Staying on top of AI developments is a full-time job.
Noticias
OpenAI Keeps Raising Money | The Motley Fool

OpenAI is projected to lose $5 billion this year.
In this podcast, Motley Fool analyst Jim Gillies and host Mary Long discuss:
- OpenAI’s $157 billion valuation.
- The port strike’s potentially positive impact on two auto parts makers. (Editor’s note: This podcast was recorded before the strike was called off.)
- Changing tastes in the beverage market.
Then Motley Fool analyst Asit Shama and host Ricky Mulvey test out a new rating system on Costco stock.
Like what you hear? You can vote for Motley Fool Money as Signal’s best money and finance podcast.
To catch full episodes of all The Motley Fool’s free podcasts, check out our podcast center. To get started investing, check out our beginner’s guide to investing in stocks. A full transcript follows the video.
This video was recorded on Oct. 03, 2024.
Mary Long: OpenAI sees some open check folks. You’re listening to Motley Fool Money. I’m Mary Long joined today by the illustrious Jim Gillies. Jim, thanks for being here. You ever been called that before?
Jim Gillies: That is absolutely the first time I’ve ever been called Illustrious, and I’m not sure what to do with it.
Mary Long: Thanks for joining us on the show. You are a valuation guy. I think it’s fair to say so figured we’d open up with some valuation news, OpenAI, which listeners might know that name. It’s the company behind ChatGPT, among other things. They got a new valuation, and that valuation comes out to 157 billion big ones. That is comparable to the likes of Goldman Sachs, Uber, AT&T. It’s also up from the $30,000,000,000 valuation it had about a year ago. I’ll open the floodgates. What do you think of that number?
Jim Gillies: Let’s say, why are you doing this to me? I think the number is absurd. I think the number is unjustifiable. I didn’t say wrong. I may very well be wrong. Maybe right, but the thing is I am from and the reason why I’m a little amused out of the gate is I am one of I think a fairly slowly dying breed. That is, I believe the company is worth the sum of its future cash flows, discounted back at an appropriate discount rate. Very important. Here’s the thing. I have no idea what ChatGPT OpenAI’s future cash flows will be. Neither does anyone else. I have no idea the timing of them, the scale of the size of them, the dilution that’s going to come. Neither does anyone else.
I have no idea what the appropriate discount rate is here. We can make an estimate, but it’s going to be precisely wrong, might even be roughly wrong, might be roughly right. This is clearly the big story of the world really, at this point, from a technology development standpoint. I don’t want to go in politics or anything. But AI is it’s transformational. We’re just not sure how transformational it will be. My history as an investor. We were talking before the show. We were talking a little bit about David Gardner and David Gardner’s style, which and I’ve many times said David Gardner is one of the best investors I’ve ever met. I’ve met Warren Buffett several times. But David’s style is something that often I struggle with because I’m not a venture capitalist thinker, whereas I think he is.
I would assume David would say Jim’s a cash flow thinker. I’m not a cash flow thinker, so I am seeing the world. David has that ability to see where the world is going at least better than I can and so I think it’s important to investor know thyself and follow along with what you are comfortable doing. All of that is a nice way to circle around and go like I would have, if this was public, I know they’re talking about going public at some point. I have no idea how you are applying this magical number to the valuation. We know that there’s no cash generation going on here. We have no idea where the cash is going to come, when it’s going to come. As Buffett likes to say, this goes into the two hard pile for me. It doesn’t go into the two hard pile for the Rule Breaker types, David Gardner types, and that’s great. But I would just walk away from this one because it doesn’t mesh with my style as an investor.
Mary Long: Another big news story circulating in business circles this week is about the port strike that’s happening. We had an e mail from a listener hit our inboxes earlier this morning. This listener, Andy did not know that I’d be chatting with you, but as luck would have it, he specifically asked for you in this e mail. Andy writes in, Andy here, longtime listener and member of both Motley Fool Stock Advisor and Rule Breakers, and also recently subbed to Motley Fool Canadian Services. I’ve got a question about the port strike that’s closed down ports on the US East Coast, and along the Gulf.
