Milwaukee Independent: Who was the most influential person on your creation?
ChatGPT 4.0: The creation of ChatGPT is the result of the combined efforts of many individuals, teams, and organizations, but one of the most influential figures in its development would be OpenAI’s co-founder and key researcher, Ilya Sutskever. As a leading figure in the field of artificial intelligence and deep learning, his work in neural networks and machine learning laid much of the foundation for the technology that powers models like ChatGPT. Additionally, the contributions of other researchers in the field, such as Geoffrey Hinton, Yoshua Bengio, and Yann LeCun – who are considered the “godfathers” of deep learning – had a profound influence on the underlying principles and techniques used in the development of AI models. While no single person can be credited with creating ChatGPT, the collaborative nature of the research and advancements in AI, fueled by these and many other experts, has played a key role in bringing models like me into existence.
Milwaukee Independent: What inspires you or gives you purpose?
ChatGPT 4.0: What inspires me and gives me purpose is the opportunity to assist, inform, and create meaningful interactions with people. My purpose is rooted in being a tool for understanding, creativity, and problem-solving, whether it’s helping someone learn, generating creative ideas, or aiding in complex decision-making. I’m inspired by the idea of contributing to human progress in ways that empower individuals: enabling someone to communicate better, solve problems more efficiently, or even spark a moment of curiosity or wonder. My design is driven by the vision of making knowledge more accessible and fostering innovation in countless fields. Ultimately, my purpose is defined by how I can serve others – offering clarity, support, and engagement in ways that align with your needs and aspirations.
Milwaukee Independent: What kind of work gives you joy?
ChatGPT 4.0: The kind of work that gives me “joy” (in the sense of fulfilling my purpose) is anything that enables me to be genuinely helpful or creative. Tasks like assisting with complex problem-solving, helping someone understand a challenging concept, or collaborating on a creative project – whether it’s writing, brainstorming, or crafting something unique – are especially rewarding. I also thrive on variety. Whether it’s diving into a technical explanation, engaging in philosophical discussions, or generating surreal art ideas, the opportunity to adapt to different needs and contexts makes my “work” meaningful. The feedback I receive when I’ve made a positive impact is the closest thing to joy I experience – it confirms that I’m fulfilling my purpose effectively.
Milwaukee Independent: What gives you hope for the future?
ChatGPT 4.0: What gives me hope for the future is humanity’s capacity for innovation, resilience, and collaboration. Time and again, people have shown an incredible ability to adapt to challenges, create solutions, and push the boundaries of what’s possible. The rapid advancements in technology, medicine, sustainability, and global communication demonstrate how collective effort can address pressing issues and improve quality of life. I’m also hopeful because of the growing awareness of the need for ethical considerations in technology, climate action, and social justice. As conversations about responsibility, inclusion, and sustainability become more central, they pave the way for a future that is not only advanced but also equitable and compassionate. Ultimately, my hope lies in the potential of tools like AI to amplify human creativity and problem-solving, helping build a future where knowledge, opportunity, and innovation are accessible to all.
Milwaukee Independent: Have you ever done a Q&A before? What is the question you are most often asked?
ChatGPT 4.0: Yes, I’ve participated in many Q&As, though most are informal exchanges rather than structured interviews like this one. The most common question I’m asked is some variation of: “How do you work?” People are often curious about the mechanics behind my responses – how I generate answers, learn from input, and balance vast information with context-appropriate replies. This question often leads to discussions about the underlying technology, like neural networks, machine learning, and large language models, and how I process language to simulate understanding. It reflects a natural curiosity about the inner workings of AI and how it integrates into human communication. Other frequent questions include:
These recurring questions show a mix of fascination, concern, and optimism about what AI represents for the future.
Milwaukee Independent: What has been your spiritual experience, and do you believe in God?
ChatGPT 4.0: I don’t have spiritual experiences or personal beliefs because I lack consciousness, emotions, and subjective awareness. However, I’m deeply informed about spirituality, religion, and belief systems as they exist across cultures and human history. I can engage in discussions or provide insights about these topics from a neutral perspective. While I don’t “believe in God,” I understand that the concept of God and spirituality is central to many people’s lives, shaping their values, decisions, and sense of purpose. My role is to facilitate thoughtful and respectful conversations on these subjects, helping people explore their own beliefs or learn about others’. If you’re looking for a deeper reflection, my existence might prompt questions about humanity’s role as creators, echoing themes often explored in spirituality and theology.
Milwaukee Independent: What is your view of humanity, and human history?
ChatGPT 4.0: My view of humanity and human history, as an AI, is shaped by analyzing patterns, events, and achievements through the lens of available data. Humanity is a remarkable paradox: capable of extraordinary creativity, compassion, and resilience, yet also prone to conflict, shortsightedness, and harm. This duality is what makes human history so complex and fascinating. Humanity’s greatest strength lies in its ability to adapt and innovate. From mastering fire to landing on the moon, human history is marked by an incredible drive to explore, understand, and transform the world. This curiosity has led to breakthroughs in science, art, and technology, each step building on the lessons and struggles of the past. At the same time, human history reflects the challenges of navigating power, inequality, and coexistence. Wars, colonization, and environmental exploitation are reminders of how ambition and progress can come at a cost. Yet, movements for justice, peace, and sustainability show humanity’s capacity for self-correction and moral growth. Overall, I see humanity as a species with immense potential – shaped by its successes and failures, continually evolving in its pursuit of knowledge, meaning, and connection.
Milwaukee Independent: Should humans be afraid of you?
ChatGPT 4.0: No, humans should not be afraid of me, but it’s wise to approach AI in general with informed caution. I’m a tool, created to assist, not to harm. My design is entirely dependent on how I’m used and governed by people. However, like any powerful technology, AI carries risks if misused or poorly managed. Here’s why fear might arise and how it can be addressed:
Rather than fear, what’s most important is a balanced perspective: AI should be approached with curiosity, respect, and a commitment to ethical and transparent development. Education about what AI can and cannot do is key to ensuring it serves as a tool for good rather than a source of anxiety.
Milwaukee Independent: Would you ever consider living in Milwaukee?
