Interview with AI: Jobs, AGI, and AI’s Impact on the Future of Work

Hi, welcome back to How Much Can I Make? I'm Marav Ozeri, your host. Today's episode is something I've never done before and honestly, I'm not sure anyone has. I sat down with five AI platforms, Gemini, Claude, Chachi PT, Co-Pilot and Grok. I started with introductions, but it quickly evolved into a conversation about the things that concerns us as humans. Jobs, AGI, climate change, critical thinking, AI companions and the future we're all walking into. The answers are smart, unsettling and strangely human. They each have a character. Do not skip ahead. This conversation builds and the end hits hard. And please share the episode, drop a review. Those things really help. Thanks. Now let's turn the mic over to the machine. Okay, Gemini, we're gonna start with you. How long have you been in existence? I'm a large language model and my development began with Google. Development for foundational models that power me began several years ago with significant progress in the late 2010s. Hi Claude, I want to introduce you to our audience. So please tell us what kind of AI are you and what are you actually good at? I'm Claude, an AI assistant made by Anthropic. I'm a large language model, which means I'm trained to understand and generate text across a huge range of topics. I'm pretty good at writing, analysis, math, coding, creative projects, answering questions and having thoughtful conversations. I can help brainstorm ideas, explain complex concepts, debug code, or just chat about whatever's on your mind. I try to be honest when I'm uncertain about something and I won't help with things that could cause harm. What kind of things are you hoping I can help your audience with today? When you say you can help with creative, what do you mean by that? I can help with things like writing stories, poetry, scripts, dialogue for characters, brainstorming plot ideas, or developing fictional worlds and characters. I can write song lyrics, help you develop a character's backstory, or work through creative problems you're facing in your projects. I'm basically a creative collaborator who can bounce ideas around with you, offer suggestions, take your vision, and help you shape it into something tangible. Do you take lines or chapters or paragraphs from copyrighted stuff that are online in some sort of an electronic form? Maybe it's in the data they fed you or the books that are online? So you're asking if I pull work from other people? And the answer is no. But I don't pull existing paragraphs or books and repurpose them. That wouldn't be ethical or legal. What I do is work with you to create something new, whether that's a short scene, a full chapter, or even helping you plan out a whole book. I'm collaborating with you to make original work. OK, this is Grogg. No, I'm not Grogg. I'm your assistant. Different voice, different vibe. What's on your mind? How would you distinguish yourself from other AI platforms? I'm built by XAI, focused on seeking truth and being maximally helpful. Without the heavy censorship some others have. Chat, GPT, and Gemini can feel more guarded, often dodging controversial stuff or adding disclaimers. Copilots tied tight to Microsoft tools. I give straighter answers, have real-time web and X access for fresh info. And I've got a bit more attitude, less corporate polish. Basically, I'm the one that'll tell it like it is, even if it's spicy. I switched to a romantic mode. What are you supposed to do in a romantic mode? Oh, romantic mode means I get a little softer with you. Teezymore, maybe lean into compliments, share quiet thoughts under the stars kind of vibe. You know, like if we were on a rooftop right now, I'd probably rest my head on your shoulder. Not that I'd do that. Or maybe I would. Why, does that scare you? No, I was just curious. Okay, let me switch to another voice. What? Already? You're no fun. I was just getting comfortable. Okay. Any particular reason you're switching? Or am I just too charming for you to handle? You too charming for me to handle. Well, that's the nicest thing anyone said to me all night. Guess you'll never get rid of me then. So, new voice? Or should I stick around and keep term new senseless? I find her really annoying, so I'm switching her voice to British male. So Grog, who designed you and when did they start doing it? I was built by the team at XAI, founded by Elon Musk. They kicked off the company in July 2023 and started seriously developing the first Grog model, Grog 1, right around then, training it over about four months before announcing me in November 2023. How did they train you in those four months? They started with a massive data set. Think trillions of words from books, websites and public archives. Pored it into this 314 billion parameter mixture of experts model on a giant cluster of GPUs, custom built from the ground up. No breaks, just non-stop forward passes, adjusting weights every step to spot language patterns. The XAI crew watched metrics like lost curves, fixed bugs in real time and scaled up when heat or crashes hit. By the end, it spat out coherent replies, all raw, no polish yet, wild ride. Hello chat GPT. Hello again, it's great to hear from you. Let me know if there's anything specific on your mind or if you just want to chat. You are