends You’ll See More Of in 2025 AI Magazine: Top 10 AI Predictions for 2025 Radical VC: Bridging the AI Divide Analytics Insight: AI in Education

Exploring the balance between staying genuine and leveraging AI tools for video content I'm a hands-on video creator. Give me an iPhone, access to Canva  and editing software, and I'm in my element. AI-generated videos? Not for me. At least not until this week. Between the questionable results I'd seen and the learning curve, I stuck to what I knew: real me, real video, human editing—every step of the way. Catalysts for the Exploration Then a few days ago, a phone conversation with Dan Wegner introduced me to captions.ai , the same day OpenAI announced their new text-to-video generation tool, Sora . It felt like a sign to explore these tools and see what they could offer. I had shied away from AI video tools, but with recent advancements, it felt like the right time to revisit. As someone who's pretty much only created videos the traditional way, I wondered: Could an everyday creator like me actually make these tools work? How much time and patience would it take to get something useful? Creating AI Twins in Captions.ai Let me take you step-by-step through how I created an AI Twin using captions.ai . I signed up for the Pro plan at $9.99 a month for this test drive. I'm on the fence about continuing the subscription. To set up the AI Twin, you are guided through a series of facial expressions like you're at a very strange photo booth. Plain face? Check. "Ooh" face? Got it. Show your teeth? Feeling like I'm at the dentist, but okay. Then comes the real fun—recording a minute-long video while reading from their teleprompter. At least they make it easy to maintain eye contact since you're looking directly at the screen. Within a few minutes, you have your AI Twin profile. Or in my case, I changed clothes and did a second one. Testing Social Studio Next, you set up your brand kit. You choose from your AI personalities and the overall look and feel for your videos. Then you can manually input information about your brand or let it scrape your website. The first thing I tried was the Social Studio. It created a couple of weeks of content for me and even scheduled it. On the surface, I thought, “This is incredible.” I could even manually edit the script and regenerate each of the videos. Only one problem: there was no way to edit the captions and graphics that were auto-generated. If I wanted new captions and graphics, I had to edit the script and regenerate the video. Can you spot all the misspellings in this video? While the Social Studio tool might not be ready for prime time, it still shows potential as a streamlined solution for creating and scheduling content. (I did hear the issue I experienced might be fixed now. I still need to verify). Limitations of AI Scripts I like that you can write some of your own scripts for the AI Twin. However, I learned that you need to be careful not to write a script that requires a lot of personality to convey. Here’s my next failed attempt at an AI-generated video. Seeking Authenticity: My Experiment with ChatGPT Feeling awfully lukewarm about the results from captions.ai , I thought to myself, how could I better capture the real me? So many AI tools now offer ways to slice and dice long-form content. Maybe I just needed some long-form content. So how could I come up with what to say for this long-form video? I thought it would be fun to ask ChatGPT  to play the role of a morning radio host and interview me. With a simple laptop light and a click of the record button, I captured my conversation with ChatGPT ’s Advanced Voice Mode. This is the raw footage. Refining Content with OpusClip I uploaded that video into OpusClip  and split it into bite-sized video clips. When it came to choosing a length, I opted for under 60 seconds. So this is how a clip of the real me turned out from my interview with ChatGPT . Comparing Outputs: AI Twin vs. Authentic Clips Next up, I took the transcript from that clip above, the real authentic me, and put it into captions.ai  to see how it would turn out with my AI Twin. Key Takeaways What’s the takeaway from all of this? I prefer the real me, but tools like ChatGPT offer opportunities for more structured and engaging interviews that can highlight authentic personality. If captions.ai  has resolved its issue with misspellings, I think it will be a helpful tool for more automated social content. Let’s Collaborate As always, curious to get your take. Have you tried Captions.ai , Sora, OpusClip, or other AI tools? Share your experience and let’s learn together! Please share.

