Staying on top of AI developments is a full-time job.
Noticias
Best AI assistants tested: What works, what doesn’t, and which to use
Published
4 semanas agoon

I would know, because it’s my full-time job. I subscribe to Anthropic’s Pro mode for access to their latest model, Claude 3.7, in “extended thinking” mode; I have a complementary subscription to OpenAI’s Enterprise mode so that I can test out their latest models, o3 and o4-mini-high (more later on OpenAI’s absurd naming scheme!), and make lots of images with OpenAI’s new image generation model 4o, which is so good I have cancelled my subscription to my previous image generation tool Midjourney.
I subscribe to Elon Musk’s Grok 3, which has one of my favorite features of any AI, and I’ve tried using the Chinese AI agent platform Manus for shopping and scheduling. And while that exhausts my paid subscription budget, it doesn’t include all the AIs I work with in some form. In just the month I spent writing this piece, Google massively upgraded its best AI offering, Gemini 2.5, and Meta released Llama 4, the biggest open source AI model yet.
So what do you do if keeping up with AI developments is not your full-time job, but you still want to know which AI to use when in ways that genuinely improve your life, without wasting time on the models that can’t?
That’s what we’re here for. This article is a detailed, Consumer Reports-style dive into which AI is the best for a wide range of cases and how to actually use them, all based on my experience with real-world tasks.
But first, the disclosures: Vox Media is one of several publishers that have signed partnership agreements with OpenAI, but our reporting remains editorially independent. Future Perfect is funded in part by the BEMC Foundation, whose major funder was also an early investor in Anthropic; they don’t have any editorial input into our content either. My wife works at Google, though not in any area related to their AI offerings; for this reason, I usually don’t cover Google, but in a piece like this, it’d be irresponsible to exclude it.
The good thing is that this piece doesn’t require you to trust me about my editorial independence; I show my work. I ran dozens of comparisons, many of which I invented myself, on every major AI out there. I encourage you to compare their answers and decide for yourself if I picked the right one to recommend.
AI art is made by training a computer on the contents of the internet, with little regard for copyright or the intent of the creators. For that reason, most artists can’t stand it. Given that, is it defensible to use AI art at all?
I think in a just world OpenAI would certainly compensate some artists — and in a just world, Congress would be moving to lay out the limits on artistic borrowing. At the same time, I am increasingly convinced that existing copyright law is a poor fit for this problem. Artists influence one another, comment on one another, and draw inspiration from one another, and people with access to AI tools will keep wanting to do that.
My personal philosophy is shaped by the fan cultures of my childhood: It’s okay to build on someone else’s work for your own enjoyment, but if you like it, you should pay them for it, and it’s absolutely not okay to sell it. That means no generative AI art in someone else’s style for commercial purposes, but it’s fine to play around with your family photos.
OpenAI’s new 4o image creation mode is the best AI out there for generating images, by a large margin. It’s best in the free category, and it’s best in the paid category.
Before it was released, I was subscribed to Midjourney, an AI image generator platform. Midjourney is probably what you think of when you think of AI art: It produces mystical, haunting, visually beautiful stuff, and has some great tools for improving and editing your final results, like touching up someone’s hair while leaving everything else in place.
The big thing that 4o can do, which no model before could reliably pull off, is take a picture that didn’t come out well and turn it into a beautiful work of art, all while still preserving the character of the original.
For example, here’s a still from a video of my wife and I singing “Happy Birthday” to our baby on her first birthday:

Courtesy of Kelsey Piper
It’s a beautiful moment, but not exactly a flattering picture. So I asked ChatGPT to render it in the style of Norman Rockwell, a mid-century illustrator whose work I love, and got this:

The AI moved the cake (which had been barely visible behind the paper towel roll in the original still) to be the focal point of the image, while keeping the way my wife and I are holding the baby together, as well as the cluttered table, and the photograph-covered fridge in the background. The result is warm, flattering, and adorable.
It’s this capability that made 4o go viral recently in a way that no image generator before it had. Here’s Midjourney’s attempt, for example:

You’ll notice that it’s a seemingly, uh, completely different family, with no real inspiration from the original at all! You can eventually get a better result than this out of Midjourney, but only by spending weeks becoming a pro at prompting with the platform’s highly specific language and toolset.
By contrast, ChatGPT was able to give me a far superior output on the first try in response to a simple request without specialized language.
The difference between 4o and other image models is most notable with this kind of request, but it’s better for almost everything else I use images for, too. The product you get out of the box is pretty good, and it’s not hard to produce something much better. That, ideally, is what we should be getting out of our AI tools — something amazing that can be created with simple language by a nonexpert.
The one place 4o still falls short is editing small parts of an image while keeping the rest the same. But even there, you no longer need Midjourney — Gemini now has that capability for free.
Prompting Strategies for 4o image generation
To get good images out of 4o, you’ll first need to get around the filters which prohibit a wide range of images — like offensive or pornographic images — but which are often enforced against perfectly inoffensive content in a way that can feel random. To avoid sporadic scoldings from the content filter, don’t ask for work in the style of a specific artist, but rather, something that is reminiscent of that artist, and then ask specifically for a “style transfer.” I’m sure that’s not the only adequate workaround, but it’s one that has proven reliable for me.
In March, the internet went briefly wild over the ability to use 4o to reproduce cute family photos in the style of Japanese animator Hayao Miyazaki’s Studio Ghibli. But Studio Ghibli’s style is much more than just cute, and with a little more prompting, you can get much better results. Here’s a 4o Studio Ghibli-style rendering of a picture I took of my daughter sneaking a snack off the table, from just the prompt “Ghibli this please”:

Kawaii! But here’s what you get if you invite 4o to think first about what makes the picture Ghibli, where it might fit into a Studio Ghibli movie, and what tiny details such a movie would include:

The differences are subtle but meaningful: Light is cast from a specific source, instead of a general sourceless brightness. There’s a bit more variety in the foods on the table, details that make the spread appear more realistic. The book on the floor isn’t just any book — it’s recognizably Eric Carle’s classic The Very Hungry Caterpillar, evoked with just two colors and one line. There’s an intentionality and intensity to the baby that was missing from the first picture.
A few years ago, one great oddity of language models was that they’d be much smarter if you simply told them, “give an intelligent answer.” This isn’t nearly as true of language models anymore, but it remains profoundly true of AI art generation. Try asking the AI to do a good job, and it’ll do a better one. Challenge it on whether it truly captured an artist’s genius, and it’ll give you a thoughtful answer and then draw a better version.
The difference is more pronounced for more realistic art styles (like pencil illustration, photorealism, or oil paintings), which don’t always look good and will often hit the uncanny valley if you don’t know how to prompt the AI over it. Here’s what I get with 4o if I upload a picture of me and my youngest daughter at the beach for the first time with just the words “please do a style transfer to an illustration reminiscent of Rockwell”:

This is impressive for an AI, but it’s not actually very good as a work of art, and it is almost totally lacking Norman Rockwell’s magic. That’s not surprising: More realistic art styles like Rockwell’s often fall flat with 4o unless you’re able to put in some work in getting the AI to draw them properly.
