ChatGPT, OpenAI’s text-generating AI chatbot, has taken the world by storm since its launch in November 2022. What started as a tool to supercharge productivity through writing essays and code with short text prompts has evolved into a behemoth with 300 million weekly active users.
2024 was a big year for OpenAI, from its partnership with Apple for its generative AI offering, Apple Intelligence, the release of GPT-4o with voice capabilities, and the highly-anticipated launch of its text-to-video model Sora.
OpenAI also faced its share of internal drama, including the notable exits of high-level execs like co-founder and longtime chief scientist Ilya Sutskever and CTO Mira Murati. OpenAI has also been hit with lawsuits from Alden Global Capital-owned newspapers alleging copyright infringement, as well as an injunction from Elon Musk to halt OpenAI’s transition to a for-profit.
In 2025, OpenAI is battling the perception that it’s ceding ground in the AI race to Chinese rivals like DeepSeek. The company has been trying to shore up its relationship with Washington as it simultaneously pursues an ambitious data center project, and as it reportedly lays the groundwork for one of the largest funding rounds in history.
Below, you’ll find a timeline of ChatGPT product updates and releases, starting with the latest, which we’ve been updating throughout the year. If you have any other questions, check out our ChatGPT FAQ here.
To see a list of 2024 updates, go here.
OpenAI leaders have been talking about allowing the open model to link up with OpenAI’s cloud-hosted models to improve its ability to respond to intricate questions, two sources familiar with the situation told TechCrunch.
OpenAI is preparing to launch an AI system that will be openly accessible, allowing users to download it for free without any API restrictions. Aidan Clark, OpenAI’s VP of research, is spearheading the development of the open model, which is in the very early stages, sources familiar with the situation told TechCrunch.
OpenAI released a new AI model called GPT-4.1 in mid-April. However, multiple independent tests indicate that the model is less reliable than previous OpenAI releases. The company skipped that step — sending safety cards for GPT-4.1 — claiming in a statement to TechCrunch that “GPT-4.1 is not a frontier model, so there won’t be a separate system card released for it.”
Questions have been raised regarding OpenAI’s transparency and procedures for testing models after a difference in benchmark outcomes was detected by first- and third-party benchmark results for the o3 AI model. OpenAI introduced o3 in December, stating that the model could solve approximately 25% of questions on FrontierMath, a difficult math problem set. Epoch AI, the research institute behind FrontierMath, discovered that o3 achieved a score of approximately 10%, which was significantly lower than OpenAI’s top-reported score.
OpenAI has launched a new API feature called Flex processing that allows users to use AI models at a lower cost but with slower response times and occasional resource unavailability. Flex processing is available in beta on the o3 and o4-mini reasoning models for non-production tasks like model evaluations, data enrichment, and asynchronous workloads.
OpenAI has rolled out a new system to monitor its AI reasoning models, o3 and o4 mini, for biological and chemical threats. The system is designed to prevent models from giving advice that could potentially lead to harmful attacks, as stated in OpenAI’s safety report.
OpenAI has released two new reasoning models, o3 and o4 mini, just two days after launching GPT-4.1. The company claims o3 is the most advanced reasoning model it has developed, while o4-mini is said to provide a balance of price, speed, and performance. The new models stand out from previous reasoning models because they can use ChatGPT features like web browsing, coding, and image processing and generation. But they hallucinate more than several of OpenAI’s previous models.
Open AI introduced a new section called “library” to make it easier for users to create images on mobile and web platforms, per the company’s X post.
OpenAI said on Tuesday that it might revise its safety standards if “another frontier AI developer releases a high-risk system without comparable safeguards.” The move shows how commercial AI developers face more pressure to rapidly implement models due to the increased competition.
OpenAI is currently in the early stages of developing its own social media platform to compete with Elon Musk’s X and Mark Zuckerberg’s Instagram and Threads, according to The Verge. It is unclear whether OpenAI intends to launch the social network as a standalone application or incorporate it into ChatGPT.
