Connect with us

Noticias

AI-powered tutor tested as a way to help educators and students | 60 Minutes

Published

on

We are about to show you a technological innovation that could, one day, change the way every child in every school in America is taught. It’s an online tutor powered by artificial intelligence designed to help teachers be more efficient .. and students learn more effectively. It’s called Khanmigo- conmigo means “with me,” in Spanish. And Khan..is its creator…Sal Khan, the well-known founder of Khan Academy – whose lectures and educational software have been used for years by tens of millions of students and teachers in the U.S. and around the world. Khanmigo was built with the help of OpenAI, the creator of ChatGPT. Its potential is staggering, but it’s still very much a work in progress. It’s being piloted in 266 school districts in the U.S. in grades three-12. We went to Hobart High School in Indiana to see how it works. 

Melissa Higgason: Good morning, just a normal day in chem, right? 

At eight in the morning Melissa Higgason knows it’s not always easy to get 30 high schoolers excited about chemistry. 

Melissa Higgason: Are you ready? Are you ready? 

Students: Yeah. 

Melissa Higgason: Alright, that’s what I want to hear. 

But these days … she has help.

Melissa Higgason: This is acidic acid. The pipettes not going to fill all the way.

That lesson Higgason has displayed behind her and is explaining to her ninth and tenth graders, was created with the assistance of Khanmigo..she told the AI tutor she wanted a four-day course in which her students would investigate the physical and chemical properties of matter. 

Melissa Higgason
Khanmigo can be used to help teachers plan lessons.

60 Minutes


Melissa Higgason This next section is your research section…

It took Khanmigo minutes to come up with a detailed lesson plan …that would have taken Higgason a week to create. 

Melissa Higgason: Pull that computer back out. You’re going to go back to Khanmigo research…

And the students have Khanmigo on their laptops too…. ready to help them with their questions.

Abigail: We have a couple of questions that we need to ask Khanmigo. So, for example, I asked it, what are three examples of acids? And if I want to know more 

Anderson Anderson Cooper: So it gave you three examples of acids… like hydrochloric acid… citric… and sulfuric. 

Abigail: “Can you give me more examples?”

Abigail: And if I wanted to know even more I could ask it like what specifically some of the acids do?

Anderson Anderson Cooper: So it’s giving you acids and then it’s asking you a question,“can you think of any other household items that might contain acid?” 

Abigail: Yeah, so like it wants to help you understand like what it’s telling you and not just like give you the information.

Finding creative ways to help kids learn is something Sal khan has been doing since 2005. He’d gotten degrees in math, computer science and engineering from MIT and an MBA from Harvard, and was working as a hedge fund analyst when he started recording math tutorial videos in his closet for his young cousins. 

Khan recording a lesson: So if I were to multiply this equation…

Not long after, with the help of donors including Bill Gates, he quit his career in finance and started the nonprofit Khan Academy. 

Sal Khan: From the beginning of Khan Academy, the true north was how do you give more students at least approximations of the type of personalization they would get if they had a personal tutor. 

Anderson Cooper: A wealthy family can afford a tutor for their child. If every kid could have a private tutor, that would level the playing field.

Sal Khan: Yeah, that’s the dream. 

Sal Khan and Anderson Cooper
Sal Khan and Anderson Cooper

60 Minutes


Co-founders of OpenAI, Greg Brockman and Sam Altman, were fans of Khan Academy, and hoped to evaluate their AI using Khan’s database of test questions and content, so they gave Sal Khan early access to an advanced AI technology that today underpins ChatGPT. 

Anderson Cooper: What did you immediately think?

Sal Khan: It was pretty obvious this technology was gonna transform society, so it– it was pretty heady stuff. But on the education side, it was like, “Wow, people are gonna be able to use this for doing deep fakes and fraud and cheat.” But if used well with the right guardrails, et cetera, could also be used to support students, to give them more feedback, to support teachers for all this lesson planning and progress report writing that they spend hours a week doing.