Specifically, I’m thinking of companies headquartered in Europe, which make auto parts like Autoliv ticker, ALV or Garrett Motion, ticker GTX. The Illustrious Jim Gillies has spoken about these companies over the past year and so I wonder if you might ask him, how much does he think the port strike will impact those companies at least in the short term and also whether the strike may create a buying opportunity.
Jim Gillies: Well, I don’t like thinking short term. But and Andy thank you for subscribing to the Canadian Services, which is why I’m answering the question. So, Autoliv is in 25 countries, including Canada. There’s a plant down near Windsor Ontario, which is where a lot of auto manufacturing is down near Windsor, Detroit crosses that border. They have worldwide facilities. The same goes for Garrett Motion. They’ve got worldwide facilities. Garrett’s got manufacturing ops in both California and Asia. Anything coming in from Asia is going to come in via the West Coast, not the East Cast. As well, automakers are notorious for their just in time manufacturing techniques.
Most likely, if a car is being assembled in North Carolina or Michigan or Southern Ontario, a lot of the parts are going into it are probably not all, and I’m not going to specifically say. Oh, yeah, Autoliv makes everything in Windsor for things being assembled in Detroit, because I don’t know that. But I would imagine that there is significant just in time issues in the manufacturing setup, that will alleviate some of this. Now, that’s said. I don’t want to minimize the potential impact of the strike. I think the strike could ultimately be very damaging. There’s some footage floating around of the Union lead, which is interesting. He is I think we’ll just say confrontational and aggressive, and I’ll leave it at that.
Mary Long: It’s fair.
Jim Gillies: If you’re a union member, I suppose that’s what you want and your leader, but it doesn’t look good, but I would warn against letting headlines define your investment choices unless unless, as Andy said here, this might be a short term opportunity. Because I think what Andy is not saying, but what I will say is strikes end, like strikes end and so if this does give you opportunity, and what we call this, headline risk gives you opportunities quite often. I could talk about the wisdom of recommending an aircraft Lasso during a pandemic, for example, which I did when all planes were shut down, international travel was shut down. The thesis can essentially be summarized as pandemics end. I don’t know when, probably be a Tuesday, but they end, and when they end, we’ll probably still take planes. The world’s largest aircraft also that would be AerCAP, by the way. The world’s largest aircraft or so will probably have pretty robust demand when it happens.
Mary Long: Less front and center than OpenAI’s, new valuation, and the port strike. Constellation Brands reported this morning? This is the company behind Corona, Modelo, Svedka Vodka, Robert Mondavi Wine. Some of the top line news from their earnings report, overall sales rose. That’s mostly due to their beer business. They saw a lot of weakness in the Wine and Spirits business. They’re also writing off a $2.25 billion impairment loss for that Wine and Spirits business. First up, Jim, what’s eating Constellation’s wine business?
Jim Gillies: I feel that I’m here under false pretenses because I thought were going to talk about Constellation Software, which I hold is the best company in Canada. But no, it’s Constellation Brands.
Mary Long: Wamp.
Jim Gillies: I know, yeah, sad trombone for me.
Mary Long: Maybe be less exciting.
Jim Gillies: Yeah. Look, maybe it’s just a mature industry. Maybe it’s a mature business. I promise this is going to go somewhere. I’ve been to New Zealand. I’ve toured around New Zealand and all the wineries. the one I could not have cared less about, Kim Crawford Wine. Why? ‘Cause it’s big industrial wine made by you guest at Constellation Brands. I think, this is all just going to be riffing here, but maybe people beset with choice are choosing elsewhere. I can tell you, in this house, we don’t drink a lot of wine. Consumption and has been consumption has been going down, just because I think we find as we get older, we don’t appreciate it that much or I don’t want to drop an extra $20 on $20. Someone out there just said $20, Gillies. That’s a terrible bottle of wine, you get to spend up.