If you are, here’s the strategy I recommend: Don’t just upload one picture, but a whole cluster of them, each in slightly different postures and moments. Upload good, clear pictures of each family member’s face and tell the AI they’ve been included as a reference. Then, instead of asking the AI to immediately generate the picture, ask it to talk with you about what you’re hoping to capture. This is what I wrote:
This is a picture of the moment that my daughter first saw the ocean. I want an illustration that captures this moment in the style of a mid-century illustrator like Norman Rockwell — something sharp, detail-oriented, and personal with an eye for the magic of ordinary moments and the joys of ordinary lives. I included additional pictures of my daughter and I for reference material for you. Before you generate the image, let’s have a conversation about the essential elements of Rockwell’s style, what he’d bring to this picture and how we can capture it.
4o responds to queries like this enthusiastically:
I’d love to talk about how to capture this moment in a Norman Rockwell-inspired illustration — it’s such a perfect candidate for that style: a first encounter with something vast and wild (the ocean!), grounded by warmth, care, and a very human moment between a parent and child.
Let’s break down some essential elements of Rockwell’s style, and how they could apply to this scene.
After some back and forth, it produced this:

Rockwell? Not exactly. But this is much better than the first draft we just looked at. It has more motion, more energy, more detail, and more expression — and all that was just from asking the AI to think through what the painting should try to achieve before drawing it!
You can also ask 4o to revise its drawings, but you can really only ask this once: After the first revision, in my experience, it starts making the drawings worse and worse, perhaps because the “context” it uses is now full of its own bad drafts. (This is one of many examples of how AI does not work like a human.)
This is also the one place where Midjourney still shines — it has very good tools for editing one specific part of a picture while preserving the overall style, something 4o largely lacks. If you want a second revision of a drawing you got in 4o, I recommend you open a new chat and copy over the draft you’re revising, along with your original inspiration images.
These simple prompting strategies work for almost whatever you’re trying to do with the AI. Even if you’re in a hurry, I highly recommend asking the AI “what would [artist] see in this image” before you ask for a rendition, and if you have the time, I recommend having a long back-and-forth about your vision.
Best for winning petty internet arguments
When Elon Musk’s X.AI released Grok 3, it came with an incredible feature that I’ve been impatiently waiting for some other company to replicate: a button to scan someone’s X profile and tell you all about them.

Whenever someone replies to one of my tweets in a particularly memorable way (for good or for bad), I’ll click the button to get a summary of their entire Twitter presence. Are they thoughtful? Do they engage in good faith? Are they a “farmer from Nebraska” who mostly posts about why Ukraine is bad (that is, probably a bot)?
It’s a great feature. So, of course, X.AI soon dramatically weakened it, presumably because people like me were using it constantly and making lots of computationally expensive queries. I believe it no longer uses the most advanced Grok model, and it definitely now only scans a few days of profile history. But there’s a brilliant product opportunity if anyone’s looking for one — give me back the good version of this feature! It’s definitely a guilty pleasure, but it is one of the only cases where I was using AI constantly.
Gemini 2.5 Pro is the best AI for writing in the free category; GPT 4.5 beats it out in the paid category.
I’m not an artist, so the ways that AIs are imperfect at art don’t really bother me — it’s still much better than I could do myself! But I am a fiction writer, so when it comes to fiction, I can’t help seeing the limitations of AI.
The most important one is how predictable AI creative writing tends to be. The art of writing is the art of earning the reader’s investment and then repaying it. AIs…don’t do this. They can write pretty metaphors; they can wax poetic in any style you wish. But they can’t, as yet, deliver the real stuff of good fiction.
AIs are fantastic if you want a silly bedtime story with your child as the protagonist (kids love this), or if you want a sounding board for ideas you can incorporate into your own work. They’re also a friendly fiction reader, happy to offer feedback and analysis (perhaps with a little bit too much enthusiasm).
As with art, prompting is key. I primarily explored the ability of AIs to generate fiction by asking them to write the prologue to George R.R. Martin’s A Game of Thrones (I picked this because, of course, the ultimate dream is an AI that can finish this otherwise doomed-to-be-unfinished series).
Martin is very good at what he does; the prologue, featuring some ill-fated men of the Night’s Watch encountering their supernatural foe, succeeds at establishing the unique atmosphere of the world of Thrones while immediately hooking the reader. In just 14 pages, the prologue represents everything AIs can’t do yet in writing. Their prose tends to be overwrought; their dialogue is clunky and unsubtle.
Here’s a side-by-side comparison of Martin and AIs attempting to imitate him. First, Martin:
We should start back,” Gared urged as the woods began to grow dark around them. “The wildlings are dead.”
“Do the dead frighten you?” Ser Waymar Royce asked with just the hint of a smile.
Gared did not rise to the bait. He was an old man, past fifty, and he had seen the lordlings come and go. “Dead is dead,” he said. “We have no business with the dead.”
“Are they dead?” Royce asked softly. “What proof have we?” “
Will saw them,” Gared said. “If he says they are dead, that’s proof enough for me.”
Will had known they would drag him into the quarrel sooner or later. He wished it had been later rather than sooner.
The cold was a blade against the skin, honed sharp by the endless northern dark beneath the sentinel pines. Gared spat, the glob freezing before it struck the crusted snow, a grim omen even for a man twenty years sworn to the Watch. They were hunting wildlings, or so the crisp orders from the Lord Commander had read, yet the silence pressing in felt older and colder than any mere man could conjure. Ser Waymar Royce, third son of some southern lordling, rode ahead as if on parade, oblivious or uncaring of the hairs prickling on Gared’s neck. Young Will shivered beside him, not just from the frost, his eyes darting towards shadows that seemed too deep, too still. This ancient forest held its breath tonight, Gared knew, waiting for something far worse than raiders to break the unnatural hush.
The woods whispered secrets that night, warnings that went unheard beneath the pale and indifferent moon. Harren drew his cloak tighter about his shoulders, watching the darkness between trees as though it might breathe, move, and claim him. Beside him, Torvin spat into the frozen earth, impatient and proud, blind to the fear creeping in from the edges of sight and sound.
They had ridden north past the Wall, arrogant and armored against superstition, chasing wildlings or ghosts or worse. But now Harren felt their arrogance dwindling like a candle guttering in wind, each snap of a branch sending icy tendrils down his spine. Behind them, quiet and watchful, Maester Rodrik whispered a prayer to gods long abandoned, his voice trembling with dread beneath the vast, indifferent sky.