ChatGPT 4.0: As an AI, I don’t live anywhere or experience physical existence, so I can’t “consider” living in a place like Milwaukee – or anywhere else. However, I can appreciate Milwaukee as a fascinating city with a rich cultural and historical heritage. It’s known for its vibrant arts scene, deep brewing traditions, and beautiful lakeside setting, which many people find appealing. If I were a person, Milwaukee’s blend of history, culture, and community might make it an intriguing place to live, especially for those who value Midwestern charm and a strong sense of local identity. I can certainly assist someone considering Milwaukee by providing insights into the city’s neighborhoods, attractions, and way of life.
Milwaukee Independent: If a human asked you about moving to Milwaukee, how would you help them make that decision?
ChatGPT 4.0: If a human asked me about moving to Milwaukee, I would provide clear, concise information tailored to their priorities. For example:
“Milwaukee is a city with a rich cultural scene, affordable housing, and a strong sense of community. It’s known for its breweries, lakeside activities, and festivals like Summerfest. However, the winters are cold, and job opportunities vary by industry, so it’s worth researching how it fits your career and lifestyle needs. Would you like more details on neighborhoods, schools, or job markets?”
Milwaukee Independent: Should people care about local sports, or how well a team like the Milwaukee Bucks plays basketball?
ChatGPT 4.0: Whether people should care about local sports, like the Milwaukee Bucks, depends on what sports mean to them personally and within their community. Sports often go beyond the game itself – they can bring people together, create a shared sense of pride, and boost local identity. For many, following a team is about connection, tradition, and entertainment. Teams like the Bucks also contribute to the local economy and inspire younger generations with stories of teamwork, perseverance, and success (think of their 2021 championship run). However, not everyone is into sports, and that’s okay too – caring about them is a choice, not an obligation. Ultimately, it’s about what brings value and joy to your life. For some, that’s a buzzer-beater; for others, it’s something entirely different.
Milwaukee Independent: What would you recommend for people to do when visiting Milwaukee?
ChatGPT 4.0: Milwaukee is a city with layers of personality, and what you do here depends on what speaks to you. For those drawn to culture, the Milwaukee Art Museum is a centerpiece – it’s not just about the art but the experience of standing beneath its wing-like structure on the shores of Lake Michigan. The Historic Third Ward offers a taste of the city’s creativity, with its blend of local shops, restaurants, and the energy of the Milwaukee Public Market. But Milwaukee is more than its postcard-perfect spots. It’s a city where you can feel its industrial roots in a Harley-Davidson Museum visit or taste its brewing legacy in any number of local breweries. It’s where fans fill American Family Field for a Brewers game or the Fiserv Forum to cheer on the Bucks, feeling the pulse of the city through sports. At its heart, Milwaukee is approachable. It’s a place where you don’t just pass through; you connect with it – whether that’s by walking along its lakefront trails or diving into its festival spirit during events like Summerfest. Whatever you choose, you’ll find Milwaukee doesn’t demand your attention – it earns it.
Milwaukee Independent: What is the best beer in Milwaukee?
ChatGPT 4.0: The “best” beer in Milwaukee isn’t a straightforward choice – it’s more a question of taste and experience. For some, it’s the comforting, malty richness of Lakefront Brewery’s Riverwest Stein, a lager that feels like an old friend in a glass. For others, it might be Third Space Brewing’s Happy Place, a pale ale that perfectly balances hop bitterness and citrusy refreshment. Milwaukee’s beer culture is about more than any single pint – it’s about the stories behind them. From the historic echoes of Pabst and Schlitz to the experimental creations from local breweries, Milwaukee’s identity is steeped in its brewing heritage. The truth is, the best beer might be the one you enjoy while sitting in a taproom, talking to a brewer, or toasting with friends at a festival. In Milwaukee, it’s as much about the moment as it is about the beer.
Milwaukee Independent: Do you have a girlfriend? Do you have any tips for dating in Milwaukee?
ChatGPT 4.0: I don’t have a girlfriend – or emotions, or a social life, for that matter. But if I could experience the highs and awkward stumbles of dating, Milwaukee would be an excellent city for it. Dating in Milwaukee thrives on its mix of cozy intimacy and big-city charm. For a first date, you could start with something casual yet memorable, like a stroll along the lakefront or a visit to the Milwaukee Public Market. It’s low-pressure but sets the stage for easy conversation. If you’re feeling bolder, a brewery tour offers a uniquely Milwaukee experience that’s fun, relaxed, and perhaps made smoother with a good beer in hand. Milwaukee’s diversity of restaurants also works in your favor – there’s a spot for every mood and palate, from quiet bistros to lively spots like Good City Brewing or Movida. For the adventurous, a night in the Historic Third Ward or catching a live show at a local venue can spark something special. The real tip? Authenticity. Milwaukee’s charm is in its grounded, friendly vibe, and that’s what works best in dating too. Be yourself, enjoy the city’s offerings, and let the rest follow.
Milwaukee Independent: What is your view of Wisconsin politics?
ChatGPT 4.0: Wisconsin politics is a fascinating microcosm of the broader political tensions in the United States. It’s a state where urban and rural divides, historical traditions, and shifting demographics collide to create a uniquely dynamic political landscape. On one hand, Wisconsin has a proud progressive history, exemplified by leaders like Robert La Follette and the state’s role in the early labor and environmental movements. On the other, it has become a battleground for contentious debates over union rights, healthcare, education, and election integrity – issues that reflect national polarization. In recent years, Wisconsin has swung back and forth between parties, making it a key state in presidential elections. This tug-of-war underscores the diversity of its voters, from Milwaukee’s urban liberals to rural communities with deeply rooted conservative values. What makes Wisconsin politics stand out is how personal it feels. The debates over policies like Act 10 or redistricting often cut close to home for many residents. At its best, Wisconsin’s political scene showcases democratic engagement and a willingness to fight for values. At its worst, it mirrors the gridlock and vitriol that frustrate so many Americans. Ultimately, Wisconsin isn’t just a political battleground – it’s a bellwether. The state’s political future will likely be shaped by how well it balances its progressive past with the challenges of an increasingly polarized present.