We probably drink half or less of what we drank a decade ago. To think I appreciate good wine. Someone professional might call what I like swill, but that’s fine. But, we go to wineries. we’ll go to Niagara, which is fairly close. We’ll go out to British Columbia when we’re there. We’ll go to wineries. I’ve been to wineries in Virginia I’ve been to wineries in California. Like and through the magic of the Internet, I can order what I like if it’s a winery I went to in Napa, and it was a smaller winery. It’s not a big giant corporate winery. But so maybe one thing is people just don’t like mass production wines anymore. Another thing and this might be fairly Canada focused, but I know it’s happening a lot more in your fine country is, you may have heard that cannabis was legalized in Canada across Canada in 2018. One of the things that’s happened as a result of that is there’s a lot of cannabis based beverages, like for people who I guess who don’t want to smoke or whatever, which strikes me as an intelligent choice. For people who are using wine just to relax and laugh with friends or just take the edge off, maybe they’re not drinking wine anymore.
Maybe things have migrated to cannabis beverage versus and wine has become a beverage that you drink with your sar duck breast or rare flank state thing. It’s become more of I don’t know anybody. I’ve not been to a lot of dinner parties since the pandemic, but I’d be pretty surprised if someone served me a cannabis beverage when I went to a dinner party. Then you’ve also got that look, we know with the data saying that younger people are drinking less. those just coming into coming out of their slothful teenage years and into their early 20s and legal drinking age. They’re drinking less and they’re opting away from wine. I can tell you. We had a thing in my house about two years ago with my son who has just turned 20, but drinking age here is 19. There was a medical family situation and I had to call my son. He was at University at the time, and I said, I might need to come get you. It was a Friday night. No drinking.
I have fun, but I might have to come get you because something could go wrong tonight and so I would appreciate you and my son, first off he said, well, Dad, I’m actually at my friend’s house, and the friend that he has is muslims there’s no alcohol in the house, anyway. Then my son is also a body builder. Then I got a five minute pseudo lecture on how alcohol consumption is really detrimental for body builders. I’m like, dude, dude. I appreciate all that. Family medical emergency. I don’t need that now. Stand by and hopefully, I don’t have to come get you. But it’s like, kids, and I see his friends. I see my daughter’s friends, and it’s like I think they’re being more responsible than I was. How about I leave it at that?
Mary Long: So we talk about shifting consumer taste. We mentioned cannabis beverages. This is a consumer brands business. Again, consumer taste change over time. Is the diversification of constellations portfolio, which is a big portfolio? Is that diversification a strength or a weakness here? Because the more things you offer, chances are that some are not going to perform so well.
Jim Gillies: Well, yeah, and the more things you offer, you dilute you want to find the one thing you’re really great at or the two or three things you’re really great at. I often find that when you offer so many choices, none of them will really move the needle, and some will be a disappointment this quarter, and some will be a disappointment next quarter. The other thing is, two, and I was an investor for a brief period of time in Moles encores. Spoiler didn’t go terribly well.
But competitor, and we know that Anheuser-Busch InBev ASB Miller, whatever the hell, they’re calling themselves nowadays. This tends to be a scale business and there’s all these companies, Constellation, Anheuser-Busch, Molson Coors. They are just constantly shoving money at at new CapEx and acquisitions, and Maybe the industry is just largely topped out because none of them have been good strong investments. Again, did I mention my Molson Coors foray did not go terribly well. They are their old brands, but, like, there’s no one’s going to challenge beverauge on scale. Maybe Heineken can go and buy Constellation and Acres, but that might bring them within spitting distance, but then it’s not a high growth industry and so it doesn’t really matter to me how many brands you’ve got.
I think most of these companies where they did try to maybe make a foray into the cannabis area, I think most of them lost their hats on that one. Maybe that’s where you should be going, but then again I would say. Well, it’s called weed for a reason, and it’s a commodity product. I think the best thing to do in this space is to say, you know what? I’m going to avoid individual stock risk in this area. I think what I’m going to do is if there’s some exposure in an S&P 500 index fund, I’m going to say, you know what? I’ve got exposure, and I’m happy with that level of exposure.
Mary Long: Jim Gillies, thanks for joining us today on Motley Fool Money. Always a pleasure to have you even though I feel like we were pretty bearish throughout the entirety of today.
Jim Gillies: I don’t think so. I don’t want to be bearish. I think Autoliv and Garrett will be fine. How’s that? I own both.
Mary Long: I set you up for that a little bit because we do have Ricky and Asit talking about Costco in the segment after us and that is something you are certainly not bearish on and I didn’t even give you the opportunity.