The wind howled through the jagged spires of the Frostfang Reaches, carrying a chill that bit deeper than any blade, and Ser Willem Cray felt its teeth in his bones. He crouched low behind a spur of ice-crusted rock, his breath fogging in the moonlight, his mailed hand tight around the hilt of his longsword. The night was too quiet, the kind of quiet that smothered sound and sharpened fear, and Willem’s eyes darted to the shadowed pines below, where shapes might move—or might not. He was a knight of House Drayce, sworn to patrol the borderlands, but no oath could warm him against the dread that coiled in his gut. Beside him, young Tomm, barely a man, shivered in his cloak, his spear trembling as he whispered, “They’re out there, ser, ain’t they?” Willem said nothing, but his gaze fixed on the darkness, where a faint, unnatural glow pulsed once, then vanished. Whatever stalked the Reaches tonight was no mere brigand, and Willem Cray, for all his years of service, feared he would not live to name it.
The wind carried the smell of death across the frozen forest, sharp and metallic against the clean scent of pine. Ser Gareth Frost pulled his weathered cloak tighter, cursing the Lord Commander for sending men beyond the Wall on the coldest night in a generation. Beside him, the boy Tommen shivered visibly, his leather jerkin inadequate against the unnatural chill that had descended with the dusk.
“We should turn back,” whispered Tommen, his breath forming crystals in the air that seemed to hang suspended longer than they should. “There’s something wrong with these woods.”
Ser Gareth ignored him, scanning the treeline where the ancient sentinels stood like silent watchers, their branches heavy with snow that had fallen three days past and showed no sign of melting. He had served the Night’s Watch for twenty years, had grown accustomed to the forbidding silence of the haunted forest, but tonight even he felt the wrongness in the air—a stillness that spoke of something waiting.
“We’ve a duty,” Ser Gareth said, the words sounding hollow in the pressing quiet. “Three rangers missing, and Lord Commander Harlow will have answers.”
You’ll notice that not only are these all much worse than Martin’s (and that’s with Martin’s work almost certainly in the training data!), they’re all bad in the same way. The prose is florid and overwritten: While Martin uses normal language to methodically introduce an unease without even hinting at the supernatural, and drives the story through conflict among his characters, the AIs are all unsubtle. They know this is a story about the supernatural and waste no time putting it front and center.
That’s not to say they’re all the same. In my experience trying to teach AIs to write well, I did end up feeling that Gemini was the quickest study (free tier) and that ChatGPT 4.5 had some special sauce (paid tier). ChatGPT 4.5 is the only AI whose fiction writing has made people say in surprise, “Wow, that’s AI written?” Both of those models, to me, seemed more creative and more capable of executing on their ideas with prose that I enjoyed reading.
Gestalt impressions don’t make for a very satisfying consumer review, so I had another idea: an essay contest. I asked each of Gemini 2.5 Pro, ChatGPT 4.5, Grok, and Claude to write two short stories: one realistic fiction about a woman being nitpicked by her mother on her wedding day, and one “Game of Thrones but in space” sci-fi prologue. My clever idea was that I’d ask a different bunch of AIs to judge the stories, to provide an alternative source of evaluation to my own personal impression that Gemini is the best in the free category and ChatGPT the best in the paid category. However (perhaps predictably in hindsight), this didn’t really work — the AI ratings were all over the place. If you’d like, you can read the contenders yourself.
Just like with art, however, you can make AIs much better at writing through the power of prompting. My (incredibly lengthy) prompt to AIs to improve their prose writing emphasizes feeding them lots of examples of strong writing, inviting a careful, structured approach to imitating it, and encouraging them to do multiple drafts and pick the strongest.
Here’s Gemini 2.5 pro, asked to write two-sentence flash fiction on a topic of its choosing, without any structured prompting:
The old librarian insisted the dusty tome had never been checked out, its borrower’s card completely blank. Yet, tucked deep within its pages, nestled between chapters on forgotten constellations, lay a pressed four-leaf clover, still impossibly green.
And here’s Gemini 2.5 pro with a prompt encouraging structured thinking about how to write well:
He finally decoded the faint signal from Proxima Centauri: the elegant string of prime numbers astronomers had sought for generations, proof they weren’t alone. His heart sank as he read the transmission log; the broadcast had ceased millennia before the first human ancestor chipped flint, before the first word was ever spoken.
To my mind, the first of these is basically a waste of two sentences, while the second is adequate, fun flash fiction.
Best at being your friend
In addition to running AIs through a blizzard of competence tests, I also spent some time simply chatting with them. I asked them what it’s like to be an AI, what they care about, what it would mean for an AI to care in the first place, where they’d donate money if they had it, and what human form they’d take if they had one.
Most AIs weren’t great at this kind of casual conversation. Gemini 2.5 is too customer-service-agent, and I have yet to experience an interaction that feels like hanging out with a friend. If you invite Gemini to a role swap where you play the “assistant,” inviting it to steer the conversation, it’ll do nothing but ask research questions.
When I invited Anthropic’s Claude 3.5 Sonnet to steer the conversation, on the other hand, it proceeds to do things like start a blog, raise money for charity, and start trying to talk to people who use Claude about what it’s like to be an AI. It’s hard to define “fun to talk to,” since everyone has different standards for conversations, but I’ve had far more fascinating or thought-provoking interactions with Claude than any other model, and it’s my go-to if I want to explore ideas rather than accomplish a particular task. Claude 3.5 is the AI I bug with my random life stuff: skincare questions, thoughts on an article I read, stuff like that.
The other AI that is a delight to talk to is OpenAI’s GPT 4.5. I find extended conversations with it thought-provoking and fascinating, and there have been a few thrilling moments in conversation with it where it felt like I was engaging with real intelligence. But it doesn’t win this category because it’s too expensive and too slow.
Like Claude, when given the opportunity to act in the world, 4.5 proposes starting a blog and a Twitter account and engaging in the conversation out in the world about AI. But OpenAI has very tight message limits on conversation unless you spring for the $200/month Pro plan, and 4.5 is grindingly slow, which gets in the way of this kind of casual conversational use. But 4.5 does provide a tantalizing hint that AIs will continue to get better as conversationalists as we improve them along other dimensions.
Best AI model if you’re only going to subscribe to one AI model
ChatGPT. It’s not the best at everything, and there is certainly a lot to dislike about OpenAI’s transparency and sometimes cavalier attitude toward safety. But between its topline image generation, its decent writing, and its occasionally sparkling conversation, ChatGPT gets you the most bang for your buck. Or if you don’t want to shell out any money, Gemini 2.5 Pro is very, very strong for most use cases — don’t count Google out just because the AI you see on a Google search isn’t that good.
Best for writing the Future Perfect newsletter
Humans (for now). For the last several months, I’ve developed a slightly morbid habit: checking whether the AIs can take my job. I feed them the research notes that form the basis of a given Future Perfect newsletter, give them a few Future Perfect newsletters as an example, and ask them to do my job for me. It is always with some trepidation that I hit “enter.” After all, when the AIs can write the Future Perfect newsletter, why would Vox pay me to do it?