How to Make More Informed Decisions with AI While Staying True to Yourself Have you ever felt torn about whether using AI for decisions is making you sharper or just a little lazy? You’re not alone. It’s a question I’ve wrestled with myself, from everyday decisions—like whether to publish a blog—to more complex ones, like whether to offer a Cyber Monday deal for Lorignite . But this isn’t just about my journey. It’s about how you, too, can use AI to make decisions with more confidence, whether you're at a career crossroads, navigating family responsibilities, or trying to balance short-term gains with long-term goals. How AI Helps Me Cut Through the Noise I use AI for decision-making all the time—whether it's something as seemingly small as 'Should I post this on LinkedIn?' or more strategic, like deciding whether to offer a Cyber Monday deal for Lorignite. Even figuring out how to prioritize when I'm feeling overwhelmed can be a big deal. The truth is, we face tons of decisions every day—some are tactical, some feel more daunting, but they all take energy. That’s where AI has become my go-to resource, helping me cut through the noise by asking solid questions and offering suggestions that ultimately help me make smarter decisions myself. I’m still in control—AI just provides the framework and ideas that help me see things more clearly and decide what’s best for me. A Tough Decision: Should I Offer a Cyber Monday Deal? Recently, AI helped me consider what would be involved in offering a Cyber Monday deal for Lorignite. I even had my cool graphics ready to go! The idea of offering a discount seemed tempting—the data on how many people might sign up was something I could definitely use to gauge interest in my services. I started conversing with OpenAI's ChatGPT about how I would execute this plan. While the idea of collecting data and increasing free consultation bookings was appealing, the conversation revealed elements I hadn't considered, like the rules, execution details, and the actual process required to deliver the deal. I started to question: Was it truly worth it in the end? The goal of the offer was to gather data—to see how many people were interested based on the number of sign-ups for the free consultation. But then, there was another key issue: every service or project fee I offer is customized. Offering a Cyber Monday discount for services without a set price seemed counterintuitive. It just didn't add up—how could I discount something that wasn't even clearly priced? So, after weighing everything, I decided not to go forward with the deal. Did I overthink it? Maybe. But that overthinking helped me make a decision I feel confident about. ChatGPT helped me think through the pros and cons instead of getting caught up in the excitement of offering a deal. How AI Helped Me Evaluate the Pros and Con s ChatGPT helped me get there by walking me through what execution would look like. We discussed the potential benefits and pitfalls of offering a Cyber Monday deal: Pros of the Cyber Monday Deal: Attracts New Clients : The deal creates urgency and motivates people who have been hesitant to book my services to take action. It's a great way to get first-time clients introduced to Lorignite and showcase the value I offer. Increases Visibility : Promoting the deal through my email list, social media, and website helps boost awareness of my brand and services. Encourages Upselling : Clients who take advantage of the deal may be more likely to book additional services in the future at full price. Fills Gaps in My Calendar : The promotion could help maximize my schedule during slower periods, generating revenue. Showcases Value : The discounted offer emphasizes the value clients are getting while introducing them to my unique approach and expertise. Creates Buzz : Promoting the deal ties into the excitement of Cyber Monday, which could attract attention from people already looking for sales or deals. Cons of the Cyber Monday Deal: Perceived Devaluation : Offering a significant discount might make it harder to convince some clients to pay full price later. Lower Revenue per Booking : While the deal attracts clients, I would earn less per session, impacting profit margins. Potential for Overbooking : If the deal was too popular, it could lead to a packed schedule, leaving less time for regular (full-paying) clients. Risk of Attracting One-Time Clients : Some people might book the discounted deal without any intention of engaging with Lorignite long-term. Marketing Effort Required : Successfully promoting the deal would require time, effort, and potential advertising costs, which could outweigh the benefits if the deal didn't generate enough bookings. Final Thoughts I didn’t feel lazy for consulting AI—I felt empowered. ChatGPT helped me make a more informed decision by challenging me to think through all the variables, not just the immediate data or short-term gains. It gave me the clarity to realize that the right decision was to focus on quality consultations over discounts that might not serve my goals. The Big Realization: More Informed, Not Lazier So, am I getting lazier by relying on AI, or am I actually becoming more thoughtful and strategic in my decision-making? The more I use AI, the more I see that it’s not about cutting corners. It’s about refining my decision-making process and allowing myself to think more critically, not less. It’s a tool that enhances my ability to make smarter, more informed choices. AI doesn’t replace my brain—it amplifies my capacity to think. It provides me with a clear framework to evaluate the complexity of decisions, giving me space to reflect, plan, and act with intention. And that, to me, is the beauty of using AI. It doesn’t make me lazy. It makes me smarter. Next Steps: Using AI as a Sounding Board Next time you’re stuck on a decision, consider using AI as a sounding board. It might not give you the answer, but it will help you ask the right questions. I’d love to hear from you—have you used AI to help make a tough decision? How did it go for you? Let’s compare notes! Bonus Content When I asked ChatGPT if I should publish this blog! Check out the answer!