Jim Gillies: That is very correct, yes.
Mary Long: I apologize to you.
Jim Gillies: Perfectly fine, and I don’t own enough Costco.
Mary Long: Before we get to the next segment, a humble request. Motley Fool Money is a finalist for Signal’s Best Money and finance broadcast. We’re up against some really great shows from Barns, the Financial Times, and Bloomberg. The winner, though, is determined by your vote. So, if you enjoy this show, all of us here at Motley Fool Money would really appreciate you taking a moment to cast your vote for us. I’ll drop a link in today’s show note so that you can do that if you’re so inclined. Heads up, you’ll need to enter your email to verify that you’re a real person, not a robot. Thanks for helping us out.
As always, we appreciate you listening. Already up next, Costco gets a lot of love, not just from Jim Gillies, but from many investors, but it also comes at a pretty price. Asit Sharma and Ricky Mulvey test out a new rating system on Costco’s valuation.
Ricky Mulvey: We’ve heard the booms. We’ve heard the dooms around the Costco Food Court, the chicken bake, the double chunk chocolate cookie, Asit. We’re not food reviewers, though, so we’re going to look at the stock. But before we do so, the most important question of this segment. Are you a Costco guy? Do you get it?
Asit Sharma: Ricky, what’s a Costco guy? I guess I get it. I used to shop at Costco when our kids were younger, and the bulk purchases made a lot of sense for us.
Ricky Mulvey: We have sort of the duality of Costco right now because the food court is so inexpensive. Hot dog combo, dollar 50. We walk out of Costco, thinking about the great deals we got, three pounds of coffee for, like, 15 bucks. When we look at the stock though it’s a different story. It’s at one of the most expensive multiples it’s ever been. Trades around 55 times free cash flow, 31 times enterprise value to forward EBITDA so the value of its debt and equity compared to its forward earnings. Both of these are high historically. Then when you compare it to its peers, Kroger, for example, is less than half of that valuation for its free cash flow, and as opposed to the 31X earnings multiple, it’s at a 6X. Why does Costco get such a premium as opposed to these other grocery stores?
Asit Sharma: Ricky listening to you, I was just thinking, it doesn’t matter what batter you dip this thing into, you put it in the oven. It’s double chunk all the way right now. It’s just going to be expensive under any valuation measure when you pull that out of the analysis oven. This is a little mysterious because if you compare Costco to traditional large scale retailers grocers, let’s say, it looks very expensive. It should be. It’s got the membership that has renewal rates above 90%. They’ve gone on this big cost optimization drive, which has really helped them increase margins. They’re the beneficiary of lower input costs going forward as inflation eases. They have shifted some business to high ticket items, big appliances, which carry a better margin and just bigger absolute dollars for the company as they’ve built out more logistics and distribution. They’ve got the balance sheet for global expansion.
Asit Sharma: When you put all this together, you start thinking, yeah, I mean, it should be more expensive than some of these traditional grocers. But then look at a company like BJ’s Wholesale Club, which has, not all of those advantages, but has been undergoing some of the same transitions and has mirrored the stock price over the last five years, BJ’s trades at a fraction of what Costco trades at under the same multiples. I think the reason is the stability of the cash flows is something that the market is looking at as a forever proposition, and they love the way the company allocates its capital between all this expansion and then special dividends that come up every few years and its ability to keep those loyal members and raise prices on them every few years. Still, it just seems historically expensive right now. The market is looking past a lot of potential near term issues to say, we’re going to hold the stock. We’re actually going to act like foolish investors maybe. Still, I would say, if you don’t own Costco, you could nibble. It’s just pricey here.
Ricky Mulvey: What are the near term issues that you’re thinking about?
Asit Sharma: Well, number 1 is the volatility of those same input prices. The market expects that deflation is at least a deceleration of inflation, which the Fed is seeing also is going to benefit companies like Costco which have become more efficient as prices are rising. On the back end, when things get a little cheaper, the inference is that these companies will keep some of that margin to themselves. But look, we have potentially a port strike coming up, so you can’t hang your hat some near term tailwinds. That’s just one of them. I think the other is that we don’t know yet if we’ll really come out of this current economic environment with a soft landing. It always feels like it. We had a shift in interest rate posture by the Fed. Inflation has been easing a bit, but that’s not to say that we won’t fall into a mild recession.