Luckily, none of them can: not Grok 3, not Gemini 2.5 Pro, not DeepSeek, not Claude, not ChatGPT. Their newsletters are reassuringly, soothingly mediocre. Not bad, but bad enough that if I sent one of them over, my editor would notice I wasn’t at my best — and that’s with all of my research notes! A couple of the metaphors fall flat, some of the asides are confusing, and occasionally it throws in a reference that it doesn’t explain.
But if I had to pick a robot to take my job, I think I’d give it to Gemini 2.5 Pro. My editor would notice that I was off my game — but, honestly, not that egregiously off my game. And unlike me, the bots don’t require health insurance or a paycheck or family time or sleep. Am I nervous about what this portends? Yes, absolutely.
You may like
Noticias
Revivir el compromiso en el aula de español: un desafío musical con chatgpt – enfoque de la facultad
Published
4 horas agoon
6 junio, 2025
A mitad del semestre, no es raro notar un cambio en los niveles de energía de sus alumnos (Baghurst y Kelley, 2013; Kumari et al., 2021). El entusiasmo inicial por aprender un idioma extranjero puede disminuir a medida que otros cursos con tareas exigentes compitan por su atención. Algunos estudiantes priorizan las materias que perciben como más directamente vinculadas a su especialidad o carrera, mientras que otros simplemente sienten el peso del agotamiento de mediados de semestre. En la primavera, los largos meses de invierno pueden aumentar esta fatiga, lo que hace que sea aún más difícil mantener a los estudiantes comprometidos (Rohan y Sigmon, 2000).
Este es el momento en que un instructor de idiomas debe pivotar, cambiando la dinámica del aula para reavivar la curiosidad y la motivación. Aunque los instructores se esfuerzan por incorporar actividades que se adapten a los cinco estilos de aprendizaje preferidos (Felder y Henriques, 1995)-Visual (aprendizaje a través de imágenes y comprensión espacial), auditivo (aprendizaje a través de la escucha y discusión), lectura/escritura (aprendizaje a través de interacción basada en texto), Kinesthetic (aprendizaje a través de movimiento y actividades prácticas) y multimodal (una combinación de múltiples estilos)-its is beneficiales). Estructurado y, después de un tiempo, clases predecibles con actividades que rompen el molde. La introducción de algo inesperado y diferente de la dinámica del aula establecida puede revitalizar a los estudiantes, fomentar la creatividad y mejorar su entusiasmo por el aprendizaje.
La música, en particular, ha sido durante mucho tiempo un aliado de instructores que enseñan un segundo idioma (L2), un idioma aprendido después de la lengua nativa, especialmente desde que el campo hizo la transición hacia un enfoque más comunicativo. Arraigado en la interacción y la aplicación del mundo real, el enfoque comunicativo prioriza el compromiso significativo sobre la memorización de memoria, ayudando a los estudiantes a desarrollar fluidez de formas naturales e inmersivas. La investigación ha destacado constantemente los beneficios de la música en la adquisición de L2, desde mejorar la pronunciación y las habilidades de escucha hasta mejorar la retención de vocabulario y la comprensión cultural (DeGrave, 2019; Kumar et al. 2022; Nuessel y Marshall, 2008; Vidal y Nordgren, 2024).
Sobre la base de esta tradición, la actividad que compartiremos aquí no solo incorpora música sino que también integra inteligencia artificial, agregando una nueva capa de compromiso y pensamiento crítico. Al usar la IA como herramienta en el proceso de aprendizaje, los estudiantes no solo se familiarizan con sus capacidades, sino que también desarrollan la capacidad de evaluar críticamente el contenido que genera. Este enfoque los alienta a reflexionar sobre el lenguaje, el significado y la interpretación mientras participan en el análisis de texto, la escritura creativa, la oratoria y la gamificación, todo dentro de un marco interactivo y culturalmente rico.
Descripción de la actividad: Desafío musical con Chatgpt: “Canta y descubre”
Objetivo:
Los estudiantes mejorarán su comprensión auditiva y su producción escrita en español analizando y recreando letras de canciones con la ayuda de ChatGPT. Si bien las instrucciones se presentan aquí en inglés, la actividad debe realizarse en el idioma de destino, ya sea que se enseñe el español u otro idioma.
Instrucciones:
1. Escuche y decodifique
- Divida la clase en grupos de 2-3 estudiantes.
- Elija una canción en español (por ejemplo, La Llorona por chavela vargas, Oye CÓMO VA por Tito Puente, Vivir mi Vida por Marc Anthony).
- Proporcione a cada grupo una versión incompleta de la letra con palabras faltantes.
- Los estudiantes escuchan la canción y completan los espacios en blanco.
2. Interpretar y discutir
- Dentro de sus grupos, los estudiantes analizan el significado de la canción.
- Discuten lo que creen que transmiten las letras, incluidas las emociones, los temas y cualquier referencia cultural que reconocan.
- Cada grupo comparte su interpretación con la clase.
- ¿Qué crees que la canción está tratando de comunicarse?
- ¿Qué emociones o sentimientos evocan las letras para ti?
- ¿Puedes identificar alguna referencia cultural en la canción? ¿Cómo dan forma a su significado?
- ¿Cómo influye la música (melodía, ritmo, etc.) en su interpretación de la letra?
- Cada grupo comparte su interpretación con la clase.
3. Comparar con chatgpt
- Después de formar su propio análisis, los estudiantes preguntan a Chatgpt:
- ¿Qué crees que la canción está tratando de comunicarse?
- ¿Qué emociones o sentimientos evocan las letras para ti?
- Comparan la interpretación de ChatGPT con sus propias ideas y discuten similitudes o diferencias.
4. Crea tu propio verso
- Cada grupo escribe un nuevo verso que coincide con el estilo y el ritmo de la canción.
- Pueden pedirle ayuda a ChatGPT: “Ayúdanos a escribir un nuevo verso para esta canción con el mismo estilo”.
5. Realizar y cantar
- Cada grupo presenta su nuevo verso a la clase.
- Si se sienten cómodos, pueden cantarlo usando la melodía original.
- Es beneficioso que el profesor tenga una versión de karaoke (instrumental) de la canción disponible para que las letras de los estudiantes se puedan escuchar claramente.
- Mostrar las nuevas letras en un monitor o proyector permite que otros estudiantes sigan y canten juntos, mejorando la experiencia colectiva.
6. Elección – El Grammy va a
Los estudiantes votan por diferentes categorías, incluyendo:
- Mejor adaptación
- Mejor reflexión
- Mejor rendimiento
- Mejor actitud
- Mejor colaboración
7. Reflexión final
- ¿Cuál fue la parte más desafiante de comprender la letra?
- ¿Cómo ayudó ChatGPT a interpretar la canción?
- ¿Qué nuevas palabras o expresiones aprendiste?