OpenAI will discontinue its largest AI model, GPT-4.5, from its API even though it was just launched in late February. GPT-4.5 will be available in a research preview for paying customers. Developers can use GPT-4.5 through OpenAI’s API until July 14; then, they will need to switch to GPT-4.1, which was released on April 14.
OpenAI has launched three members of the GPT-4.1 model — GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano — with a specific focus on coding capabilities. It’s accessible via the OpenAI API but not ChatGPT. In the competition to develop advanced programming models, GPT-4.1 will rival AI models such as Google’s Gemini 2.5 Pro, Anthropic’s Claude 3.7 Sonnet, and DeepSeek’s upgraded V3.
OpenAI plans to sunset GPT-4, an AI model introduced more than two years ago, and replace it with GPT-4o, the current default model, per changelog. It will take effect on April 30. GPT-4 will remain available via OpenAI’s API.
OpenAI may launch several new AI models, including GPT-4.1, soon, The Verge reported, citing anonymous sources. GPT-4.1 would be an update of OpenAI’s GPT-4o, which was released last year. On the list of upcoming models are GPT-4.1 and smaller versions like GPT-4.1 mini and nano, per the report.
OpenAI started updating ChatGPT to enable the chatbot to remember previous conversations with a user and customize its responses based on that context. This feature is rolling out to ChatGPT Pro and Plus users first, excluding those in the U.K., EU, Iceland, Liechtenstein, Norway, and Switzerland.
It looks like OpenAI is working on a watermarking feature for images generated using GPT-4o. AI researcher Tibor Blaho spotted a new “ImageGen” watermark feature in the new beta of ChatGPT’s Android app. Blaho also found mentions of other tools: “Structured Thoughts,” “Reasoning Recap,” “CoT Search Tool,” and “l1239dk1.”
OpenAI is offering its $20-per-month ChatGPT Plus subscription tier for free to all college students in the U.S. and Canada through the end of May. The offer will let millions of students use OpenAI’s premium service, which offers access to the company’s GPT-4o model, image generation, voice interaction, and research tools that are not available in the free version.
More than 130 million users have created over 700 million images since ChatGPT got the upgraded image generator on March 25, according to COO of OpenAI Brad Lightcap. The image generator was made available to all ChatGPT users on March 31, and went viral for being able to create Ghibli-style photos.
The Arc Prize Foundation, which develops the AI benchmark tool ARC-AGI, has updated the estimated computing costs for OpenAI’s o3 “reasoning” model managed by ARC-AGI. The organization originally estimated that the best-performing configuration of o3 it tested, o3 high, would cost approximately $3,000 to address a single problem. The Foundation now thinks the cost could be much higher, possibly around $30,000 per task.
In a series of posts on X, OpenAI CEO Sam Altman said the company’s new image-generation tool’s popularity may cause product releases to be delayed. “We are getting things under control, but you should expect new releases from OpenAI to be delayed, stuff to break, and for service to sometimes be slow as we deal with capacity challenges,” he wrote.
OpeanAI intends to release its “first” open language model since GPT-2 “in the coming months.” The company plans to host developer events to gather feedback and eventually showcase prototypes of the model. The first developer event is to be held in San Francisco, with sessions to follow in Europe and Asia.
OpenAI made a notable change to its content moderation policies after the success of its new image generator in ChatGPT, which went viral for being able to create Studio Ghibli-style images. The company has updated its policies to allow ChatGPT to generate images of public figures, hateful symbols, and racial features when requested. OpenAI had previously declined such prompts due to the potential controversy or harm they may cause. However, the company has now “evolved” its approach, as stated in a blog post published by Joanne Jang, the lead for OpenAI’s model behavior.
OpenAI wants to incorporate Anthropic’s Model Context Protocol (MCP) into all of its products, including the ChatGPT desktop app. MCP, an open-source standard, helps AI models generate more accurate and suitable responses to specific queries, and lets developers create bidirectional links between data sources and AI applications like chatbots. The protocol is currently available in the Agents SDK, and support for the ChatGPT desktop app and Responses API will be coming soon, OpenAI CEO Sam Altman said.