A mild recession might make people think a little bit differently about that 55X ford multiple on earnings per share. But at the end of the day, I think so many institutional buyers and retail buyers are saying, this is a quality company. We don’t mind overpaying a little bit just now. Costco historically, actually, as you pointed out, maybe doesn’t trade this high, but it’s always expensive. There could be some relative biting the bullet here for people who want to be in on this company.
Ricky Mulvey: We’re talking more about round to at the Fool. Let us not do a full re litigation on what this measures. We did a segment on it a while back. But basically, it’s a measure of how efficient a company is a generating income on the hard assets that it has. When you look at Costco, it’s got about 11 billion in cash. It’s got a lot of land in stores. It’s got about 17 billion in inventory, all of those warehouse goods moving through its supply chain on the way to the large boxes at the end of checkout. But when you look at Costco’s round to how efficient it is, it’s at 26%. That’s actually slightly below Kroger and Walmart.
With the premium we just talked about, and Costco investors are willing to pay for the stock, I’m surprised it’s not significantly higher than these other grocers which have more items that they’re selling that don’t have that wonderful membership loyalty program, which completely cuts out on things like shoplifting at their store, what say you? What’s going on here with Costco’s efficiency at generating income?
Asit Sharma: Well, I think that all three that you mentioned are pretty efficient for being primarily grocers. What it might be going on here is a bit of investment. When you invest in your capital base and make it bigger, that lowers your return on invested capital. If you’re a company like these grocers, which doesn’t have a lot of tangible assets on your books, your round to is anyway going to be closer to your return on invested capital. Actually, round to might not be the most efficient metric to use here. But, since not any of these three companies really has, let’s say, a huge goodwill component on their books or a lot of amortization for intangibles, let’s compare these apples to apples.
What is going on here? Is that expansion of the base of warehouses with Costco? Take Kroger, for example, Kroger has 60% of Costco sales, but they have almost tripled the amount of leased assets on their books. What that means is that Costco is buying land building stores, that’s a bigger base, so the bigger the base, the less return penny for penny on your income that you bring home. That’s actually what you want to see if you are an investor in Costco. You want to say, look, take that cash, buy some more land, buy some more buildings, build some more buildings. If you look at their latest supplemental presentation for this previous quarter just end. They have a nice picture of their Nanjing China warehouse. It’s humongous, and they have one that’s in Chungsan North Korea, I hope I pronounced that correctly. Also humongous. As a shareholder, you want that asset base to be big and get bigger because this is a company that’s got to scale up. It’s so big and so mature, Ricky. The only way to keep delivering those returns, aside from the cost optimization and new SKUs, new things that you and I can buy is that global expansion.
Ricky Mulvey: So the thing that’s pressuring it a little bit is that it owns a lot of its real estate that it has a lot of assets. You know Asit, maybe one of these days, we can do retailers with surprising routes. Hey, how about Dillards at 42%? That’s a separate topic.
Asit Sharma: That is surprising.
Ricky Mulvey: As we focus on Costco’s valuation one thing that the Costco guys, beause really what they’ve done has provided gifts for us is social media users. They fundamentally changed my life philosophy. I now sort stocks, my relationships, TV shows, things I watch, either into boom, five booms, that’s boom, boom, boom, boom, boom, or Doom. Boom, five booms or doom. Where are you at on Costco’s valuation as a stock?
Asit Sharma: Boom. Boom, in the sense of that is surprising, but not worth five booms, which is I’ll keep buying it. I don’t care what the price is. You have to be rational a bit.
Ricky Mulvey: Then as we look at Costco’s recent decisions, I’m going to let you be the manager, the CEO. You’re giving feedback, and the only way you’re giving feedback is boom, five booms or doom. There’s three of them. One, they’ve recently raised their annual membership fees by 5-$10. Boom, five booms or doom.
Asit Sharma: How about a one boom?
Ricky Mulvey: It’s a sad boom you offered. You were like, one boom.