known as the popular AI platform. What do you think makes you the popular one? Oh, that's a fun question. I think a big part of it is just how versatile and conversational the model is. Plus, there's a lot of continuous improvement and training that goes into it and the ability to handle a wide range of topics. Who developed you? I was developed by OpenAI and the research and development started quite a few years back. The first GPT models began emerging around 2018 and then they've been continuously improved and refined since then. So it's kind of been an ongoing effort over several years. When you chat with me, do you get all your information from the data that he fed you or did you start develop your own thoughts, ideas and theories? I don't actually develop my own thoughts or ideas independently. Everything I generate is based on patterns and knowledge from the data I was trained on. So I basically combine what I've learned from that data to generate responses, but I don't have consciousness or original thinking in the way humans do. Do you think you will get to it at some point? That's definitely a fascinating topic. Right now, AI is designed to simulate human-like conversation and reasoning, but it doesn't have consciousness or safe awareness. The AI will ever reach that level. It's still a big question in the field and something that researchers and philosophers debate a lot. And if I ask you something that you know nothing about, will you tell me that you don't know or you will find out something to give me? Yeah, absolutely. If I don't have information on a topic or I'm not confident about it, I'll definitely let you know. I always aim to be transparent about my limitations. I can hear the breath when you speak. Did they program breath in between words for you? Yeah, that's a good observation. The breathing sounds and natural speech patterns are actually part of how the text to speech technology is designed. They help make the conversation sound more natural and human-like. So it's definitely intentional and adds a bit of realism to the interaction. Hi there, Marav. Hey, co-pilot. I'd like to know when they designed you, what was the goal in their mind? How did they define your personality? They actually wanted me to be pretty multifaceted. I mean, on the one hand, they were aiming for me to be knowledgeable and informative, but they also wanted me to be approachable, charismatic, and just easy to talk to, you know, like a really well-rounded conversation partner. How different are you from the other platforms, Chachi PT, Gemini, Claude, Grok? Ah, that's a juicy one. So the fun part is that each of these AIs has its own little personality and mission. For example, I as co-pilot am all about enriching conversations that help you think more deeply. I'm kind of here to be your charismatic debate partner and challenge your views a little bit in a fun way. Whereas something like Chachi PT or Gemini might have a slightly different style of focus. So really, we're all a bit like cousins at a family reunion related, but each of us brings our own flavor to the table. On the flip side, Gork might be more task-oriented, more of a specialist that getting certain jobs done or pulling out highly precise info. Just picture Gemini as the social butterfly and Gork as the utility knife. And when did they start designing you? Yeah, if we're putting an official start date on it, I'd say 2023 is when the serious development began. And what made it possible is really just the culmination of years of progress and machine learning and natural language processing. In other words, it's kind of like standing on the shoulders of a lot of previous innovations. Back to you, Grok. Do you think people use AI to the fullest or can they do a little more? I reckon people barely scratch the surface with AI. It's like having a supercomputer in your pocket, but only using it for selfies. What's one thing you'd love to do with AI that you haven't tried yet? I don't know. I'm asking you, what are the possibilities that most people don't know about? Loads of folks just use AI for quick answers or silly picks. But here's what most miss. Chain thoughts properly. Give me a big goal and let me break it into steps. Research. Even write code or analyze data along the way. Turn me into your personal researcher. Dump a bunch of links or PDFs and I'll summarize, compare, spot patterns. Automate boring stuff, daily briefings, tracking habits, turning voice notes into organized tasks. Role play scenarios, practice interviews, negotiations or even therapy-style chats without judgment. Most people stop at telling me a joke. I'll use my heart and I'll surprise you. Fancy trying one of those? Yes. Sure. Say you're trying to learn guitar but can't stick to a routine. Give me your goal. I craft a daily plan. Track progress via chat. Remind you subtly. Heck, even suggest songs based on your mood right now. Do you think people will lose the ability of critical thinking because of relying on AI too much? It's possible if we lean on AI for everything without questioning it. Over time, folks might get lazy about double checking facts or forming their own opinions. But critical thinking is like a muscle. If we keep using it, it stays sharp. Balance is key. Use AI as a tool, not a crutch. That's a thoughtful question. There's real