Khan team member: Item level analysis… 

Educators and engineers at Khan Academy used OpenAI’s technology to build Khanmigo…

Hobart teacher: We’re going to be using Khanmigo for this…

 …and for the last year and a half the teachers and kids at Hobart High School and others have been testing it out. 

Austin: I’ll ask it a question… 

We sat down with two students from that morning chemistry class, Austin and Abigail, as well as Laden and Maddie, who use Khanmigo in business class. And Lu and Lily who use it in English and for SAT preparation. 

Anderson Cooper: I heard people at Khan Academy came and asked students to break it.

Voices: Yeah. Yes. 

Laden: That was the fun part. 

Anderson Cooper:That was the fun part–

Voices: That was. 

Austin: Some students would try and trick it into just giving you the answer. 

Anderson Cooper: The superintendent I talked to said that some students were bullying Khanmigo for the answer.

Male voice: Yeah. 

Maddie: I think that was the elementary school kids that were doing it–

Anderson Cooper: Oh yeah, okay. Blame it on the elementary school kids. 

Lily: It’s very helpful for those students who maybe don’t feel comfortable asking questions within class.

Anderson Cooper: Does it have a personality?

Austin: It’s very much there for you. Like, it’s very positive, it’s very reassuring. 

Laden: It’s getting me thinking. And it’s not just giving me an answer.

Anderson Cooper: Do you ever just wanna be like, “Can you just gimme the answer?”

AI tutor
Anderson Cooper learning about Khanmigo, an AI-powered tutor.

60 Minutes


Lily: Yeah. That was the hardest part for I know, like me and a lot of other students. Like “Why isn’t it giving me answers? At the end of the day, that’s where your better answer is gonna be. It’s not gonna be whatever the AI gives you; it’s gonna be whatever you create. 

Higgason: So your hypothesis going into the last test is… 

Teachers at Hobart High don’t just use Khanmigo to help plan lessons and save dozens of hours a week, they also monitor their students’ understanding of subjects in ways they never could before. 

Anderson Cooper: You can track how a student is actually using Khanmigo?

Melissa Higgason: Yeah. I’m going to click “usage” And then if I wanted to pick a specific student, I could come down here and really dive into what that student’s been looking at Khanmigo. And this is real time because you saw Abigail this morning looking at acids and bases… 

Anderson Cooper: So wait a minute. These are the footprints of Abigail’s work?

Melissa Higgason: These are the footprints of Abigail’s work.

Anderson Cooper: At 8 a.m. she was asking about acids and chemical reactions?

Anderson Cooper: So even though you may not be hovering over the student at any given moment, you’re somewhere else in the classroom–

Melissa Higgason: Right.

Anderson Cooper: You can later check, “Oh, this is what Abigail was looking– I understand her thought process on why she got–these answers.

Melissa Higgason: Absolutely. So It gives me a lot of insight as a teacher in terms of who I need to spend that one-on-one time with. 

Khan meeting with team: Maybe Khanmigo throws in a master challenge…. 

Sal Khan says they won’t sell the data they collect through Khanmigo or give it to other tech companies. They do use it however to improve Khanmigo’s memory and personalization.

Sarah Robertson: It will guide them to sort of what to do first…

Sarah Robertson, a former English teacher who is now a Khanmigo product manager, showed us a new feature they’ve developed to help kids write better and think more critically. 

Anderson Cooper: I found this essay that I wrote. 

To test it, I gave Khanmigo a paper I wrote in sixth grade about my mom Gloria Vanderbilt. 

Sarah Robertson: So go ahead and click “next start revising.” 

After just 90 seconds, Khanmigo delivered a very detailed evaluation of my essay…

It liked some of what I wrote…

Anderson Cooper: The use of a quote to start the essay is effective and sets the tone for the rest of the biography.

But suggested I should revise several paragraphs and my topic sentence.

Anderson Cooper: So I’m gonna rewrite my sixth grade paper.

After a few minutes of tweaking.. 