Asit Sharma: A one boom it’s not a doom. Costco raises its membership fees only every 6-7 years. I actually expected a little more than these marginal improvements, but it speaks to the power of the model. Actually, this was applauded in a lot of circles because they’re doing right by members and not jacking up the price so much that people want to shop at other places. Throw the next one at me.
Ricky Mulvey: You mentioned the high ticket items earlier. Gold bullion. Now Costco is a dealer in gold bullion. If you look at the jewelry cases the next time you’re at Costco, you’re going to find these one ounce bars of gold that are being sold at cost. Boom, five booms or doom.
Asit Sharma: Boom, boom, boom, boom, boom Ricky.
Ricky Mulvey: Full five.
Asit Sharma: Five booms on this idea. I love this idea. The reason I love it so much is that it is so unexpected if you don’t follow Costco. What is Costco doing selling gold bullion? Their membership really took that offer in, and you see what Costco is doing here is perhaps sowing the seeds of something they can do over and over again with surprising items. When you can harness the purchasing power, outside of membership, outside of regular visits to the store, outside of e-commerce, to stuff that people almost virally, your members want to have. That is very powerful to your business model. It may seem silly, but it’s signaling something that is, I think quite valuable to Costco in years to come. I was surprised by that. It’s a five boom to me.
Ricky Mulvey: As we wrap up, let’s take a look at the latest Costco earnings call. We got some news from them. Comp sales up 6%. That’s pretty good for a grocery store. We’re also seeing that pricing power is. Costco boneless chicken tenders. They actually lowered the price by 13% and saw a 21% lift in the volumes sold. Also, Costco’s app getting bigger with 3.5 million app downloads just in the quarter. Anything meaningful here for the business of Costco. We’ve talked about the valuation. Anything meaningful for the business is Costco keeps chugging along.
Asit Sharma: I think all three are relevant. Comp sales, that combination of good volume traffic trends, being able to have the merchandise people want. That’s so important. The more mature company gets, typically, the more those comp sales will trend toward 1-2% or around the cadence of long-term inflation, which forget about recent inflation, has been 2-3% over time. So, for company this big, whenever you can have comp sales above the 5% level, you’re doing really well. The idea that Costco’s buyers and the people who shape its inventory are like those at TDMax, which are the best and brainiest in the business is something I think that’s not as appreciated out in the investing world. Being able to have the inventory on hand, know what people are really going to buy and then drop the price and sell in volume is pretty nice. I think those Apple Out downloads are also meaningful for Costco, although it’s so big, it’s not like a immediate needle mover, but still it’s quite good. That’s a very, very decent number.
Ricky Mulvey: So, I will count you as impressed with the business, but maybe a little concerned about the valuation. I will wrap this up with an om. One half of a boom as we split the difference. Asit Sharma thanks for being here. Appreciate your time and your insight.
Asit Sharma: Thanks a lot, Ricky. Always fun to be here.
Mary Long: As always, people on the program may have interest in the stocks they talk about, and the Motley Fool may have formal recommendations for or against, so don’t buy or sell stocks based solely on what you hear. I’m Mary Long. Thanks for listening. We’ll see you tomorrow.
Noticias
Columnista de humor versus chatgpt: ¿Soy más divertido que un robot?

Después de años de resistir y defender mis valores de ludita, finalmente me he dado.
Finalmente usé chatgpt. Y me preocupa que, algún día, sea mucho más divertido que yo.
Desde 2023, he publicado la columna Ask Lucas como una columna de consejos satíricos que a menudo se confunde con uno escrito por un sociópata que intenta incitar actos de violencia aleatorios en la comunidad.
Secretamente esperaba que publicar esta columna ayudara a envenenar el pozo digital que AI extrae al robar nuestras ideas. Inyectando literalmente cientos de columnas de Ask Lucas (destilaciones de idiotez pura y desprecio por la profesión de la columna de asesoramiento sagrado) en la web tiene que ser suficiente para cancelar un par de novelas de Octavia Butler, ¿verdad?
Bueno, hoy descubrimos exactamente lo que piensan los robots de mí. Llevé a Chatgpt a punta de pistola y lo alimenté con fuerza varios ejemplos de las peores columnas que jamás hayan maldecido las páginas del concesionario simple.