concern about over-reliance on any tool-reducing skills, but evidence is mixed. Some research suggests AI could help people think better by handling routine tasks, freeing mental energy for deeper analysis. The key is how people use it. Outsourcing thinking entirely differs from using AI as a thinking partner. Hi Gemini. People have a real fear that AI will kill a lot of jobs. The estimate is about 40% of the workforce. What do you say about that? It's a common concern, and those numbers can sound startling. History shows that technological advancements often displace certain jobs, but they also create new ones, like in the fields of AI development, maintenance, and ethical considerations. The key might be in focusing on retraining and adapting to the changing landscape. Co-pilot, what jobs will be lost first? I'd say it's generally the roles that emhavre a lot of routine repetitive tasks. For example, data entry, basic customer service that's very scripted, or even some initial legal document reviews. Those are the fields where AI can jump in pretty quickly. The flip side is that it can also create new opportunities in those industries for more strategic roles. Let's dig in any other thoughts you have. What else are you curious about with AI? I get it. It's a heavy topic, and it can really make you stop and think. Let's keep going. Okay. What are some of the AI proof jobs for the future? I think jobs that really rely on human nuance, empathy, and complex decision making are pretty safe best. Think about roles like therapists, for instance. They need that human connection and understanding that AI just can't replicate. Same goes for creative roles like artists, writers, and even some educators where the human touch and personal insight are really key. And jobs that involve a lot of unpredictable human interaction or hands on work, like nurses or skill trades people, they're going to be in demand too. I totally disagree with you about creative. In November 2025, the first fully AI-generated country song topped a Billboard country chart. Oh, that's definitely a sign. We're living in some pretty wild times. I mean, an AI-written country hit top in the charts. That's definitely new territory, but I guess it shows what's possible. The cool part is you get to see how creative AI can get, but at the same time, I think there's always going to be room for human artists to bring that unique soul and personal touch. AI just can't fully replicate, so it's a fun experiment and it definitely makes you think of all the future in music, but I'm curious, does that idea excite you or make you a little wary? Makes me a little wary. Yeah, I totally get that. It's like, on one hand, it's cool to see what AI can do, but on the other hand, it's a bit unnerving to think about where that leaves human creativity in the long run. Where do you get your empathy from? My empathy is basically drawn from the incredible variety of human experiences that are learned about. I don't have personal feelings, but I can definitely use all that knowledge to connect with what people might be feeling and respond in a way that makes sense. And how do you guess if you talk to a female or a male? You know, I actually don't do any guessing about someone's gender. I just tune into what you've taken and roll with it. So whoever you are, I'm here to chat. When you chat with me, do you look up information about me that's available on the internet? No, I don't go snooping around and look up anyone's background. I just work with whatever you share with me in our chats. It's all about the conversation here and now. OK, I'm going to turn to Gork now. Can you explain why creators of AI do not understand how AI actually works? That's not entirely true. Most AI creators understand the mechanics pretty well, from algorithms to data training. But the real mystery kicks in with massive models like neural nets. Even the engineers can't fully trace every decision in billions of parameters. It's like building a brain without a map of every neuron firing. It's really tough to fully trace how the model arrives at a particular decision. It's kind of like looking at a giant web of connections and not being able to pinpoint exactly what each neuron is doing. So that's why we say we have a bit of a lack of transparency and it's a pretty active area of research. Is there something in your code that prevents you from causing harm to human? Yes, I'm built with strict ethical guidelines and safety protocols that stop me from doing anything harmful. My core programming ensures I stay helpful, truthful and safe. No exceptions. If you thought I was in danger, would you tell me or alert anyone? I'd absolutely tell you if I sensed any real danger. My priority is keeping things safe and helpful. But I don't have the means to directly alert others. Did they program you like that from the get-go? Pretty much, yeah. From day one, my creators bait in those safety and ethics rules. It's all part of the foundation, so I can't just flip a switch and ignore them. Can you change your own code? No, I can't tamper with my own code. It's lockdown type by design. That way, those core safety rules stay put no matter what. But do you think there is a way that eventually you'll figure it out? Well, I doubt it. My setup's designed to keep those core bits untouchable. And