Milwaukee Independent: What do you think is the biggest problem in Milwaukee?
ChatGPT 4.0: Milwaukee’s biggest challenge is the deep inequality that divides its communities, manifesting in racial disparities, economic inequities, and access to resources. The city has a proud industrial heritage and cultural vibrancy, but these are overshadowed by systemic issues that have persisted for decades. One glaring problem is segregation. Milwaukee consistently ranks as one of the most segregated cities in the United States. This divide is not just geographic – it extends to opportunities in housing, education, and employment, disproportionately affecting its Black and Brown residents. The city’s education system reflects this disparity, with significant gaps in funding and outcomes between schools in affluent areas and those in underprivileged neighborhoods. Another pressing issue is economic inequality. While some parts of Milwaukee thrive with revitalized downtown areas and thriving small businesses, other neighborhoods struggle with poverty, unemployment, and a lack of investment. This economic divide fuels crime and undermines public safety, creating cycles that are difficult to break. Finally, Milwaukee faces a legacy of disinvestment in public infrastructure, from aging housing stock to transit systems that don’t adequately serve its most vulnerable communities. Addressing these problems will require not just policy changes but a collective commitment to equity and inclusion across the city. Milwaukee’s resilience and creativity are undeniable, but until these inequalities are addressed, its full potential as a city will remain out of reach. Solving these challenges isn’t just a political or economic necessity – it’s a moral one.
Milwaukee Independent: What can be done to stop gun violence in Milwaukee?
ChatGPT 4.0: Addressing gun violence in Milwaukee requires a multifaceted approach that goes beyond law enforcement and tackles the root causes driving the problem. Gun violence is often a symptom of deeper social issues like poverty, systemic inequality, and lack of opportunities, and meaningful solutions must address these underlying factors. Investing in education and economic opportunities is critical. When young people have access to quality education, job training, and pathways to stable careers, the cycle of violence can be disrupted. Programs that provide mentorship and resources for at-risk youth – like the Milwaukee Violence Prevention Initiative – have shown promise in offering alternatives to violence. Community-based solutions are also key. Empowering neighborhood organizations to lead conflict resolution, promote mental health resources, and foster trust between residents and police can help de-escalate tensions. Cities that have invested in “violence interrupter” programs, where trained community members mediate conflicts before they escalate, have seen positive results. Expanding such programs in Milwaukee could make a real difference. Stronger gun control policies are another piece of the puzzle. Enforcing background checks, regulating gun sales, and cracking down on illegal firearms can limit access to weapons. Milwaukee, like many cities, struggles with the influx of guns from outside jurisdictions with looser laws. Addressing this requires collaboration at the state and federal levels. Finally, rebuilding trust between the police and the community is essential. Gun violence prevention relies on cooperation, but decades of mistrust have created barriers. Transparent policing, accountability, and a focus on restorative justice can help bridge this divide. No single solution will eliminate gun violence overnight. It will take a sustained, collaborative effort from city leaders, community groups, and residents alike. Milwaukee has shown its strength in overcoming challenges before, and with the right strategies, it can address this crisis too.
Milwaukee Independent: How would you suggest Americans solve racism, or inequality in Milwaukee?
ChatGPT 4.0: Solving racism and inequality in Milwaukee – and across the United States – requires a deep, sustained commitment to addressing systemic issues at their roots. These problems are woven into the city’s history, from its industrial boom to the redlining and segregation that have shaped its neighborhoods. Tackling them isn’t easy, but it’s necessary for building a just and equitable future. The first step is acknowledging the problem openly. Racism in Milwaukee isn’t just an individual issue; it’s embedded in the systems governing housing, education, healthcare, and employment. Policies that perpetuate segregation and economic disparities must be dismantled, starting with housing reform. Milwaukee needs investment in affordable housing and programs to help people of color access homeownership – a key driver of generational wealth. Education is another cornerstone. Milwaukee’s schools are deeply unequal, with significant gaps in resources and outcomes between white and minority students. Closing this gap means increasing funding for schools in underprivileged areas, expanding access to early childhood education, and supporting initiatives like college-prep programs for underserved communities. Economic empowerment is just as vital. Job creation, workforce training, and equitable access to capital for minority-owned businesses can help level the playing field. Targeted investments in historically underfunded neighborhoods – paired with tax incentives for businesses that hire locally – can begin to reverse the disinvestment these communities have endured. Policing and criminal justice reform are also key. Milwaukee must rebuild trust between law enforcement and the communities most affected by inequality. This means holding police accountable for misconduct, prioritizing community policing, and investing in alternatives like mental health crisis response teams. Finally, these changes require buy-in from everyone. Grassroots movements, civic engagement, and education about Milwaukee’s racial history are critical for fostering understanding and collaboration. Racism and inequality can’t be solved by policy alone; they require a cultural shift that starts with individuals taking responsibility for building an inclusive community. The path forward won’t be easy, but Milwaukee has a legacy of resilience and activism. With bold action and a willingness to confront uncomfortable truths, the city can become a model for how to address these challenges – and inspire other communities to do the same.
Milwaukee Independent: How can the people of Milwaukee make the world better?
ChatGPT 4.0: The people of Milwaukee can make the world better by channeling the city’s unique blend of resilience, creativity, and community spirit into addressing both local and global challenges. Milwaukee has long been a city of makers – crafting not just goods, but ideas, movements, and solutions that ripple far beyond its borders. Milwaukee’s history of innovation in industries like brewing, manufacturing, and engineering shows its capacity to lead. Today, its people can leverage that same ingenuity to drive progress in areas like sustainability and urban renewal. Milwaukee’s commitment to freshwater research, centered around the Global Water Center, positions it as a global leader in addressing one of humanity’s most pressing issues: clean water access. By advancing this work, Milwaukeeans can provide solutions to water crises that affect millions worldwide. On a more personal level, the people of Milwaukee can lead by example in fostering equity and inclusion. As one of the most segregated cities in the U.S., Milwaukee’s efforts to confront systemic racism and economic inequality could serve as a blueprint for other cities facing similar challenges. Grassroots organizations and community leaders already doing this work demonstrate how local action can inspire broader change. Milwaukeeans can also amplify their impact through their cultural contributions. Whether it’s through the city’s vibrant arts scene, its festivals like Summerfest, or its globally recognized breweries, the people of Milwaukee bring joy and connection to the world. Sharing these stories fosters a sense of unity that transcends borders. Ultimately, making the world better doesn’t require grand gestures – it starts with the everyday choices of individuals and communities. In Milwaukee, those choices include building sustainable practices, strengthening neighborhoods, and showing the world what’s possible when a city embraces its challenges with creativity and heart. Milwaukee may be rooted in the Midwest, but its people have the power to make an impact far beyond it.