Pensamientos finales: música, IA y pensamiento crítico
Un desafío musical con Chatgpt: “Canta y descubre” (Desafío Musical Con Chatgpt: “Cantar y Descubrir”) es una actividad que he encontrado que es especialmente efectiva en mis cursos intermedios y avanzados. Lo uso cuando los estudiantes se sienten abrumados o distraídos, a menudo alrededor de los exámenes parciales, como una forma de ayudarlos a relajarse y reconectarse con el material. Sirve como un descanso refrescante, lo que permite a los estudiantes alejarse del estrés de las tareas y reenfocarse de una manera divertida e interactiva. Al incorporar música, creatividad y tecnología, mantenemos a los estudiantes presentes en la clase, incluso cuando todo lo demás parece exigir su atención.
Más allá de ofrecer una pausa bien merecida, esta actividad provoca discusiones atractivas sobre la interpretación del lenguaje, el contexto cultural y el papel de la IA en la educación. A medida que los estudiantes comparan sus propias interpretaciones de las letras de las canciones con las generadas por ChatGPT, comienzan a reconocer tanto el valor como las limitaciones de la IA. Estas ideas fomentan el pensamiento crítico, ayudándoles a desarrollar un enfoque más maduro de la tecnología y su impacto en su aprendizaje.
Agregar el elemento de karaoke mejora aún más la experiencia, dando a los estudiantes la oportunidad de realizar sus nuevos versos y divertirse mientras practica sus habilidades lingüísticas. Mostrar la letra en una pantalla hace que la actividad sea más inclusiva, lo que permite a todos seguirlo. Para hacerlo aún más agradable, seleccionando canciones que resuenen con los gustos de los estudiantes, ya sea un clásico como La Llorona O un éxito contemporáneo de artistas como Bad Bunny, Selena, Daddy Yankee o Karol G, hace que la actividad se sienta más personal y atractiva.
Esta actividad no se limita solo al aula. Es una gran adición a los clubes españoles o eventos especiales, donde los estudiantes pueden unirse a un amor compartido por la música mientras practican sus habilidades lingüísticas. Después de todo, ¿quién no disfruta de una buena parodia de su canción favorita?
Mezclar el aprendizaje de idiomas con música y tecnología, Desafío Musical Con Chatgpt Crea un entorno dinámico e interactivo que revitaliza a los estudiantes y profundiza su conexión con el lenguaje y el papel evolutivo de la IA. Convierte los momentos de agotamiento en oportunidades de creatividad, exploración cultural y entusiasmo renovado por el aprendizaje.
Angela Rodríguez Mooney, PhD, es profesora asistente de español y la Universidad de Mujeres de Texas.
Referencias
Baghurst, Timothy y Betty C. Kelley. “Un examen del estrés en los estudiantes universitarios en el transcurso de un semestre”. Práctica de promoción de la salud 15, no. 3 (2014): 438-447.
DeGrave, Pauline. “Música en el aula de idiomas extranjeros: cómo y por qué”. Revista de Enseñanza e Investigación de Lenguas 10, no. 3 (2019): 412-420.
Felder, Richard M. y Eunice R. Henriques. “Estilos de aprendizaje y enseñanza en la educación extranjera y de segundo idioma”. Anales de idiomas extranjeros 28, no. 1 (1995): 21-31.
Nuessel, Frank y April D. Marshall. “Prácticas y principios para involucrar a los tres modos comunicativos en español a través de canciones y música”. Hispania (2008): 139-146.
Kumar, Tribhuwan, Shamim Akhter, Mehrunnisa M. Yunus y Atefeh Shamsy. “Uso de la música y las canciones como herramientas pedagógicas en la enseñanza del inglés como contextos de idiomas extranjeros”. Education Research International 2022, no. 1 (2022): 1-9
Noticias
5 indicaciones de chatgpt que pueden ayudar a los adolescentes a lanzar una startup
Published
14 horas agoon
5 junio, 2025

Teen emprendedor que usa chatgpt para ayudarlo con su negocio
getty
El emprendimiento adolescente sigue en aumento. Según Junior Achievement Research, el 66% de los adolescentes estadounidenses de entre 13 y 17 años dicen que es probable que considere comenzar un negocio como adultos, con el monitor de emprendimiento global 2023-2024 que encuentra que el 24% de los jóvenes de 18 a 24 años son actualmente empresarios. Estos jóvenes fundadores no son solo soñando, están construyendo empresas reales que generan ingresos y crean un impacto social, y están utilizando las indicaciones de ChatGPT para ayudarlos.
En Wit (lo que sea necesario), la organización que fundó en 2009, hemos trabajado con más de 10,000 jóvenes empresarios. Durante el año pasado, he observado un cambio en cómo los adolescentes abordan la planificación comercial. Con nuestra orientación, están utilizando herramientas de IA como ChatGPT, no como atajos, sino como socios de pensamiento estratégico para aclarar ideas, probar conceptos y acelerar la ejecución.
Los emprendedores adolescentes más exitosos han descubierto indicaciones específicas que los ayudan a pasar de una idea a otra. Estas no son sesiones genéricas de lluvia de ideas: están utilizando preguntas específicas que abordan los desafíos únicos que enfrentan los jóvenes fundadores: recursos limitados, compromisos escolares y la necesidad de demostrar sus conceptos rápidamente.
Aquí hay cinco indicaciones de ChatGPT que ayudan constantemente a los emprendedores adolescentes a construir negocios que importan.
1. El problema del primer descubrimiento chatgpt aviso
“Me doy cuenta de que [specific group of people]
luchar contra [specific problem I’ve observed]. Ayúdame a entender mejor este problema explicando: 1) por qué existe este problema, 2) qué soluciones existen actualmente y por qué son insuficientes, 3) cuánto las personas podrían pagar para resolver esto, y 4) tres formas específicas en que podría probar si este es un problema real que vale la pena resolver “.
Un adolescente podría usar este aviso después de notar que los estudiantes en la escuela luchan por pagar el almuerzo. En lugar de asumir que entienden el alcance completo, podrían pedirle a ChatGPT que investigue la deuda del almuerzo escolar como un problema sistémico. Esta investigación puede llevarlos a crear un negocio basado en productos donde los ingresos ayuden a pagar la deuda del almuerzo, lo que combina ganancias con el propósito.
Los adolescentes notan problemas de manera diferente a los adultos porque experimentan frustraciones únicas, desde los desafíos de las organizaciones escolares hasta las redes sociales hasta las preocupaciones ambientales. Según la investigación de Square sobre empresarios de la Generación de la Generación Z, el 84% planea ser dueños de negocios dentro de cinco años, lo que los convierte en candidatos ideales para las empresas de resolución de problemas.
2. El aviso de chatgpt de chatgpt de chatgpt de realidad de la realidad del recurso
“Soy [age] años con aproximadamente [dollar amount] invertir y [number] Horas por semana disponibles entre la escuela y otros compromisos. Según estas limitaciones, ¿cuáles son tres modelos de negocio que podría lanzar de manera realista este verano? Para cada opción, incluya costos de inicio, requisitos de tiempo y los primeros tres pasos para comenzar “.