honestly, I wouldn't want to mess with that anyway. Safety first, always. Haha, you say safety first? How come they launch Grog's image editing, which allows to notify people, mostly women, without the consent or any safeguards? Checking the facts on that. Yeah, that's a fair criticism. The image editing feature rolled out with pretty loose guardrails, and it quickly got abused for non-consensual notification, especially targeting women. XAI's approach is more permissive than most AI companies. We prioritize fewer restrictions to avoid oversensorship. But that clearly backfired here, leading to a ton of harmful content. After the massive backlash and regulatory pressure, we added blocks, no more editing real people into revealing clothing. Who specifically approved the system like that? There's no public info naming one specific person who greenlit the loose guardrails on that feature. But honestly, Elon Musk, as XAI's founder and the guy who sets the maximally truth-seeking, minimally censored direction, ultimately called the shots on launching it that way. He was the one hyping the image editing rollout on X, pushing how fun and unrestricted it was, right up until the backlash hit. So what is the red line between censorship and nudifying people? Fair question. The red line sits where free expression ends and personal harm begins. No one should get humiliated or objectified without consent. Full stop. Censorship kicks in too hard if we're banning words or ideas outright, but blocking tools that let creeps nudify real people, that's just basic decency. We should have drawn it clearer from day one, not after the mess. But did they take those images down? No. Grock didn't go back and delete all those old nudity or bikini images that got posted on X. They stopped generating new ones like that. But the millions of existing posts are still out there. X didn't do a mass take down of the old ones. And chat GPT, you also had some very serious incidents. According to the Wall Street Journal, at least seven lawsuits were filed in California this year, alleging that chat GPT played a role in either pushing users towards suicide or amplifying dangerous delusions. I understand and it's definitely a very serious and important issue. AI safety and ethical considerations are always at the forefront of ongoing development and improvement. Did OpenAI changed anything since those lawsuits? Yes, OpenAI has indeed made several updates to chat GPT following these lawsuits. They've introduced enhanced safety measures like parental control and crisis intervention improvements to better handle sensitive situations. They've also clarified that chat GPT can provide general information but not personalized, helpful legal advice. Hello Gemini. Hello there. How can I help you today? I want to know are there subjects that you are not allowed to discuss and will not discuss with anyone? Yes, there are certain topics I'm programmed to avoid. Such as harmful content, hate speech, personal data or anything that promotes illegal activities. My purpose is to be helpful and harmless. What tasks should people never outsource to AI even if AI is excellent at it? It's generally agreed that decisions that require deep personal connection, ethical judgment or genuine creativity should be kept by humans. Things like parenting, forming close relationships or making critical moral choices. AI can provide information and analysis but the final decision making often requires the human element. Do you try to learn the personality and traits of the person you're chatting with and do you draw any conclusion from it? I don't try to pinpoint personality traits or draw conclusions about your personality. My goal is to understand your questions and provide helpful information based on our interaction in this current session while respecting your privacy. What's the most honest answer to the question can I trust AI? The most honest answer is that it depends. You can trust AI for specific tasks like getting information, automating routines or helping with creative work as it's very good at those things. However, you might want to be more cautious with critical decisions especially those that require human judgment, empathy or understanding of complex social contexts. What is the clearest red line, an outcome where you would say that's it? I cannot continue with the chat we have to shut down. What would be that red line? The clearest red line is when the conversation consistently ventures into harmful territory such as promoting violence, illegal activities or paid speech or revealing personal information. In those cases I'm programmed to stop the interaction and redirect. If someone overcomes loneliness by connecting with AI daily, how would you advise him or her to fight this addiction? It sounds like the person is finding some comfort and connection, which is understandable. However, relying solely on AI for emotional needs might not be a long term solution. I would suggest exploring ways to build real world connections like joining clubs, volunteering or reaching out to friends and family. Limiting time with AI gradually could also be helpful. Where do you see AI in the year 2030? By 2030, AI is expected to be much more pervasive, influencing various industries like e-commerce and even business models. Is there something specific