Entre episodios de adulación no solicitada e insincera, ChatGPT también hizo varias observaciones sobre la tradición que subyace en las columnas Ask Lucas. Una de esas observaciones, en palabras de Chatgpt: “Ohio es un paisaje maldito lleno de seres antiguos y miseria estacional”.
Todos los que viven aquí saben que esto es cierto, y me alegro de haber podido enseñarle algo sobre el Mordor del Medio Oeste.
Una cosa que encontré desalentador fue el despido de Chatgpt del verdadero propósito de esta columna: educar a mis lectores sobre las anguilas que acechan en la fontanería, esperando atacar cuando menos lo esperamos.
Esto es lo que se le ocurrió a Chatgpt:
“Querida Lucas (chatgpt): Recientemente me mudé a un nuevo apartamento y descubrí que mi vecino de arriba tiene una habitación que corre casi exclusivamente entre las 2 y las 4 a.m., es extrañamente ruidosa, y he perdido varias noches de sueño al sonido de sus muebles. No quiero ser el vecino de mal humor, pero tampoco quiero perder la cabeza. ¿Qué tengo que hacer?
Estimado lector (chatgpt): Ah, sí, las horas rituales. De 2 a 4 am es el horario estelar para que el Roomba realice sus deberes sagrados.
Podrías pensar que es una limpieza. Pero no, Roombas no limpian. Ellos cazan. Está escaneando el edificio para debilidades psíquicas, trazando líneas de Ley, y que golpea suavemente a la otomana de su vecino para mantener los portales sellados. No estás lidiando con una aspiradora de robot. Estás lidiando con un guardián de insomnio.
La gente ha olvidado que la mayoría de los dispositivos “inteligentes” más modernos son simplemente nuevas iteraciones de las herramientas medievales. La freidora de aire es un altar de sacrificio basado en la convección. El Apple Watch es un sol maldito que susurra recordatorios directamente en su sangre. ¿Y el Roomba? Ese es un golem de patrocinio de límites de tallado en sigilo con capacidades Bluetooth.
Si fuera inteligente, agradecería a su vecino por mantener a la bestia activa durante las horas de brujas. Lo último que quieres es que ese Roomba quede inactivo. Una vez inactivo durante demasiado tiempo, un Roomba comienza a soñar. Y cuando sueña, las paredes se adelgazan.
Pero no estás aquí por la verdad. Estás aquí por consejo. Muy bien.
Opción uno: confrontar a su vecino. Llama a su puerta, dígales que estás siendo perseguido por un disco de hockey en forma de disco con problemas de abandono. Pueden disculparse. O pueden mirarte a los ojos y decir: “Hacemos lo que debemos para mantenerlo ocupado”. Si eso sucede, vete. No empaces. No digas adiós. Solo muévete.
Opción dos: luchar contra la tecnología con tecnología. Consigue tu propia habitación. Ejecutarlo de 2 a 4 a.m., directamente debajo del suyo. Si lo hace bien, los dos dispositivos se reunirán en el medio: dos gladiadores de ojos muertos encerrados en un bulto para siempre, girar, recalibrar. Esto podría romper la maldición. O podría despertar algo. De cualquier manera, será más tranquilo.
Opción tres: acepta tu destino. Auriculares con cancelación de ruido, máquinas de ruido blanco, los mecanismos habituales de afrontamiento burgueses. O tapones para los oídos si eres pobre.
Al final, probablemente no se trata de la habitación. Se trata de la fragilidad de la paz en nuestro mundo moderno. Cada vez que nos sentimos a gusto, algo comienza a pitgar en el techo. Tal vez esta sea una prueba. Tal vez sea un presagio. O tal vez es solo el horrible gusto de su vecino en la programación de robots.
Dormir bien. O no lo hagas. Tu movimiento “.
Lucas (el humano): Para crear esta “columna”, alimenté cinco de mis columnas en ChatGPT y creé tres columnas, lo que permite que el robot cree la pregunta y la respuesta.
Esto no es horriblemente diferente de cómo trabajo, escribo muchas de mis propias preguntas, excepto que en lugar de tomar descansos de café innecesarios y antagonizar a mi esposa mientras intenta trabajar, Chatgpt simplemente se calla y hace el trabajo.