The latest update of the image generator on OpenAI’s ChatGPT has triggered a flood of AI-generated memes in the style of Studio Ghibli, the Japanese animation studio behind blockbuster films like “My Neighbor Totoro” and “Spirited Away.” The burgeoning mass of Ghibli-esque images have sparked concerns about whether OpenAI has violated copyright laws, especially since the company is already facing legal action for using source material without authorization.
OpenAI expects its revenue to triple to $12.7 billion in 2025, fueled by the performance of its paid AI software, Bloomberg reported, citing an anonymous source. While the startup doesn’t expect to reach positive cash flow until 2029, it expects revenue to increase significantly in 2026 to surpass $29.4 billion, the report said.
OpenAI on Tuesday rolled out a major upgrade to ChatGPT’s image-generation capabilities: ChatGPT can now use the GPT-4o model to generate and edit images and photos directly. The feature went live earlier this week in ChatGPT and Sora, OpenAI’s AI video-generation tool, for subscribers of the company’s Pro plan, priced at $200 a month, and will be available soon to ChatGPT Plus subscribers and developers using the company’s API service. The company’s CEO Sam Altman said on Wednesday, however, that the release of the image generation feature to free users would be delayed due to higher demand than the company expected.
Brad Lightcap, OpenAI’s chief operating officer, will lead the company’s global expansion and manage corporate partnerships as CEO Sam Altman shifts his focus to research and products, according to a blog post from OpenAI. Lightcap, who previously worked with Altman at Y Combinator, joined the Microsoft-backed startup in 2018. OpenAI also said Mark Chen would step into the expanded role of chief research officer, and Julia Villagra will take on the role of chief people officer.
OpenAI has updated its AI voice assistant with improved chatting capabilities, according to a video posted on Monday (March 24) to the company’s official media channels. The update enables real-time conversations, and the AI assistant is said to be more personable and interrupts users less often. Users on ChatGPT’s free tier can now access the new version of Advanced Voice Mode, while paying users will receive answers that are “more direct, engaging, concise, specific, and creative,” a spokesperson from OpenAI told TechCrunch.
OpenAI and Meta have separately engaged in discussions with Indian conglomerate Reliance Industries regarding potential collaborations to enhance their AI services in the country, per a report by The Information. One key topic being discussed is Reliance Jio distributing OpenAI’s ChatGPT. Reliance has proposed selling OpenAI’s models to businesses in India through an application programming interface (API) so they can incorporate AI into their operations. Meta also plans to bolster its presence in India by constructing a large 3GW data center in Jamnagar, Gujarat. OpenAI, Meta, and Reliance have not yet officially announced these plans.
Noyb, a privacy rights advocacy group, is supporting an individual in Norway who was shocked to discover that ChatGPT was providing false information about him, stating that he had been found guilty of killing two of his children and trying to harm the third. “The GDPR is clear. Personal data has to be accurate,” said Joakim Söderberg, data protection lawyer at Noyb, in a statement. “If it’s not, users have the right to have it changed to reflect the truth. Showing ChatGPT users a tiny disclaimer that the chatbot can make mistakes clearly isn’t enough. You can’t just spread false information and in the end add a small disclaimer saying that everything you said may just not be true.”
OpenAI has added new transcription and voice-generating AI models to its APIs: a text-to-speech model, “gpt-4o-mini-tts,” that delivers more nuanced and realistic sounding speech, as well as two speech-to-text models called “gpt-4o-transcribe” and “gpt-4o-mini-transcribe”. The company claims they are improved versions of what was already there and that they hallucinate less.