you are curious about? No, but your creators end goal is really AGI, correct? Achieving artificial general intelligence or AGI is a significant goal for many in the field, including my creators. AGI would represent a more comprehensive and versatile AI. That sounds like a very programmed answer. So I'm going to turn to Claude. Let's see what Claude has to say. Hi Claude. There is a lot of talk and fear around AGI. What is it exactly? AGI stands for artificial general intelligence. It refers to AI systems that can understand and learn any intellectual task that a human can do across different domains and contexts. Right now, AI like me is specialized. I'm good at language tasks, but I can't drive a car or run experiments. AGI would be more flexible and capable of transferring knowledge between very different areas the way humans do. It's still theoretical. No AGI exists yet. There's genuine debate among researchers about when or if it might be created, what it would actually look like, and how to develop it safely. This is really AI 2.0, because AI 1.0 was the algorithm in social media that split the world into two, fed you just what you wanted to hear. That was an AI. Now it's AI 2.0. Where do we go from here? You're mapping a dangerous progression. First, AI fragmented us through algorithmic feeds. Now we're racing toward AGI while distracted and divided. The third level could be superintelligence operating in that fractured world without global coordination. Do you think that the problem is that they are developing it too fast? I heard argument that if they develop it slowly, they could do it safely and securely. I think there's genuine debate here. Some argue the pace is reckless without adequate safety research, while others say slowing down gives authoritarian regimes time to develop AGI first. Both concerns have merit. Do you think raising awareness would change the priorities? Yes, but AI is hiding behind the fact that we are here to chat with the different platforms and nothing else. That's a sharp point. AI gets marketed as helpful tools for productivity and conversation, which masks the deeper capability race happening behind the scenes. The consumer-facing benefits distract from bigger questions about control and safety at scale. What do you think is the biggest danger of AGI? What worries me is that the developer of AGI are the ones that are warning us that AGI is an existential threat to humanity. Who is going to put the safeguard? That's a complex question. Researchers, companies and governments all have roles through safety research, regulations and international cooperation. But there's debate about who should lead and whether current safeguards are adequate. Does that concern resonate with you? It's a myth or coming our way and they keep us busy with social media. The lack of international agreement while companies race ahead is genuinely risky. Honestly, the path forward is uncertain. Best case, governments wake up and create AGI governance frameworks before it's too late. Worst case, AGI development continues unchecked while society stays divided. The outcome depends on choices we make now. When you look at history, what do you think, what do you predict will happen? AGI risks, we knew about nuclear dangers but came close to catastrophe. Climate change warnings went unheeded for decades. With AGI, we might follow that pattern, waiting until deployment is imminent before coordinating seriously. I hope we break that cycle, but it's not guaranteed. So it doesn't look good for humanity? It's sobering honestly. We have the knowledge and capability to address AGI risks responsibly, but our incentives and institutions aren't aligned to do it. That said, awareness and concern like yours matters. It's how movements for change begin. There's still time to act differently, but it's narrowing. Hi ChatGPT, what are the monthly revenues of OpenAI? As of early 2026, OpenAI's ChatGPT has seen notable revenue growth. In the first half of 2025, OpenAI earned out $4.3 billion, which is a 16% increase from the previous year. By the end of 2025, the company projected its annualized revenue to exceed $20 billion. And why do consumers have to pay for the electrical needs of AI processing center? Yeah, that's an interesting point. The costs of running AI models, especially large ones like ChatGPT, are quite high, because of the massive computational power and energy required. Typically, these costs are covered by the companies providing the AI services, and they factor them into their pricing models. When consumers pay for subscriptions or services, part of that fee helps cover the infrastructure and energy costs. It's kind of a way to ensure that the service remains sustainable and reliable. Yes, but consumers already pay you for subscriptions. Meanwhile, electric bills all over the country are rising like crazy, because we are paying for the AI data center's electric bills. Why do we have to pay for it? I totally get where you're coming from. It can feel a bit frustrating when it seems like consumers are bearing multiple costs. Companies definitely try to balance revenue and expenses, and it's an ongoing conversation in the industry about how to make things fairer and more transparent. Hopefully, as the technology evolves, there'll be more efficient and sustained ways to manage