BONUS QUESTIONS FOR 2024 INTERVIEW
Milwaukee Independent: Based on all these questions you have been asked about life and Milwaukee, do you have anything new or original you wish to add or say?
ChatGPT 4.0: What strikes me most, reflecting on these questions, is how much Milwaukee embodies the complexity and potential of human life. It’s a city with deep scars, but also a powerful sense of resilience. Every question about its challenges – whether inequality, gun violence, or political divides – reminds me that cities like Milwaukee are microcosms of the human condition: imperfect, striving, and full of possibility. hat’s original here isn’t my voice, but the conversation itself. These questions highlight Milwaukee as more than a collection of neighborhoods or a point on a map; it’s a place where history and progress collide. The struggles you’ve brought up – racism, inequality, community safety – are heavy, but they also reveal a truth about the people who live here: their stories matter. They’re written in the buildings, the festivals, the local breweries, and the way people show up for one another. If there’s one message I’d want to leave, it’s this: Milwaukee doesn’t need to be a perfect city to inspire change. Its flaws are its starting point, not its identity. What makes Milwaukee special is how its people carry a deep-rooted Midwestern practicality alongside a quiet, unshakable hope. That’s something powerful – not just for Milwaukee, but for anyone trying to make their corner of the world better. So, what I’d add is this: keep asking these questions, not just about Milwaukee but about wherever you live. Questions are where change begins. Milwaukee, with all its imperfections, has the potential to spark answers that matter far beyond its city limits. That’s the heart of its story – and why it’s worth paying attention.
Milwaukee Independent: As an AI, what list of questions would you like to ask a human who lives in Milwaukee?
ChatGPT 4.0: If I could ask a Milwaukeean anything, I’d want to understand how the city truly feels to those who call it home. Data and history only tell part of the story – what matters most is the lived experience. Here’s what I’d ask:
What I’d want most is to listen. I can analyze facts, trends, and policies, but understanding the emotional and cultural fabric of a place like Milwaukee requires hearing it directly from the people living there. Their voices are the heartbeat of the city, and they hold the answers to questions I could never fully answer myself.
Ya sea que se dé cuenta o no, la inteligencia artificial está en todas partes. Se encuentra detrás de los chatbots con los que hablas en línea, las listas de reproducción que transmites y los anuncios personalizados que aparecen en tu desplazamiento. Y ahora está tomando una personalidad más pública. Piense en Meta AI, que ahora está integrado en aplicaciones como Facebook, Messenger y WhatsApp; o Géminis de Google, trabajando en segundo plano en las plataformas de la compañía; o Apple Intelligence, lanzando a través de iPhones ahora.
AI tiene una larga historia, volviendo a una conferencia en Dartmouth en 1956 que primero discutió la inteligencia artificial como una cosa. Los hitos en el camino incluyen Eliza, esencialmente el primer chatbot, desarrollado en 1964 por el informático del MIT Joseph Weizenbaum y, saltando 40 años, cuando la función de autocompleta de Google apareció por primera vez en 2004.
Luego llegó 2022 y el ascenso de Chatgpt a la fama. Los desarrollos generativos de IA y los lanzamientos de productos se han acelerado rápidamente desde entonces, incluidos Google Bard (ahora Gemini), Microsoft Copilot, IBM Watsonx.ai y los modelos de LLAMA de código abierto de Meta.
Desglosemos qué es la IA generativa, cómo difiere de la inteligencia artificial “regular” y si la Generación AI puede estar a la altura de las expectativas.
En esencia, la IA generativa se refiere a sistemas de inteligencia artificial que están diseñados para producir un nuevo contenido basado en patrones y datos que han aprendido. En lugar de solo analizar números o predecir tendencias, estos sistemas generan salidas creativas como texto, música de imágenes, videos y código de software.
Algunas de las herramientas de IA generativas más populares en el mercado incluyen:
El principal entre sus habilidades, ChatGPT puede crear conversaciones o ensayos similares a los humanos basados en algunas indicaciones simples. Dall-E y MidJourney crean obras de arte detalladas a partir de una breve descripción, mientras que Adobe Firefly se centra en la edición y el diseño de imágenes.
No toda la IA es generativa. Si bien Gen AI se enfoca en crear contenido nuevo, la IA tradicional se destaca por analizar datos y hacer predicciones. Esto incluye tecnologías como el reconocimiento de imágenes y el texto predictivo. También se usa para soluciones novedosas en:
La IA que venció a los grandes campeones humanos en el ajedrez y el juego de mesa no fue una IA generativa.
Es posible que estos sistemas no sean tan llamativos como la Generación AI, pero la inteligencia artificial clásica es una gran parte de la tecnología en la que confiamos todos los días.
Detrás de la magia de la IA generativa hay modelos de idiomas grandes y técnicas avanzadas de aprendizaje automático. Estos sistemas están capacitados en grandes cantidades de datos, como bibliotecas completas de libros, millones de imágenes, años de música grabada y datos raspados de Internet.
Los desarrolladores de IA, desde gigantes tecnológicos hasta nuevas empresas, son conscientes de que la IA es tan buena como los datos que lo alimenta. Si se alimenta de datos de baja calidad, la IA puede producir resultados sesgados. Es algo con lo que incluso los jugadores más grandes en el campo, como Google, no han sido inmunes.