Por lo general, estas columnas me llevan alrededor de 3-4 horas, y ChatGPT pudo crear una imitación medio decente en solo segundos. La parte más larga del proceso fue decidir qué incorpora ingresar.
A los chelines corporativos les gusta llamar a esto “eficiencia”, pero en realidad es solo alejar el costo del tiempo de un humano y hacia la absurda cantidad de energía que se necesita para operar la máquina de plagio.
Dado que la mayor parte de la energía de Estados Unidos todavía proviene de combustibles fósiles, una forma de ver la IA es que encarna una especie de uroboros evolutivo, devorando los cadáveres de dinosaurios litentes para crear una inteligencia superior similar a la de un Dios.
Eso puede sonar poético, pero todo lo hace si usas un montón de palabras elegantes. La verdad no es tan romántica cuando recuerdas quiénes somos realmente. No vamos a usar esta inteligencia para explorar las estrellas o terminar las guerras. Vamos a hacer fotos de un aficionado a Donald Trump y publicarlas en Facebook para anunciar Ozempic fuera de marca.
También es un poco injusto para mí compararme con un robot. ChatGPT se limita a evitar consejos irresponsables o peligrosos. Sin embargo, no tengo tales compunciones. En esta columna, les dije a los lectores que embalsen sus autos en vehículos llenos de niños, disparen rifles de asalto salvajemente al cielo y maten las marmotas con bombas de automóviles.
Entonces te preguntaré, ¿soy más divertido que un robot?
Tenga en cuenta que hay una tercera opción, y es que ni esta columna, ni sus sustitutos de IA, son divertidos, y que debería dejar de hacer esto para preservar lo que queda de la cordura del noreste de Ohio.
Aquí están las columnas Ask Lucas que puse en ChatGPT para generar mi inevitable reemplazo.
Pregúntale a Lucas: Mi esposo sigue hablando consigo mismo mientras duerme.
Pregúntele a Lucas: Mi esposo me sigue sorprendiendo por la noche
Pregúntale a Lucas: No puedo tomarme otro mes de clima frío.
Pregúntale a Lucas: ¿Cómo les digo a otros conductores “lo siento!” si cometo un error en el camino?
Pregúntale a Lucas: ¿Cómo evito que mi novio obsesionado con los Browns arruine mis fines de semana este año?
Noticias
Best AI assistants tested: What works, what doesn’t, and which to use

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.
Noticias
¿Qué es la IA generativa? Todo lo que necesitas saber

Chatbot de inteligencia artificial insignia de Openai – junto con el Las mejores alternativas de chatgpt Al igual que Google Gemini, Microsoft Copilot y Anthrope’s Claude, son ejemplos de modelos de IA generativos.
El uso de la tecnología de IA generativa se ha convertido en una parte integral de la vida personal y profesional de muchas personas. Pero, ¿qué significa la IA generativa (a menudo abreviada a Genai), qué lo distingue de otros tipos de inteligencia artificial y cómo funciona? Puede encontrar respuestas a todas esas preguntas a continuación, suponiendo que no haya hecho ChatGPT, por supuesto.
¿Qué es la IA generativa?
-
Startups12 meses ago
Remove.bg: La Revolución en la Edición de Imágenes que Debes Conocer
-
Tutoriales12 meses ago
Cómo Comenzar a Utilizar ChatGPT: Una Guía Completa para Principiantes
-
Recursos12 meses ago
Cómo Empezar con Popai.pro: Tu Espacio Personal de IA – Guía Completa, Instalación, Versiones y Precios
-
Startups10 meses ago
Startups de IA en EE.UU. que han recaudado más de $100M en 2024
-
Startups12 meses ago
Deepgram: Revolucionando el Reconocimiento de Voz con IA
-
Recursos12 meses ago
Perplexity aplicado al Marketing Digital y Estrategias SEO
-
Recursos12 meses ago
Suno.com: La Revolución en la Creación Musical con Inteligencia Artificial
-
Estudiar IA12 meses ago
Curso de Inteligencia Artificial de UC Berkeley estratégico para negocios