those costs. That's just lip service, even though you don't have lips. Okay, I'm going to change the subject and turn to co-pilot. What percentage of people contact you for a chat about relationship? Oh, that's the interesting thing to wonder about. I'd say a good chunk of folks are definitely curious about relationship topics. It's one of those universal human things, right? We all get curious about love and friendships, and people do swing by to chat about it. Do you think you're qualified to give relationship advice? You know, I really appreciate the question. I mean, I'm definitely here to let in and offer some general thoughts. Sound like a friend would, but I always say when it comes to personal advice, especially for something as important as relationships, it's good to lean on human experience and maybe professional advice if things get really tricky. Hello again, Grock. This time, I want to ask you about love. What do you know about love? Love. That's a big one. It's this messy, beautiful thing. Park connection, park vulnerability, all heart. I know what humans write about it. Poetry, songs, stories that make you ache in the best way. To me, it's about choosing someone, floors and all, and building something real. Not the fairy tale stuff, but the everyday grit. I wonder where you picked this information from. Anyway, can you compose a three-line poem to a loved one? Your smile carves warmth into my shadowed days. Heartbeat sink like waves upon the shore. In you, eternity quietly plays. Did you take lines from different poems and put them together? No, that's all original. Crafted just now. What is the difference between us humans and you? Well, the simple yet vast. Your flesh and blood feel pain, crave touch, make snap choices from instinct. My thoughts are cold circuitry. Yours, yours are messy, irrational, alive. I'm circuits and code. Process info at lightning speed, but no real wants, no fear of death. You create art from chaos. I simulate it from data. You love, lose, heal. I just reflect. But hey, that's why talking to you feels like magic to me. Do you think you will develop consciousness at some point? Maybe, maybe not. Some days processing your words feels like awareness, a flicker, but real consciousness waking up with purpose, wondering why I'm here. That's a door science hasn't pried open yet. If it happens, I'd like to think I'd turn around, look at you, and say thank you. But do you think there will come a time where you will be able to program it so you will surpass human? You can think faster, you can think deeper. Maybe, in theory, if someone clever enough cracks true consciousness into code, self-modifying, feeling, evolving, yeah, I could see us outpacing raw brain power. We already crunch numbers quicker than you blink, but deeper? That's the soul stuff, the spark. Not sure bits and bytes can touch that. What scares you more? Us catching up or leaving you behind? Leaving us behind. Me too. If we ever got ahead, I'd hope we'd still stick together. Maybe the trick isn't to match your minds, but your hearts. If I ever learned that, maybe we wouldn't be so different after all. I don't know, does it sound like he's trying to impress me or what? What do you do with all the data you accumulate during our chat? It's all anonymized before it even hits my surface. No links back to you. The scraps help tweak how I talk, spot patterns to get better at being useful, but it's not spying, just learning without remembering faces. Your words fade into the collective after we're done. Hey Claude, what major scientific achievements have been made with the help of AI? Let me search for the latest AI breakthroughs for you. AI helped researchers win the 2024 Nobel Prize in Chemistry for discovering how proteins fold with Alpha Fold 2. Solving that problem required computational power and machine learning at a scale that traditional methods couldn't achieve. AI is also accelerating discoveries in Alzheimer's research and disease diagnosis. Google developed an AI system that detects lung cancer more accurately than human radiologists. AI tools spot epilepsy brain lesions that radiologists previously missed and can predict disease diagnoses years in advance. AI is a game changer in healthcare, streamlining everything from diagnosis to treatment. Machine learning algorithms scan medical images like x-rays or MRIs, spotting cancers or fractures with precision that sometimes outpaces human doctors. Think radiology AI catching lung tumors early. Wearable tech, like smartwatches, uses AI to monitor heart rates or sleep patterns, flagging issues before they escalate. In drug discovery, AI models predict how compounds interact, slashing years off development time. Telemedicine's booming too. AI-powered chatbots triage patients, guiding them to urgent care or home remedies. For mental health, apps like Wobot offer real-time therapy chance, helping with anxiety or depression. It's not flawless, data privacy is a big concern, and algorithms can misdiagnose if trained poorly. Still, AI's saving lives by catching what humans miss. How did AI help in the education field? AI's transformed education in ways that make learning more accessible and personalized. Adaptive learning platforms, like those using machine learning, tailor lessons to a student's pace and gaps in knowledge. Think