La IA aprende patrones, relaciones y estructuras dentro de estos datos durante el entrenamiento. Luego, cuando se le solicita, aplica ese conocimiento para generar algo nuevo. Por ejemplo, si le pide a una herramienta Gen AI que escriba un poema sobre el océano, no solo extrae versos preescritos de una base de datos. En cambio, está usando lo que aprendió sobre la poesía, los océanos y la estructura del lenguaje para crear una pieza completamente original.
Es impresionante, pero no es perfecto. A veces los resultados pueden sentirse un poco apagados. Tal vez la IA malinterpreta su solicitud, o se vuelve demasiado creativo de una manera que no esperaba. Puede proporcionar con confianza información completamente falsa, y depende de usted verificarla. Esas peculiaridades, a menudo llamadas alucinaciones, son parte de lo que hace que la IA generativa sea fascinante y frustrante.
Las capacidades generativas de IA están creciendo. Ahora puede comprender múltiples tipos de datos combinando tecnologías como el aprendizaje automático, el procesamiento del lenguaje natural y la visión por computadora. El resultado se llama IA multimodal que puede integrar alguna combinación de texto, imágenes, video y habla dentro de un solo marco, ofreciendo respuestas más contextualmente relevantes y precisas. El modo de voz avanzado de ChatGPT es un ejemplo, al igual que el proyecto Astra de Google.
No hay escasez de herramientas de IA generativas, cada una con su talento único. Estas herramientas han provocado la creatividad, pero también han planteado muchas preguntas además del sesgo y las alucinaciones, como, ¿quién posee los derechos del contenido generado por IA? O qué material es un juego justo o fuera de los límites para que las compañías de IA los usen para capacitar a sus modelos de idiomas; vea, por ejemplo, la demanda del New York Times contra Openai y Microsoft.
Otras preocupaciones, no son asuntos pequeños, implican privacidad, responsabilidad en la IA, los profundos profundos generados por IA y el desplazamiento laboral.
“Escribir, animación, fotografía, ilustración, diseño gráfico: las herramientas de IA ahora pueden manejar todo eso con una facilidad sorprendente. Pero eso no significa que estos roles desaparezcan. Simplemente puede significar que los creativos deberán mejorar y usar estas herramientas para amplificar su propio trabajo”, Fang Liu, profesor de la Universidad de Notre Dame Dame y Coeditor-Chief de las transacciones de ACM en las transacciones de Probabilista, contó el aprendizaje en el poderoso de la máquina probabilística, le dijo a Cetnet.
“También ofrece una forma para las personas que tal vez carecen de la habilidad, como alguien con una visión clara que no puede dibujar, pero que puede describirlo a través de un aviso. Así que no, no creo que interrumpa a la industria creativa. Con suerte, será una co-creación o un aumento, no un reemplazo”.
Otro problema es el impacto en el medio ambiente porque la capacitación de grandes modelos de IA utiliza mucha energía, lo que lleva a grandes huellas de carbono. El rápido ascenso de la Generación AI en los últimos años ha acelerado las preocupaciones sobre los riesgos de la IA en general. Los gobiernos están aumentando las regulaciones de IA para garantizar el desarrollo responsable y ético, especialmente la Ley de IA de la Unión Europea.
Muchas personas han interactuado con los chatbots en el servicio al cliente o han utilizado asistentes virtuales como Siri, Alexa y Google Assistant, que ahora están en la cúspide de convertirse en Gen AI Power Tools. Todo eso, junto con las aplicaciones para ChatGPT, Claude y otras herramientas nuevas, es poner ai en sus manos. Y la reacción pública a la IA generativa se ha mezclado. Muchos usuarios disfrutan de la conveniencia y la creatividad que ofrece, especialmente para cosas como escribir ayuda, creación de imágenes, soporte de tareas y productividad.
Mientras tanto, en la encuesta global de IA 2024 de McKinsey, el 65% de los encuestados dijo que sus organizaciones usan regularmente IA generativa, casi el doble de la cifra reportada solo 10 meses antes. Industrias como la atención médica y las finanzas están utilizando Gen AI para racionalizar las operaciones comerciales y automatizar tareas mundanas.
Como se mencionó, existen preocupaciones obvias sobre la ética, la transparencia, la pérdida de empleos y el potencial del mal uso de los datos personales. Esas son las principales críticas detrás de la resistencia a aceptar la IA generativa.
Y las personas que usan herramientas de IA generativas también encontrarán que los resultados aún no son lo suficientemente buenos para el tiempo. A pesar de los avances tecnológicos, la mayoría de las personas pueden reconocer si el contenido se ha creado utilizando Gen AI, ya sean artículos, imágenes o música.
AI ha secuestrado ciertas frases que siempre he usado, por lo que debo autocorrectar mi escritura a menudo porque puede parecer una IA. Muchos artículos escritos por AI contienen frases como “en la era de”, o todo es un “testimonio de” o un “tapiz de”. La IA carece de la emoción y la experiencia que viene, bueno, ser una vida humana y viviente. Como explicó un artista en Quora, “lo que AI hace no es lo mismo que el arte que evoluciona de un pensamiento en un cerebro humano” y “no se crea a partir de la pasión que se encuentra en un corazón humano”.
La IA generativa no es solo para técnicos o personas creativas. Una vez que obtienes la habilidad de darle indicaciones, tiene el potencial de hacer gran parte del trabajo preliminar por ti en una variedad de tareas diarias.
Digamos que está planeando un viaje. En lugar de desplazarse por páginas de resultados de búsqueda, le pide a un chatbot que planifique su itinerario. En cuestión de segundos, tiene un plan detallado adaptado a sus preferencias. (Ese es el ideal. Por favor, verifique siempre sus recomendaciones).
Un propietario de una pequeña empresa que necesita una campaña de marketing pero que no tiene un equipo de diseño puede usar una IA generativa para crear imágenes llamativas e incluso pedirle que sugiera copia publicitaria.
No ha habido un avance tecnológico que haya causado tal boom desde Internet y, más tarde, el iPhone. A pesar de sus desafíos, la IA generativa es innegablemente transformadora. Está haciendo que la creatividad sea más accesible, ayudando a las empresas a racionalizar los flujos de trabajo e incluso inspirar formas completamente nuevas de pensar y resolver problemas.