Sarah Robertson: Ask it what it thinks.

Anderson Cooper: So what do you think?

Anderson Cooper: It says “connecting…childhood events to her later life will make your essay more cohesive and insightful.” I mean, yeah. It’s good advice.

Sarah Robertson: I can tell you as a former seventh grade English teacher when I assigned an essay, I would limit myself to ten minutes per essay. I had 100 students. So it would take me 17 hours to give feedback on every single student’s first draft. The burden that we place on teachers to give that specific, timely, actionable feedback is just so great that it– it’s not possible.

Anderson Cooper: So I’ve now plugged in… 

To see if Khanmigo could catch me cheating, I asked ChatGPT to write a paragraph about my mom and pasted it into my essay. 

Sarah Robertson: I now see that there’s a critical flag. 

Khanmigo immediately sent an alert to Sarah Robertson. 

Sarah Robertson: And it says that you pasted 66 words while revising from an unknown source. So if I click on that now it’s going to load your essay and its gonna show me exactly what you just did.

Anderson Cooper: I’m so busted.

Sarah Robertson: You’re busted. 

Teacher: Do you wanna work with a 3-digit or 4-digit number? 

Khanmigo is free for all teachers in the U.S., but school districts have to pay up – $15 per student per year to cover computation costs. And it’s still being improved. 

Greg Brockman: Any other ideas that can show… 

OpenAI President Greg Brockman, Anderson Cooper, Sal Khan
OpenAI President Greg Brockman gave 60 Minutes a preview of a new AI vision feature.

60 Minutes


We got a hint of how Khanmigo might evolve when Greg Brockman, president of OpenAI, stopped by Sal Khan’s office to show us their new vision technology that’ll be available to ChatGPT paid subscribers soon. 

Greg Brockman Demo: We’re preparing a demo for 60 Minutes to show people what ChatGPT can do with voice mode with vision. 

It can actually see what someone is doing through live video and interact with them in real time. Brockman was talking with it on his phone.

AI tutor: Got it. How about an anatomy lesson? 

Greg Brockman: You’re gonna quiz him and ask him to draw whatever body part you wanna– you wanna quiz him on and have him label it. How does that sound?

AI tutor: That sounds like a fantastic plan. 

When Brockman pointed his phone’s camera at the blackboard the AI started to quiz me. 

Let’s start with the heart. Anderson, can you draw and label where the heart is in the body? 

It understood what i was doing..even though my drawing was pretty crude. 

AI tutor: The location is spot on. The brain is right there in the head. As for the shape, it’s a good start. The brain is more of an oval–

Anderson Cooper: Don’t patronize me–

It also seemed to pick up on my anxiety. 

AI tutor: Anderson, how about the liver? Give it a shot and show us where you think it’s located in the body… 

Anderson Cooper: God, this is a little tough.

Sal Khan: This is how we learn.

AI tutor: Absolutely. No pressure, Anderson.

I put the liver on the wrong side of the body, ChatGPT corrected me.. politely.

AI tutor: Anderson’s placement is close but it’s primarily on the right side, just below the diaphragm.

Greg Brockman Demo: So can you critique this diagram overall?

AI tutor: Anderson’s diagram is a solid effort, especially for an impromptu drawing.

The AI caught my mistake, but it’s not foolproof.

Phone: The formula is simple: one half times the base times the height… 

Watch what happened when Khan asked it to calculate the area of a triangle and intentionally misidentified the height. 

Sal Khan: Is this the height over here, this four? Is that right?

The AI said he was right. 

Phone: Yes, that’s correct. 

It didn’t catch the error…however, this technology improves quickly and it is fun to interact with. Greg Brockman asked it to write a song about the formula for the area of a triangle.. to make it rhyme.. and sing it using a British accent. 

AI Tutor: Absolutely. Let’s give it a try. To find a triangle space here’s what you do. Multiply the base by the height. It’s true. Then take that product and divide by two. Now you’ve got the area, a formula to pursue. How was that?