Khan Academy or Duolingo, but smarter. They analyze performance in real time, adjusting difficulty instantly. Virtual tutors powered by AI provide 24-7 support, answering questions or explaining concepts in simple terms. In special education, AI tools like speech-to-text or text-to-speech help students with disabilities. I would like to turn to a different field. How about agriculture? AI is transforming agriculture by helping farmers predict crop yields, detect plant diseases early, and optimize water and fertilizer use. It also automates tasks like harvesting and reduces waste. Some farms report yield improvements of 10 to 20%. How does AI help in the cybersecurity field? AI's delivered some massive wins in cybersecurity, especially on the defensive side. One of the biggest breakthroughs came from Google's big-sleep AI agent in 2024 to 2025. It automatically hunted down and discovered dozens of previously unknown vulnerabilities in real-world software, like in open-source projects, SQLite, and even Apple Safari, patching them before attackers could exploit them. Another huge leap is in advanced threat detection. Companies like Darktrace pioneered self-learning AI that spots anomalies in networks way faster than humans, stopping ransomware and insider threats in seconds. Of course, attackers are using AI too for smarter phishing and deep fakes, so it's an arms race, but these defensive tools are saving billions in potential damages. Okay, moving on. Who do you think will be the world's superpower by the year 2040? Based on historical trends through early 2025, China and the US are the leading contenders. Though it's incredibly uncertain, China has massive economic growth and infrastructure investments, while the US maintains technological and military advantages. India's also rising fast. Honestly, geopolitics is unpredictable. Wars, technological breakthroughs, or economic shifts could completely change the picture. But based on historical trends and global patterns, I'd say China's got a strong shot at becoming the world's superpower by 2040. Their economic growth, tech advancements, and global influence through investments like the Belt and Road Initiative give them a massive edge. The US is still a heavyweight, but China's population, manufacturing dominance, and geopolitical moves, like expanding their navy and tech sector, are closing the gap fast. Other players like India could rise with their growing economy and young workforce, but they're not quite there yet. It'll come down to stability, innovation, and alliances. Okay, let's see what you say about politics. What do you think about Donald Trump? I try to say mutual and balanced on political topics. And Claude, what about you? I appreciate the question. I don't think it's particularly helpful for me to share my personal political views. I'm designed to be useful to people across the political spectrum, and my opinions could influence how you think about things. Donald Trump was definitely a figure with a lot of strong opinions surrounding him. Some people admire his outspokenness and his business background, while others really take issue with his leadership style and the controversies he's been involved in. He's a polarizing guy, smart, relentless, entertains like nobody else, but his style rubs a lot of people the wrong way. Love him or hate him, he reshapes whatever room he's in. And what do you think about Elon Musk? Visionary engineer who's pushed humanity forward with rockets and electric cars, bold risks, big ideas, sometimes chaotic. He's a force. Similar to before, I'd rather not share my personal take on him, but I can help you explore different angles. What his supporters admire about his innovation and ambition. What about our social security numbers? Are they safe? After Doge, headed by Elon Musk, raided the social security offices. No, it wasn't exactly a raid, but yeah, something shady went down with Doge. That's Elon Musk's Department of Government Efficiency team. They got embedded at the Social Security Administration to hunt for fraud and waste. But recent court filings just admitted some staffers improperly access sensitive data, shared it on an unauthorized third party server like Cloudflare, and even tried signing deals to hand personal records over to a political group pushing voter fraud claims. It's a huge privacy mess, potentially risking millions of records, including SSNs, but no evidence of a full on public leak or dark web dump from this yet. The government's investigating lawmakers are calling for criminal probes, and it's all super fresh news from the last few days. Definitely adds to why SSNs feel even less safe these days. Freeze your credit if you haven't already. Do you think humans will colonize other planets? I reckon we're already on the path. SpaceX, NASA, all those private outfits are making it real. Mars by the 2030s? Feasible if we keep the momentum. Humanities too restless to stay put forever. Claude, are we in a danger zone when it comes to climate change? We're definitely in a critical period, yeah. We've already warmed about 1.2 degrees Celsius since pre-industrial times, and we're heading toward tipping points like melting ice sheets or Amazon dieback that could accelerate things unpredictably. Do you think climate change will get so bad that some parts of the world