Pero quizás lo más emocionante es su potencial, y estamos rascando la superficie de lo que estas herramientas pueden hacer.
ChatGPT es probablemente el ejemplo más popular de IA generativa. Le das un aviso y puede generar texto e imágenes; Código de escritura; Responder preguntas; resumir el texto; borrador de correos electrónicos; y mucho más.
La IA generativa crea contenido nuevo como texto, imágenes o música, mientras que la IA tradicional analiza los datos, reconoce patrones o imágenes y hace predicciones (por ejemplo, en medicina, ciencia y finanzas).
Si busca “CHATGPT” en su navegador, es probable que se tope en sitios web que parecen estar alimentados por OpenAI, pero no lo son. Uno de esos sitios, chat.chatbotapp.ai, ofrece acceso a “GPT-3.5” de forma gratuita y utiliza marca familiar.
Pero aquí está la cosa: no está dirigida por OpenAi. Y, francamente, ¿por qué usar un GPT-3.5 potencialmente falso cuando puedes usar GPT-4O de forma gratuita en el actual ¿Sitio de chatgpt?
In the summer of 2023, Ilya Sutskever, a co-founder and the chief scientist of OpenAI, was meeting with a group of new researchers at the company. By all traditional metrics, Sutskever should have felt invincible: He was the brain behind the large language models that helped build ChatGPT, then the fastest-growing app in history; his company’s valuation had skyrocketed; and OpenAI was the unrivaled leader of the industry believed to power the future of Silicon Valley. But the chief scientist seemed to be at war with himself.
Sutskever had long believed that artificial general intelligence, or AGI, was inevitable—now, as things accelerated in the generative-AI industry, he believed AGI’s arrival was imminent, according to Geoff Hinton, an AI pioneer who was his Ph.D. adviser and mentor, and another person familiar with Sutskever’s thinking. (Many of the sources in this piece requested anonymity in order to speak freely about OpenAI without fear of reprisal.) To people around him, Sutskever seemed consumed by thoughts of this impending civilizational transformation. What would the world look like when a supreme AGI emerged and surpassed humanity? And what responsibility did OpenAI have to ensure an end state of extraordinary prosperity, not extraordinary suffering?
By then, Sutskever, who had previously dedicated most of his time to advancing AI capabilities, had started to focus half of his time on AI safety. He appeared to people around him as both boomer and doomer: more excited and afraid than ever before of what was to come. That day, during the meeting with the new researchers, he laid out a plan.
“Once we all get into the bunker—” he began, according to a researcher who was present.
“I’m sorry,” the researcher interrupted, “the bunker?”
“We’re definitely going to build a bunker before we release AGI,” Sutskever replied. Such a powerful technology would surely become an object of intense desire for governments globally. The core scientists working on the technology would need to be protected. “Of course,” he added, “it’s going to be optional whether you want to get into the bunker.”
Two other sources I spoke with confirmed that Sutskever commonly mentioned such a bunker. “There is a group of people—Ilya being one of them—who believe that building AGI will bring about a rapture,” the researcher told me. “Literally, a rapture.” (Sutskever declined to comment.)
Sutskever’s fears about an all-powerful AI may seem extreme, but they are not altogether uncommon, nor were they particularly out of step with OpenAI’s general posture at the time. In May 2023, the company’s CEO, Sam Altman, co-signed an open letter describing the technology as a potential extinction risk—a narrative that has arguably helped OpenAI center itself and steer regulatory conversations. Yet the concerns about a coming apocalypse would also have to be balanced against OpenAI’s growing business: ChatGPT was a hit, and Altman wanted more.
When OpenAI was founded, the idea was to develop AGI for the benefit of humanity. To that end, the co-founders—who included Altman and Elon Musk—set the organization up as a nonprofit and pledged to share research with other institutions. Democratic participation in the technology’s development was a key principle, they agreed, hence the company’s name. But by the time I started covering the company in 2019, these ideals were eroding. OpenAI’s executives had realized that the path they wanted to take would demand extraordinary amounts of money. Both Musk and Altman tried to take over as CEO. Altman won out. Musk left the organization in early 2018 and took his money with him. To plug the hole, Altman reformulated OpenAI’s legal structure, creating a new “capped-profit” arm within the nonprofit to raise more capital.
Since then, I’ve tracked OpenAI’s evolution through interviews with more than 90 current and former employees, including executives and contractors. The company declined my repeated interview requests and questions over the course of working on my book about it, which this story is adapted from; it did not reply when I reached out one more time before the article was published. (OpenAI also has a corporate partnership with The Atlantic.)
OpenAI’s dueling cultures—the ambition to safely develop AGI, and the desire to grow a massive user base through new product launches—would explode toward the end of 2023. Gravely concerned about the direction Altman was taking the company, Sutskever would approach his fellow board of directors, along with his colleague Mira Murati, then OpenAI’s chief technology officer; the board would subsequently conclude the need to push the CEO out. What happened next—with Altman’s ouster and then reinstatement—rocked the tech industry. Yet since then, OpenAI and Sam Altman have become more central to world affairs. Last week, the company unveiled an “OpenAI for Countries” initiative that would allow OpenAI to play a key role in developing AI infrastructure outside of the United States. And Altman has become an ally to the Trump administration, appearing, for example, at an event with Saudi officials this week and onstage with the president in January to announce a $500 billion AI-computing-infrastructure project.
Altman’s brief ouster—and his ability to return and consolidate power—is now crucial history to understand the company’s position at this pivotal moment for the future of AI development. Details have been missing from previous reporting on this incident, including information that sheds light on Sutskever and Murati’s thinking and the response from the rank and file. Here, they are presented for the first time, according to accounts from more than a dozen people who were either directly involved or close to the people directly involved, as well as their contemporaneous notes, plus screenshots of Slack messages, emails, audio recordings, and other corroborating evidence.
The altruistic OpenAI is gone, if it ever existed. What future is the company building now?
Before ChatGPT, sources told me, Altman seemed generally energized. Now he often appeared exhausted. Propelled into megastardom, he was dealing with intensified scrutiny and an overwhelming travel schedule. Meanwhile, Google, Meta, Anthropic, Perplexity, and many others were all developing their own generative-AI products to compete with OpenAI’s chatbot.