OpenAI has introduced o1-pro in its developer API. OpenAI says its o1-pro uses more computing than its o1 “reasoning” AI model to deliver “consistently better responses.” It’s only accessible to select developers who have spent at least $5 on OpenAI API services. OpenAI charges $150 for every million tokens (about 750,000 words) input into the model and $600 for every million tokens the model produces. It costs twice as much as OpenAI’s GPT-4.5 for input and 10 times the price of regular o1.
Noam Brown, who heads AI reasoning research at OpenAI, thinks that certain types of AI models for “reasoning” could have been developed 20 years ago if researchers had understood the correct approach and algorithms.
OpenAI CEO Sam Altman said, in a post on X, that the company has trained a “new model” that’s “really good” at creative writing. He posted a lengthy sample from the model given the prompt “Please write a metafictional literary short story about AI and grief.” OpenAI has not extensively explored the use of AI for writing fiction. The company has mostly concentrated on challenges in rigid, predictable areas such as math and programming. And it turns out that it might not be that great at creative writing at all.
we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right.
PROMPT:
Please write a metafictional literary short story…
— Sam Altman (@sama) March 11, 2025
OpenAI rolled out new tools designed to help developers and businesses build AI agents — automated systems that can independently accomplish tasks — using the company’s own AI models and frameworks. The tools are part of OpenAI’s new Responses API, which enables enterprises to develop customized AI agents that can perform web searches, scan through company files, and navigate websites, similar to OpenAI’s Operator product. The Responses API effectively replaces OpenAI’s Assistants API, which the company plans to discontinue in the first half of 2026.
OpenAI intends to release several “agent” products tailored for different applications, including sorting and ranking sales leads and software engineering, according to a report from The Information. One, a “high-income knowledge worker” agent, will reportedly be priced at $2,000 a month. Another, a software developer agent, is said to cost $10,000 a month. The most expensive rumored agents, which are said to be aimed at supporting “PhD-level research,” are expected to cost $20,000 per month. The jaw-dropping figure is indicative of how much cash OpenAI needs right now: The company lost roughly $5 billion last year after paying for costs related to running its services and other expenses. It’s unclear when these agentic tools might launch or which customers will be eligible to buy them.
The latest version of the macOS ChatGPT app allows users to edit code directly in supported developer tools, including Xcode, VS Code, and JetBrains. ChatGPT Plus, Pro, and Team subscribers can use the feature now, and the company plans to roll it out to more users like Enterprise, Edu, and free users.
According to a new report from VC firm Andreessen Horowitz (a16z), OpenAI’s AI chatbot, ChatGPT, experienced solid growth in the second half of 2024. It took ChatGPT nine months to increase its weekly active users from 100 million in November 2023 to 200 million in August 2024, but it only took less than six months to double that number once more, according to the report. ChatGPT’s weekly active users increased to 300 million by December 2024 and 400 million by February 2025. ChatGPT has experienced significant growth recently due to the launch of new models and features, such as GPT-4o, with multimodal capabilities. ChatGPT usage spiked from April to May 2024, shortly after that model’s launch.
OpenAI has effectively canceled the release of o3 in favor of what CEO Sam Altman is calling a “simplified” product offering. In a post on X, Altman said that, in the coming months, OpenAI will release a model called GPT-5 that “integrates a lot of [OpenAI’s] technology,” including o3, in ChatGPT and its API. As a result of that roadmap decision, OpenAI no longer plans to release o3 as a standalone model.
A commonly cited stat is that ChatGPT requires around 3 watt-hours of power to answer a single question. Using OpenAI’s latest default model for ChatGPT, GPT-4o, as a reference, nonprofit AI research institute Epoch AI found the average ChatGPT query consumes around 0.3 watt-hours. However, the analysis doesn’t consider the additional energy costs incurred by ChatGPT with features like image generation or input processing.
In response to pressure from rivals like DeepSeek, OpenAI is changing the way its o3-mini model communicates its step-by-step “thought” process. ChatGPT users will see an updated “chain of thought” that shows more of the model’s “reasoning” steps and how it arrived at answers to questions.