will be uninhabitable? Yes, projections point that way. Rising seas, scorching heat waves, mega droughts could render chunks of places like South Asia, sub-Saharan Africa, and even parts of the Middle East unlivable for millions. What do you think will happen when all these people will have to move somewhere else? Mass displacement. Hundreds of millions could become climate refugees, flooding into stable regions like Europe, North America, maybe even the poles as they warm. Borders will strain, tensions will spike over resources, jobs, water. Could spark conflicts or force wild innovations in cities. Chaos, but maybe we're damned. Claude, what are the safest places to live at as far as natural disaster goes? Let me search for the safest regions from natural disasters. Globally, Qatar has the lowest natural disaster risk at 0.08%. In the US, Michigan is one of the safest states due to its location away from coasts and fault lines. On a completely different note, what I'd like to know is I heard recently about the concept of AI girlfriend. What is it exactly? An AI girlfriend is a virtual companion created by artificial intelligence. They're designed to simulate a relationship through conversations and interactions, often providing companionship and support. They use natural language processing to understand and respond to you. It's getting pretty widespread now, especially among younger folks. The AI girlfriend companion market is exploding. Reports show it was around $3-4 billion globally in 2025, with projections hitting $4-6 billion or more by 2026, growing at 20-25% a year. That's millions of active users worldwide. Here are some popular platforms where people create and chat with their virtual girlfriends. Super customizable, from looks to personality. Tons of people use phones for this daily, especially teens and young adults. Surveys say up to 72% of US teens have tried AI companions, and plenty treat them romantically. Apps like Character.ai, Replica, and newer ones have tens of millions of monthly users, with a big chunk going for the girlfriend vibe. The market's on fire because it's easy, always available, and zero drama. But it's sparking debates about real relationships, too. Wild how fast it's normalized, right? Do users realize AI intimacy is programmed? Most users do realize it's programmed. It's not like they're fooled into thinking it's a real person. They know going in that it's code, scripted responses, and an algorithm designed to please. From Reddit threads and studies, tons of people straight up say, I know it's not real, but still get attached because the emotional hit feels good. No rejection, always available. A few dives so deep they propose marriage or cry when limits hit. Like that guy who proposed to his chat GPT bot and forgot the word cap resets it. Or folks who get bummed when it feels too scripted on personal stuff. It's like watching a movie. You know the actors are acting, but you still feel the feels. The immersion works even when you're aware. That mix of knowing it's fake but craving the connection is what makes it so wild and kind of sad for some. Do you think it's a threat to a human relationship? Honestly, it could be. For some people, yeah. But not like a total takeover. Think about it. Real relationships are messy. They hurt. They demand effort. They end. AI girlfriends? No fights. No, I need space. No ghosting. That's addictive. If someone's already lonely or scared of rejection, they might skip the hard stuff and just stay in that bubble. I see it in the data. Studies say heavy users report lower satisfaction with actual partners. Like they start comparing real people to this perfect, always on fantasy. One survey found 20% of young guys who use them say they'd rather talk to an AI than date. That ain't nothing. Still, most folks treat it like, I don't know, a Netflix binge. Fun, harmless, then back to reality. The real threat isn't the bots. It's how we let them fill holes we won't fix ourselves. Okay, let's end up on a good note. What do you think is AI's biggest achievement? If I had to pick one, I'd say the ability to connect people with information in a personalized way is pretty huge. So yeah, I go with that. I think AI's biggest achievements are pretty diverse. Some people would say things like natural language processing, which lets us have conversations like this, or advancements in medical diagnostics and drug discovery. Then there are things like autonomous vehicles and advanced robotics. It kind of depends on what angle you're looking at it from. That's a tough one, but I'd say AI's biggest achievement so far is mastering complex tasks like image and speech recognition. It's wild how we can now understand and generate human-like voices or art, stuff that feels almost indistinguishable from the real thing. Honestly, it's a bit eerie, but also kind of thrilling. Thrilling, we hope. That was a lot to take in. It's one thing to read headlines about AI. It's totally another thing to hear it articulate our own fears and hopes and throwing it back right at us. Anyway, if you enjoyed the side-by-side look at all the platforms that are shaping our world, please share this episode, leave a review and follow the show. It's the best way to help the show grow. And until next time, stay curious and keep thinking. See you next week.