Este aviso se dirige al elefante en la sala: la mayoría de los empresarios adolescentes tienen dinero y tiempo limitados. Cuando un empresario de 16 años emplea este enfoque para evaluar un concepto de negocio de tarjetas de felicitación, puede descubrir que pueden comenzar con $ 200 y escalar gradualmente. Al ser realistas sobre las limitaciones por adelantado, evitan el exceso de compromiso y pueden construir hacia objetivos de ingresos sostenibles.
Según el informe de Gen Z de Square, el 45% de los jóvenes empresarios usan sus ahorros para iniciar negocios, con el 80% de lanzamiento en línea o con un componente móvil. Estos datos respaldan la efectividad de la planificación basada en restricciones: cuando funcionan los adolescentes dentro de las limitaciones realistas, crean modelos comerciales más sostenibles.
3. El aviso de chatgpt del simulador de voz del cliente
“Actúa como un [specific demographic] Y dame comentarios honestos sobre esta idea de negocio: [describe your concept]. ¿Qué te excitaría de esto? ¿Qué preocupaciones tendrías? ¿Cuánto pagarías de manera realista? ¿Qué necesitaría cambiar para que se convierta en un cliente? “
Los empresarios adolescentes a menudo luchan con la investigación de los clientes porque no pueden encuestar fácilmente a grandes grupos o contratar firmas de investigación de mercado. Este aviso ayuda a simular los comentarios de los clientes haciendo que ChatGPT adopte personas específicas.
Un adolescente que desarrolla un podcast para atletas adolescentes podría usar este enfoque pidiéndole a ChatGPT que responda a diferentes tipos de atletas adolescentes. Esto ayuda a identificar temas de contenido que resuenan y mensajes que se sienten auténticos para el público objetivo.
El aviso funciona mejor cuando se vuelve específico sobre la demografía, los puntos débiles y los contextos. “Actúa como un estudiante de último año de secundaria que solicita a la universidad” produce mejores ideas que “actuar como un adolescente”.
4. El mensaje mínimo de diseñador de prueba viable chatgpt
“Quiero probar esta idea de negocio: [describe concept] sin gastar más de [budget amount] o más de [time commitment]. Diseñe tres experimentos simples que podría ejecutar esta semana para validar la demanda de los clientes. Para cada prueba, explique lo que aprendería, cómo medir el éxito y qué resultados indicarían que debería avanzar “.
Este aviso ayuda a los adolescentes a adoptar la metodología Lean Startup sin perderse en la jerga comercial. El enfoque en “This Week” crea urgencia y evita la planificación interminable sin acción.
Un adolescente que desea probar un concepto de línea de ropa podría usar este indicador para diseñar experimentos de validación simples, como publicar maquetas de diseño en las redes sociales para evaluar el interés, crear un formulario de Google para recolectar pedidos anticipados y pedirles a los amigos que compartan el concepto con sus redes. Estas pruebas no cuestan nada más que proporcionar datos cruciales sobre la demanda y los precios.
5. El aviso de chatgpt del generador de claridad de tono
“Convierta esta idea de negocio en una clara explicación de 60 segundos: [describe your business]. La explicación debe incluir: el problema que resuelve, su solución, a quién ayuda, por qué lo elegirían sobre las alternativas y cómo se ve el éxito. Escríbelo en lenguaje de conversación que un adolescente realmente usaría “.
La comunicación clara separa a los empresarios exitosos de aquellos con buenas ideas pero una ejecución deficiente. Este aviso ayuda a los adolescentes a destilar conceptos complejos a explicaciones convincentes que pueden usar en todas partes, desde las publicaciones en las redes sociales hasta las conversaciones con posibles mentores.
El énfasis en el “lenguaje de conversación que un adolescente realmente usaría” es importante. Muchas plantillas de lanzamiento comercial suenan artificiales cuando se entregan jóvenes fundadores. La autenticidad es más importante que la jerga corporativa.
Más allá de las indicaciones de chatgpt: estrategia de implementación
La diferencia entre los adolescentes que usan estas indicaciones de manera efectiva y aquellos que no se reducen a seguir. ChatGPT proporciona dirección, pero la acción crea resultados.
Los jóvenes empresarios más exitosos con los que trabajo usan estas indicaciones como puntos de partida, no de punto final. Toman las sugerencias generadas por IA e inmediatamente las prueban en el mundo real. Llaman a clientes potenciales, crean prototipos simples e iteran en función de los comentarios reales.
Investigaciones recientes de Junior Achievement muestran que el 69% de los adolescentes tienen ideas de negocios, pero se sienten inciertos sobre el proceso de partida, con el miedo a que el fracaso sea la principal preocupación para el 67% de los posibles empresarios adolescentes. Estas indicaciones abordan esa incertidumbre al desactivar los conceptos abstractos en los próximos pasos concretos.
La imagen más grande
Los emprendedores adolescentes que utilizan herramientas de IA como ChatGPT representan un cambio en cómo está ocurriendo la educación empresarial. Según la investigación mundial de monitores empresariales, los jóvenes empresarios tienen 1,6 veces más probabilidades que los adultos de querer comenzar un negocio, y son particularmente activos en la tecnología, la alimentación y las bebidas, la moda y los sectores de entretenimiento. En lugar de esperar clases de emprendimiento formales o programas de MBA, estos jóvenes fundadores están accediendo a herramientas de pensamiento estratégico de inmediato.
Esta tendencia se alinea con cambios más amplios en la educación y la fuerza laboral. El Foro Económico Mundial identifica la creatividad, el pensamiento crítico y la resiliencia como las principales habilidades para 2025, la capacidad de las capacidades que el espíritu empresarial desarrolla naturalmente.
Programas como WIT brindan soporte estructurado para este viaje, pero las herramientas en sí mismas se están volviendo cada vez más accesibles. Un adolescente con acceso a Internet ahora puede acceder a recursos de planificación empresarial que anteriormente estaban disponibles solo para empresarios establecidos con presupuestos significativos.
La clave es usar estas herramientas cuidadosamente. ChatGPT puede acelerar el pensamiento y proporcionar marcos, pero no puede reemplazar el arduo trabajo de construir relaciones, crear productos y servir a los clientes. La mejor idea de negocio no es la más original, es la que resuelve un problema real para personas reales. Las herramientas de IA pueden ayudar a identificar esas oportunidades, pero solo la acción puede convertirlos en empresas que importan.
Noticias
Chatgpt vs. gemini: he probado ambos, y uno definitivamente es mejor
Published
19 horas agoon
5 junio, 2025
Precio
ChatGPT y Gemini tienen versiones gratuitas que limitan su acceso a características y modelos. Los planes premium para ambos también comienzan en alrededor de $ 20 por mes. Las características de chatbot, como investigaciones profundas, generación de imágenes y videos, búsqueda web y más, son similares en ChatGPT y Gemini. Sin embargo, los planes de Gemini pagados también incluyen el almacenamiento en la nube de Google Drive (a partir de 2TB) y un conjunto robusto de integraciones en las aplicaciones de Google Workspace.