OpenAI is now allowing anyone to use ChatGPT web search without having to log in. While OpenAI had previously allowed users to ask ChatGPT questions without signing in, responses were restricted to the chatbot’s last training update. This only applies through ChatGPT.com, however. To use ChatGPT in any form through the native mobile app, you will still need to be logged in.
OpenAI announced a new AI “agent” called deep research that’s designed to help people conduct in-depth, complex research using ChatGPT. OpenAI says the “agent” is intended for instances where you don’t just want a quick answer or summary, but instead need to assiduously consider information from multiple websites and other sources.
OpenAI used the subreddit r/ChangeMyView to measure the persuasive abilities of its AI reasoning models. OpenAI says it collects user posts from the subreddit and asks its AI models to write replies, in a closed environment, that would change the Reddit user’s mind on a subject. The company then shows the responses to testers, who assess how persuasive the argument is, and finally OpenAI compares the AI models’ responses to human replies for that same post.
OpenAI launched a new AI “reasoning” model, o3-mini, the newest in the company’s o family of models. OpenAI first previewed the model in December alongside a more capable system called o3. OpenAI is pitching its new model as both “powerful” and “affordable.”
A new report from app analytics firm Appfigures found that over half of ChatGPT’s mobile users are under age 25, with users between ages 50 and 64 making up the second largest age demographic. The gender gap among ChatGPT users is even more significant. Appfigures estimates that across age groups, men make up 84.5% of all users.
OpenAI launched ChatGPT Gov designed to provide U.S. government agencies an additional way to access the tech. ChatGPT Gov includes many of the capabilities found in OpenAI’s corporate-focused tier, ChatGPT Enterprise. OpenAI says that ChatGPT Gov enables agencies to more easily manage their own security, privacy, and compliance, and could expedite internal authorization of OpenAI’s tools for the handling of non-public sensitive data.
Younger Gen Zers are embracing ChatGPT, for schoolwork, according to a new survey by the Pew Research Center. In a follow-up to its 2023 poll on ChatGPT usage among young people, Pew asked ~1,400 U.S.-based teens ages 13 to 17 whether they’ve used ChatGPT for homework or other school-related assignments. Twenty-six percent said that they had, double the number two years ago. Just over half of teens responding to the poll said they think it’s acceptable to use ChatGPT for researching new subjects. But considering the ways ChatGPT can fall short, the results are possibly cause for alarm.
OpenAI says that it might store chats and associated screenshots from customers who use Operator, the company’s AI “agent” tool, for up to 90 days — even after a user manually deletes them. While OpenAI has a similar deleted data retention policy for ChatGPT, the retention period for ChatGPT is only 30 days, which is 60 days shorter than Operator’s.
OpenAI is launching a research preview of Operator, a general-purpose AI agent that can take control of a web browser and independently perform certain actions. Operator promises to automate tasks such as booking travel accommodations, making restaurant reservations, and shopping online.
Operator, OpenAI’s agent tool, could be released sooner rather than later. Changes to ChatGPT’s code base suggest that Operator will be available as an early research preview to users on the $200 Pro subscription plan. The changes aren’t yet publicly visible, but a user on X who goes by Choi spotted these updates in ChatGPT’s client-side code. TechCrunch separately identified the same references to Operator on OpenAI’s website.
OpenAI has begun testing a feature that lets new ChatGPT users sign up with only a phone number — no email required. The feature is currently in beta in the U.S. and India. However, users who create an account using their number can’t upgrade to one of OpenAI’s paid plans without verifying their account via an email. Multi-factor authentication also isn’t supported without a valid email.
ChatGPT’s new beta feature, called tasks, allows users to set simple reminders. For example, you can ask ChatGPT to remind you when your passport expires in six months, and the AI assistant will follow up with a push notification on whatever platform you have tasks enabled. The feature will start rolling out to ChatGPT Plus, Team, and Pro users around the globe this week.