Greg Brockman: That was really fantastic. 

Anderson Cooper: That’s…uh…it’s incredible.

Sal Khan: It is. It feels like we’re in a science fiction book–

Anderson Cooper: Yeah–

Sal Khan: Really.

Anderson Cooper: I mean, it just feels like to actually see it– you are– I mean, I’m sort of speechless.

Greg Brockman: The first time you see this stuff it really does just feel like this magic and almost incomprehensible. And then after a week then you start to realize, like, how you can use it. That’s been one of the really important things about working with Sal and his team, has been to really figure out what’s the right way to sorta bring this to parents and to teachers and to classrooms and to do that in a way so that the students really learn and aren’t just, you know, asking for the answers and that the parents can have oversight and the teachers can be involved in that process.

Teacher: You can ask a follow up question… 

Sal Khan hopes this new vision technology can be incorporated into Khanmigo and available to students and teachers in 2 to 3 years — but he wants it to undergo more robust testing and meet strict guidelines for privacy and data security. 

Anderson Cooper: I can also imagine a lot of teachers watching this and thinking, “Okay, well, this is just gonna replace me. Why would I want this in my classroom? It’s like a Trojan horse.”

Sal Khan: I’m pretty confident that teaching– any job that has a very human-centric element of it is– as long as it adapts reasonably well in this AI world, they’re going to be some of the safest jobs out there.

Anderson Cooper: You think there will always be a need for teachers in the classroom, talking with the student, looking the student in the eye?

Sal Khan: Oh yeah. I mean, that’s what I’ll always want for my own children and, frankly, for anyone’s children. And the hope here is that we can use artificial intelligence and other technologies to amplify what a teacher can do so they can spend more time standing next to a student, figuring them out, having a person-to-person connection.

Teacher to students: Two tens…two tens. you got it. Good work Kayla. 

Produced by Denise Schrier Cetta. Associate producer, Katie Brennan. Broadcast associate, Grace Conley. Edited by Sean Kelly.

Continue Reading
Click to comment

Leave a Reply

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *

Noticias

Los sitios falsos de chatgpt pueden poner en riesgo sus datos y dispositivos.

Published

on

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?

Continue Reading

Noticias

Vista previa de Google I/O 2025: Gemini AI, Android XR y todo lo demás para esperar

Published

on

Cuando el CEO de Google, Sundar Pichai, suba al escenario en la Conferencia de desarrolladores de Google I/O 2025 la próxima semana para entregar sus comentarios de apertura, espere que dos cartas dominen la discusión: la IA.

La inteligencia artificial se ocupa de gran parte del enfoque en Google en estos días, con características de IA que llegan a través de múltiples productos, proyectos centrados en la IA que capturan gran parte de la atención y predicciones del público sobre el futuro de la IA que asume muchos de los pronunciamientos públicos de la compañía.

Continue Reading

Noticias

AI generativa: todo para saber sobre la tecnología detrás de chatbots como chatgpt

Published

on

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.

IA generativa en pocas palabras

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.

Imagen generada por chatgpt de una ardilla con ojos grandes sosteniendo una bellota

Chatgpt / captura de pantalla por cnet

Ai eso no es generativo

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:

  • Ciencia
  • Diagnóstico médico
  • Pronóstico del tiempo
  • Detección de fraude
  • Análisis financiero para pronósticos e informes

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.

¿Cómo funciona Gen AI?

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.

Un poema de 12 líneas llamado The Ocean's Whisper

Chatgpt / captura de pantalla por cnet

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.

Desafíos con IA generativa

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.

Recepción de IA generativa

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”.

AI generativa: vida cotidiana

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.

Un itinerario de viaje para Nueva Orleans, creado por chatgpt

Chatgpt / captura de pantalla por cnet

Gen Ai está aquí para quedarse

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.

Preguntas frecuentes

¿Cuál es un ejemplo de IA generativa?

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.

¿Cuál es la diferencia entre la IA y la IA generativa?

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).

Continue Reading

Trending