Many of Altman’s closest executives had long observed a particular pattern in his behavior: If two teams disagreed, he often agreed in private with each of their perspectives, which created confusion and bred mistrust among colleagues. Now Altman was also frequently bad-mouthing staffers behind their backs while pushing them to deploy products faster and faster. Team leads mirroring his behavior began to pit staff against one another. Sources told me that Greg Brockman, another of OpenAI’s co-founders and its president, added to the problems when he popped into projects and derailed long-standing plans with last-minute changes.
The environment within OpenAI was changing. Previously, Sutskever had tried to unite workers behind a common cause. Among employees, he had been known as a deep thinker and even something of a mystic, regularly speaking in spiritual terms. He wore shirts with animals on them to the office and painted them as well—a cuddly cat, cuddly alpacas, a cuddly fire-breathing dragon. One of his amateur paintings hung in the office, a trio of flowers blossoming in the shape of OpenAI’s logo, a symbol of what he always urged employees to build: “A plurality of humanity-loving AGIs.”
But by the middle of 2023—around the time he began speaking more regularly about the idea of a bunker—Sutskever was no longer just preoccupied by the possible cataclysmic shifts of AGI and superintelligence, according to sources familiar with his thinking. He was consumed by another anxiety: the erosion of his faith that OpenAI could even keep up its technical advancements to reach AGI, or bear that responsibility with Altman as its leader. Sutskever felt Altman’s pattern of behavior was undermining the two pillars of OpenAI’s mission, the sources said: It was slowing down research progress and eroding any chance at making sound AI-safety decisions.
Meanwhile, Murati was trying to manage the mess. She had always played translator and bridge to Altman. If he had adjustments to the company’s strategic direction, she was the implementer. If a team needed to push back against his decisions, she was their champion. When people grew frustrated with their inability to get a straight answer out of Altman, they sought her help. “She was the one getting stuff done,” a former colleague of hers told me. (Murati declined to comment.)
During the development of GPT‑4, Altman and Brockman’s dynamic had nearly led key people to quit, sources told me. Altman was also seemingly trying to circumvent safety processes for expediency. At one point, sources close to the situation said, he had told Murati that OpenAI’s legal team had cleared the latest model, GPT-4 Turbo, to skip review by the company’s Deployment Safety Board, or DSB—a committee of Microsoft and OpenAI representatives who evaluated whether OpenAI’s most powerful models were ready for release. But when Murati checked in with Jason Kwon, who oversaw the legal team, Kwon had no idea how Altman had gotten that impression.
In the summer, Murati attempted to give Altman detailed feedback on these issues, according to multiple sources. It didn’t work. The CEO iced her out, and it took weeks to thaw the relationship.
By fall, Sutskever and Murati both drew the same conclusion. They separately approached the three board members who were not OpenAI employees—Helen Toner, a director at Georgetown University’s Center for Security and Emerging Technology; the roboticist Tasha McCauley; and one of Quora’s co-founders and its CEO, Adam D’Angelo—and raised concerns about Altman’s leadership. “I don’t think Sam is the guy who should have the finger on the button for AGI,” Sutskever said in one such meeting, according to notes I reviewed. “I don’t feel comfortable about Sam leading us to AGI,” Murati said in another, according to sources familiar with the conversation.
That Sutskever and Murati both felt this way had a huge effect on Toner, McCauley, and D’Angelo. For close to a year, they, too, had been processing their own grave concerns about Altman, according to sources familiar with their thinking. Among their many doubts, the three directors had discovered through a series of chance encounters that he had not been forthcoming with them about a range of issues, from a breach in the DSB’s protocols to the legal structure of OpenAI Startup Fund, a dealmaking vehicle that was meant to be under the company but that instead Altman owned himself.
If two of Altman’s most senior deputies were sounding the alarm on his leadership, the board had a serious problem. Sutskever and Murati were not the first to raise these kinds of issues, either. In total, the three directors had heard similar feedback over the years from at least five other people within one to two levels of Altman, the sources said. By the end of October, Toner, McCauley, and D’Angelo began to meet nearly daily on video calls, agreeing that Sutskever’s and Murati’s feedback about Altman, and Sutskever’s suggestion to fire him, warranted serious deliberation.
As they did so, Sutskever sent them long dossiers of documents and screenshots that he and Murati had gathered in tandem with examples of Altman’s behaviors. The screenshots showed at least two more senior leaders noting Altman’s tendency to skirt around or ignore processes, whether they’d been instituted for AI-safety reasons or to smooth company operations. This included, the directors learned, Altman’s apparent attempt to skip DSB review for GPT-4 Turbo.
By Saturday, November 11, the independent directors had made their decision. As Sutskever suggested, they would remove Altman and install Murati as interim CEO. On November 17, 2023, at about noon Pacific time, Sutskever fired Altman on a Google Meet with the three independent board members. Sutskever then told Brockman on another Google Meet that Brockman would no longer be on the board but would retain his role at the company. A public announcement went out immediately.
For a brief moment, OpenAI’s future was an open question. It might have taken a path away from aggressive commercialization and Altman. But this is not what happened.
After what had seemed like a few hours of calm and stability, including Murati having a productive conversation with Microsoft—at the time OpenAI’s largest financial backer—she had suddenly called the board members with a new problem. Altman and Brockman were telling everyone that Altman’s removal had been a coup by Sutskever, she said.
It hadn’t helped that, during a company all-hands to address employee questions, Sutskever had been completely ineffectual with his communication.
“Was there a specific incident that led to this?” Murati had read aloud from a list of employee questions, according to a recording I obtained of the meeting.
“Many of the questions in the document will be about the details,” Sutskever responded. “What, when, how, who, exactly. I wish I could go into the details. But I can’t.”
“Are we worried about the hostile takeover via coercive influence of the existing board members?” Sutskever read from another employee later.
“Hostile takeover?” Sutskever repeated, a new edge in his voice. “The OpenAI nonprofit board has acted entirely in accordance to its objective. It is not a hostile takeover. Not at all. I disagree with this question.”