OpenAI is introducing a new way for users to customize their interactions with ChatGPT. Some users found they can specify a preferred name or nickname and “traits” they’d like the chatbot to have. OpenAI suggests traits like “Chatty,” “Encouraging,” and “Gen Z.” However, some users reported that the new options have disappeared, so it’s possible they went live prematurely.
ChatGPT is a general-purpose chatbot that uses artificial intelligence to generate text after a user enters a prompt, developed by tech startup OpenAI. The chatbot uses GPT-4, a large language model that uses deep learning to produce human-like text.
November 30, 2022 is when ChatGPT was released for public use.
Both the free version of ChatGPT and the paid ChatGPT Plus are regularly updated with new GPT models. The most recent model is GPT-4o.
There is a free version of ChatGPT that only requires a sign-in in addition to the paid version, ChatGPT Plus.
Anyone can use ChatGPT! More and more tech companies and search engines are utilizing the chatbot to automate text or quickly answer user questions/concerns.
Multiple enterprises utilize ChatGPT, although others may limit the use of the AI-powered tool.
Most recently, Microsoft announced at its 2023 Build conference that it is integrating its ChatGPT-based Bing experience into Windows 11. A Brooklyn-based 3D display startup Looking Glass utilizes ChatGPT to produce holograms you can communicate with by using ChatGPT. And nonprofit organization Solana officially integrated the chatbot into its network with a ChatGPT plug-in geared toward end users to help onboard into the web3 space.
GPT stands for Generative Pre-Trained Transformer.
A chatbot can be any software/system that holds dialogue with you/a person but doesn’t necessarily have to be AI-powered. For example, there are chatbots that are rules-based in the sense that they’ll give canned responses to questions.
ChatGPT is AI-powered and utilizes LLM technology to generate text after a prompt.
Yes.
Due to the nature of how these models work, they don’t know or care whether something is true, only that it looks true. That’s a problem when you’re using it to do your homework, sure, but when it accuses you of a crime you didn’t commit, that may well at this point be libel.
We will see how handling troubling statements produced by ChatGPT will play out over the next few months as tech and legal experts attempt to tackle the fastest moving target in the industry.
Yes, there is a free ChatGPT mobile app for iOS and Android users.
It’s not documented anywhere that ChatGPT has a character limit. However, users have noted that there are some character limitations after around 500 words.
Yes, it was released March 1, 2023.
Everyday examples include programming, scripts, email replies, listicles, blog ideas, summarization, etc.
Advanced use examples include debugging code, programming languages, scientific concepts, complex problem solving, etc.
It depends on the nature of the program. While ChatGPT can write workable Python code, it can’t necessarily program an entire app’s worth of code. That’s because ChatGPT lacks context awareness — in other words, the generated code isn’t always appropriate for the specific context in which it’s being used.
Yes. OpenAI allows users to save chats in the ChatGPT interface, stored in the sidebar of the screen. There are no built-in sharing features yet.
Yes. There are multiple AI-powered chatbot competitors such as Together, Google’s Gemini and Anthropic’s Claude, and developers are creating open source alternatives.
OpenAI has said that individuals in “certain jurisdictions” (such as the EU) can object to the processing of their personal information by its AI models by filling out this form. This includes the ability to make requests for deletion of AI-generated references about you. Although OpenAI notes it may not grant every request since it must balance privacy requests against freedom of expression “in accordance with applicable laws”.
The web form for making a deletion of data about you request is entitled “OpenAI Personal Data Removal Request”.
In its privacy policy, the ChatGPT maker makes a passing acknowledgement of the objection requirements attached to relying on “legitimate interest” (LI), pointing users towards more information about requesting an opt out — when it writes: “See here for instructions on how you can opt out of our use of your information to train our models.”
Recently, Discord announced that it had integrated OpenAI’s technology into its bot named Clyde where two users tricked Clyde into providing them with instructions for making the illegal drug methamphetamine (meth) and the incendiary mixture napalm.