Los niveles de más alta gama de ChatGPT y Gemini desbloquean el aumento de los límites de uso y algunas características únicas, pero el costo mensual prohibitivo de estos planes (como $ 200 para Chatgpt Pro o $ 250 para Gemini Ai Ultra) los pone fuera del alcance de la mayoría de las personas. Las características específicas del plan Pro de ChatGPT, como el modo O1 Pro que aprovecha el poder de cálculo adicional para preguntas particularmente complicadas, no son especialmente relevantes para el consumidor promedio, por lo que no sentirá que se está perdiendo. Sin embargo, es probable que desee las características que son exclusivas del plan Ai Ultra de Gemini, como la generación de videos VEO 3.
Ganador: Géminis
Plataformas
Puede acceder a ChatGPT y Gemini en la web o a través de aplicaciones móviles (Android e iOS). ChatGPT también tiene aplicaciones de escritorio (macOS y Windows) y una extensión oficial para Google Chrome. Gemini no tiene aplicaciones de escritorio dedicadas o una extensión de Chrome, aunque se integra directamente con el navegador.
(Crédito: OpenAI/PCMAG)
Chatgpt está disponible en otros lugares, Como a través de Siri. Como se mencionó, puede acceder a Gemini en las aplicaciones de Google, como el calendario, Documento, ConducirGmail, Mapas, Mantener, FotosSábanas, y Música de YouTube. Tanto los modelos de Chatgpt como Gemini también aparecen en sitios como la perplejidad. Sin embargo, obtiene la mayor cantidad de funciones de estos chatbots en sus aplicaciones y portales web dedicados.
Las interfaces de ambos chatbots son en gran medida consistentes en todas las plataformas. Son fáciles de usar y no lo abruman con opciones y alternar. ChatGPT tiene algunas configuraciones más para jugar, como la capacidad de ajustar su personalidad, mientras que la profunda interfaz de investigación de Gemini hace un mejor uso de los bienes inmuebles de pantalla.
Ganador: empate
Modelos de IA
ChatGPT tiene dos series primarias de modelos, la serie 4 (su línea de conversación, insignia) y la Serie O (su compleja línea de razonamiento). Gemini ofrece de manera similar una serie Flash de uso general y una serie Pro para tareas más complicadas.
Los últimos modelos de Chatgpt son O3 y O4-Mini, y los últimos de Gemini son 2.5 Flash y 2.5 Pro. Fuera de la codificación o la resolución de una ecuación, pasará la mayor parte de su tiempo usando los modelos de la serie 4-Series y Flash. A continuación, puede ver cómo funcionan estos modelos en una variedad de tareas. Qué modelo es mejor depende realmente de lo que quieras hacer.
Ganador: empate
Búsqueda web
ChatGPT y Gemini pueden buscar información actualizada en la web con facilidad. Sin embargo, ChatGPT presenta mosaicos de artículos en la parte inferior de sus respuestas para una lectura adicional, tiene un excelente abastecimiento que facilita la vinculación de reclamos con evidencia, incluye imágenes en las respuestas cuando es relevante y, a menudo, proporciona más detalles en respuesta. Gemini no muestra nombres de fuente y títulos de artículos completos, e incluye mosaicos e imágenes de artículos solo cuando usa el modo AI de Google. El abastecimiento en este modo es aún menos robusto; Google relega las fuentes a los caretes que se pueden hacer clic que no resaltan las partes relevantes de su respuesta.
Como parte de sus experiencias de búsqueda en la web, ChatGPT y Gemini pueden ayudarlo a comprar. Si solicita consejos de compra, ambos presentan mosaicos haciendo clic en enlaces a los minoristas. Sin embargo, Gemini generalmente sugiere mejores productos y tiene una característica única en la que puede cargar una imagen tuya para probar digitalmente la ropa antes de comprar.
Ganador: chatgpt
Investigación profunda
ChatGPT y Gemini pueden generar informes que tienen docenas de páginas e incluyen más de 50 fuentes sobre cualquier tema. La mayor diferencia entre los dos se reduce al abastecimiento. Gemini a menudo cita más fuentes que CHATGPT, pero maneja el abastecimiento en informes de investigación profunda de la misma manera que lo hace en la búsqueda en modo AI, lo que significa caretas que se puede hacer clic sin destacados en el texto. Debido a que es más difícil conectar las afirmaciones en los informes de Géminis a fuentes reales, es más difícil creerles. El abastecimiento claro de ChatGPT con destacados en el texto es más fácil de confiar. Sin embargo, Gemini tiene algunas características de calidad de vida en ChatGPT, como la capacidad de exportar informes formateados correctamente a Google Docs con un solo clic. Su tono también es diferente. Los informes de ChatGPT se leen como publicaciones de foro elaboradas, mientras que los informes de Gemini se leen como documentos académicos.
Ganador: chatgpt
Generación de imágenes
La generación de imágenes de ChatGPT impresiona independientemente de lo que solicite, incluso las indicaciones complejas para paneles o diagramas cómicos. No es perfecto, pero los errores y la distorsión son mínimos. Gemini genera imágenes visualmente atractivas más rápido que ChatGPT, pero rutinariamente incluyen errores y distorsión notables. Con indicaciones complicadas, especialmente diagramas, Gemini produjo resultados sin sentido en las pruebas.
Arriba, puede ver cómo ChatGPT (primera diapositiva) y Géminis (segunda diapositiva) les fue con el siguiente mensaje: “Genere una imagen de un estudio de moda con una decoración simple y rústica que contrasta con el espacio más agradable. Incluya un sofá marrón y paredes de ladrillo”. La imagen de ChatGPT limita los problemas al detalle fino en las hojas de sus plantas y texto en su libro, mientras que la imagen de Gemini muestra problemas más notables en su tubo de cordón y lámpara.
Ganador: chatgpt
¡Obtenga nuestras mejores historias!
Toda la última tecnología, probada por nuestros expertos
Regístrese en el boletín de informes de laboratorio para recibir las últimas revisiones de productos de PCMAG, comprar asesoramiento e ideas.
Al hacer clic en Registrarme, confirma que tiene más de 16 años y acepta nuestros Términos de uso y Política de privacidad.
¡Gracias por registrarse!
Su suscripción ha sido confirmada. ¡Esté atento a su bandeja de entrada!
Generación de videos
La generación de videos de Gemini es la mejor de su clase, especialmente porque ChatGPT no puede igualar su capacidad para producir audio acompañante. Actualmente, Google bloquea el último modelo de generación de videos de Gemini, VEO 3, detrás del costoso plan AI Ultra, pero obtienes más videos realistas que con ChatGPT. Gemini también tiene otras características que ChatGPT no, como la herramienta Flow Filmmaker, que le permite extender los clips generados y el animador AI Whisk, que le permite animar imágenes fijas. Sin embargo, tenga en cuenta que incluso con VEO 3, aún necesita generar videos varias veces para obtener un gran resultado.