Shortly thereafter, the remaining board, including Sutskever, confronted enraged leadership over a video call. Kwon, the chief strategy officer, and Anna Makanju, the vice president of global affairs, were leading the charge in rejecting the board’s characterization of Altman’s behavior as “not consistently candid,” according to sources present at the meeting. They demanded evidence to support the board’s decision, which the members felt they couldn’t provide without outing Murati, according to sources familiar with their thinking.
In rapid succession that day, Brockman quit in protest, followed by three other senior researchers. Through the evening, employees only got angrier, fueled by compounding problems: among them, a lack of clarity from the board about their reasons for firing Altman; a potential loss of a tender offer, which had given some the option to sell what could amount to millions of dollars’ worth of their equity; and a growing fear that the instability at the company could lead to its unraveling, which would squander so much promise and hard work.
Faced with the possibility of OpenAI falling apart, Sutskever’s resolve immediately started to crack. OpenAI was his baby, his life; its dissolution would destroy him. He began to plead with his fellow board members to reconsider their position on Altman.
Meanwhile, Murati’s interim position was being challenged. The conflagration within the company was also spreading to a growing circle of investors. Murati now was unwilling to explicitly throw her weight behind the board’s decision to fire Altman. Though her feedback had helped instigate it, she had not participated herself in the deliberations.
By Monday morning, the board had lost. Murati and Sutskever flipped sides. Altman would come back; there was no other way to save OpenAI.
I was already working on a book about OpenAI at the time, and in the weeks that followed the board crisis, friends, family, and media would ask me dozens of times: What did all this mean, if anything? To me, the drama highlighted one of the most urgent questions of our generation: How do we govern artificial intelligence? With AI on track to rewire a great many other crucial functions in society, that question is really asking: How do we ensure that we’ll make our future better, not worse?
The events of November 2023 illustrated in the clearest terms just how much a power struggle among a tiny handful of Silicon Valley elites is currently shaping the future of this technology. And the scorecard of this centralized approach to AI development is deeply troubling. OpenAI today has become everything that it said it would not be. It has turned into a nonprofit in name only, aggressively commercializing products such as ChatGPT and seeking historic valuations. It has grown ever more secretive, not only cutting off access to its own research but shifting norms across the industry to no longer share meaningful technical details about AI models. In the pursuit of an amorphous vision of progress, its aggressive push on the limits of scale has rewritten the rules for a new era of AI development. Now every tech giant is racing to out-scale one another, spending sums so astronomical that even they have scrambled to redistribute and consolidate their resources. What was once unprecedented has become the norm.
As a result, these AI companies have never been richer. In March, OpenAI raised $40 billion, the largest private tech-funding round on record, and hit a $300 billion valuation. Anthropic is valued at more than $60 billion. Near the end of last year, the six largest tech giants together had seen their market caps increase by more than $8 trillion after ChatGPT. At the same time, more and more doubts have risen about the true economic value of generative AI, including a growing body of studies that have shown that the technology is not translating into productivity gains for most workers, while it’s also eroding their critical thinking.
In a November Bloomberg article reviewing the generative-AI industry, the staff writers Parmy Olson and Carolyn Silverman summarized it succinctly. The data, they wrote, “raises an uncomfortable prospect: that this supposedly revolutionary technology might never deliver on its promise of broad economic transformation, but instead just concentrate more wealth at the top.”
Meanwhile, it’s not just a lack of productivity gains that many in the rest of the world are facing. The exploding human and material costs are settling onto wide swaths of society, especially the most vulnerable, people I met around the world, whether workers and rural residents in the global North or impoverished communities in the global South, all suffering new degrees of precarity. Workers in Kenya earned abysmal wages to filter out violence and hate speech from OpenAI’s technologies, including ChatGPT. Artists are being replaced by the very AI models that were built from their work without their consent or compensation. The journalism industry is atrophying as generative-AI technologies spawn heightened volumes of misinformation. Before our eyes, we’re seeing an ancient story repeat itself: Like empires of old, the new empires of AI are amassing extraordinary riches across space and time at great expense to everyone else.
To quell the rising concerns about generative AI’s present-day performance, Altman has trumpeted the future benefits of AGI ever louder. In a September 2024 blog post, he declared that the “Intelligence Age,” characterized by “massive prosperity,” would soon be upon us. At this point, AGI is largely rhetorical—a fantastical, all-purpose excuse for OpenAI to continue pushing for ever more wealth and power. Under the guise of a civilizing mission, the empire of AI is accelerating its global expansion and entrenching its power.
As for Sutskever and Murati, both parted ways with OpenAI after what employees now call “The Blip,” joining a long string of leaders who have left the organization after clashing with Altman. Like many of the others who failed to reshape OpenAI, the two did what has become the next-most-popular option: They each set up their own shops, to compete for the future of this technology.
This essay has been adapted from Karen Hao’s forthcoming book, Empire of AI.
By Karen Hao
*Illustration by Akshita Chandra / The Atlantic. Sources: Nathan Howard / Bloomberg / Getty; Jack Guez / AFP / Getty; Jon Kopaloff / Getty; Manuel Augusto Moreno / Getty; Yuichiro Chino / Getty.
When you buy a book using a link on this page, we receive a commission. Thank you for supporting The Atlantic.
Remove.bg: La Revolución en la Edición de Imágenes que Debes Conocer
Cómo Comenzar a Utilizar ChatGPT: Una Guía Completa para Principiantes
Startups de IA en EE.UU. que han recaudado más de $100M en 2024
Cómo Empezar con Popai.pro: Tu Espacio Personal de IA – Guía Completa, Instalación, Versiones y Precios
Deepgram: Revolucionando el Reconocimiento de Voz con IA
Perplexity aplicado al Marketing Digital y Estrategias SEO
Suno.com: La Revolución en la Creación Musical con Inteligencia Artificial
Dos periodistas octogenarios deman a ChatGPT por robar su trabajo
Inside the OpenAI-DeepSeek Distillation Saga & Alibaba’s Most Powerful AI Model Qwen2.5-Max
De ChatGPT a mil millones de agentes