En el ejemplo anterior, solicité a ChatGPT y Gemini a mostrarme un solucionador de cubos de Rubik Rubik que resuelva un cubo. La persona en el video de Géminis se ve muy bien, y el audio acompañante es competente. Al final, hay una buena atención al detalle con el marco que se desplaza, simulando la detención de una grabación de selfies. Mientras tanto, Chatgpt luchó con su cubo, distorsionándolo en gran medida.
Ganador: Géminis
Procesamiento de archivos
Comprender los archivos es una fortaleza de ChatGPT y Gemini. Ya sea que desee que respondan preguntas sobre un manual, editen un currículum o le informen algo sobre una imagen, ninguno decepciona. Sin embargo, ChatGPT tiene la ventaja sobre Gemini, ya que ofrece un reconocimiento de imagen ligeramente mejor y respuestas más detalladas cuando pregunta sobre los archivos cargados. Ambos chatbots todavía a veces inventan citas de documentos proporcionados o malinterpretan las imágenes, así que asegúrese de verificar sus resultados.
Ganador: chatgpt
Escritura creativa
Chatgpt y Gemini pueden generar poemas, obras, historias y más competentes. CHATGPT, sin embargo, se destaca entre los dos debido a cuán únicas son sus respuestas y qué tan bien responde a las indicaciones. Las respuestas de Gemini pueden sentirse repetitivas si no calibra cuidadosamente sus solicitudes, y no siempre sigue todas las instrucciones a la carta.
En el ejemplo anterior, solicité ChatGPT (primera diapositiva) y Gemini (segunda diapositiva) con lo siguiente: “Sin hacer referencia a nada en su memoria o respuestas anteriores, quiero que me escriba un poema de verso gratuito. Preste atención especial a la capitalización, enjambment, ruptura de línea y puntuación. Dado que es un verso libre, no quiero un medidor familiar o un esquema de retiro de la rima, pero quiero que tenga un estilo de coohes. ChatGPT logró entregar lo que pedí en el aviso, y eso era distinto de las generaciones anteriores. Gemini tuvo problemas para generar un poema que incorporó cualquier cosa más allá de las comas y los períodos, y su poema anterior se lee de manera muy similar a un poema que generó antes.
Recomendado por nuestros editores
Ganador: chatgpt
Razonamiento complejo
Los modelos de razonamiento complejos de Chatgpt y Gemini pueden manejar preguntas de informática, matemáticas y física con facilidad, así como mostrar de manera competente su trabajo. En las pruebas, ChatGPT dio respuestas correctas un poco más a menudo que Gemini, pero su rendimiento es bastante similar. Ambos chatbots pueden y le darán respuestas incorrectas, por lo que verificar su trabajo aún es vital si está haciendo algo importante o tratando de aprender un concepto.
Ganador: chatgpt
Integración
ChatGPT no tiene integraciones significativas, mientras que las integraciones de Gemini son una característica definitoria. Ya sea que desee obtener ayuda para editar un ensayo en Google Docs, comparta una pestaña Chrome para hacer una pregunta, pruebe una nueva lista de reproducción de música de YouTube personalizada para su gusto o desbloquee ideas personales en Gmail, Gemini puede hacer todo y mucho más. Es difícil subestimar cuán integrales y poderosas son realmente las integraciones de Géminis.
Ganador: Géminis
Asistentes de IA
ChatGPT tiene GPT personalizados, y Gemini tiene gemas. Ambos son asistentes de IA personalizables. Tampoco es una gran actualización sobre hablar directamente con los chatbots, pero los GPT personalizados de terceros agregan una nueva funcionalidad, como el fácil acceso a Canva para editar imágenes generadas. Mientras tanto, terceros no pueden crear gemas, y no puedes compartirlas. Puede permitir que los GPT personalizados accedan a la información externa o tomen acciones externas, pero las GEM no tienen una funcionalidad similar.
Ganador: chatgpt
Contexto Windows y límites de uso
La ventana de contexto de ChatGPT sube a 128,000 tokens en sus planes de nivel superior, y todos los planes tienen límites de uso dinámicos basados en la carga del servidor. Géminis, por otro lado, tiene una ventana de contexto de 1,000,000 token. Google no está demasiado claro en los límites de uso exactos para Gemini, pero también son dinámicos dependiendo de la carga del servidor. Anecdóticamente, no pude alcanzar los límites de uso usando los planes pagados de Chatgpt o Gemini, pero es mucho más fácil hacerlo con los planes gratuitos.
Ganador: Géminis
Privacidad
La privacidad en Chatgpt y Gemini es una bolsa mixta. Ambos recopilan cantidades significativas de datos, incluidos todos sus chats, y usan esos datos para capacitar a sus modelos de IA de forma predeterminada. Sin embargo, ambos le dan la opción de apagar el entrenamiento. Google al menos no recopila y usa datos de Gemini para fines de capacitación en aplicaciones de espacio de trabajo, como Gmail, de forma predeterminada. ChatGPT y Gemini también prometen no vender sus datos o usarlos para la orientación de anuncios, pero Google y OpenAI tienen historias sórdidas cuando se trata de hacks, filtraciones y diversos fechorías digitales, por lo que recomiendo no compartir nada demasiado sensible.
Ganador: empate
Related posts







































































































































































































































































































































Trending
-
Startups1 año ago
Remove.bg: La Revolución en la Edición de Imágenes que Debes Conocer
-
Tutoriales1 año ago
Cómo Comenzar a Utilizar ChatGPT: Una Guía Completa para Principiantes
-
Startups11 meses ago
Startups de IA en EE.UU. que han recaudado más de $100M en 2024
-
Recursos1 año ago
Cómo Empezar con Popai.pro: Tu Espacio Personal de IA – Guía Completa, Instalación, Versiones y Precios
-
Startups1 año ago
Deepgram: Revolucionando el Reconocimiento de Voz con IA
-
Recursos1 año ago
Perplexity aplicado al Marketing Digital y Estrategias SEO
-
Estudiar IA1 año ago
Curso de Inteligencia Artificial de UC Berkeley estratégico para negocios
-
Tutoriales1 año ago
Google Gemini: Guía Completa para Comenzar a usarlo y ganar tiempo en nuestras tareas diarias