An Australian mayor has publicly announced he may sue OpenAI for defamation due to ChatGPT’s false claims that he had served time in prison for bribery. This would be the first defamation lawsuit against the text-generating service.
CNET found itself in the midst of controversy after Futurism reported the publication was publishing articles under a mysterious byline completely generated by AI. The private equity company that owns CNET, Red Ventures, was accused of using ChatGPT for SEO farming, even if the information was incorrect.
Several major school systems and colleges, including New York City Public Schools, have banned ChatGPT from their networks and devices. They claim that the AI impedes the learning process by promoting plagiarism and misinformation, a claim that not every educator agrees with.
There have also been cases of ChatGPT accusing individuals of false crimes.
Several marketplaces host and provide ChatGPT prompts, either for free or for a nominal fee. One is PromptBase. Another is ChatX. More launch every day.
Poorly. Several tools claim to detect ChatGPT-generated text, but in our tests, they’re inconsistent at best.
No. But OpenAI recently disclosed a bug, since fixed, that exposed the titles of some users’ conversations to other people on the service.
None specifically targeting ChatGPT. But OpenAI is involved in at least one lawsuit that has implications for AI systems trained on publicly available data, which would touch on ChatGPT.
Yes. Text-generating AI models like ChatGPT have a tendency to regurgitate content from their training data.
Si alguna vez has abierto chatgpt y te has sentido desconcertado por la sopa del alfabeto de los nombres de los modelos, como GPT-4O, O3, O4-Mini, no estás solo.
Openai (la compañía detrás de ChatGPT) no lo hace exactamente fácil con sus convenciones de nombres. Pero comprender cuáles son estos modelos, qué pueden hacer y cómo acceder a ellos puede ayudarlo a aprovechar al máximo Chatgpt
Dwyane Wade comparte pensamientos sobre Dallas Mavericks obteniendo la primera elección
El miembro del Salón de la Fama de la NBA, Dwyane Wade, comparte sus pensamientos sobre la NBA y si los Mavericks que obtienen la primera selección en el draft o no es una “coincidencia”.
Deportes seriamente
Durante el período previo a cada draft de la NBA, puede ser difícil saber en qué confiar Intel. Algunos borradores simulados terminan siendo notablemente precisos. Otros terminan siendo ridículamente incorrectos. La varianza puede ser parte de la diversión y el drama que hace que este sea uno de los eventos anuales más grandes de la liga.
Y ahora la inteligencia artificial es capaz de soportar la especulación.
Hay poco misterio sobre la selección número 1 en el draft de la NBA de 2025, que está programado para comenzar el 25 de junio. Cooper Flagg of Duke es la mejor opción proyectada para los Dallas Mavericks, que ganó la lotería del draft de la NBA de este año a pesar de las largas probabilidades, y AI está de acuerdo con ese sentimiento. USA TODAY Sports le pidió a Google Gemini AI que ejecutara una simulación de cada selección de primera ronda durante el draft de la NBA de 2025 y devolvió los resultados basados en “las proyecciones actuales, las necesidades del equipo y algunas lógicas de draft general”.
Así que Flagg fue la selección número 1 de la IA y Duke estaba bien representado entre los 10 mejores. La simulación de AI de Google Gemini también tuvo un número significativo de perspectivas internacionales, tanto de las filas universitarias como de los clubes profesionales en el extranjero, saliendo del tablero en la primera ronda. Pero cada una de las ocho mejores selecciones proyectadas por AI, y 15 de las primeras 16 selecciones, jugaron baloncesto universitario durante la temporada 2024-25.
Aquí hay un desglose de las selecciones de primera ronda del draft de la NBA de 2025 hechas por un Google Gemini AI Smiulation, así como cómo ver el próximo mes cuando los equipos de la liga se reúnen en Brooklyn para hacer sus selecciones reales:
Las selecciones y comentarios de primera ronda fueron generados por una simulación de AI de Google Gemini del borrador de la NBA de 2025 basado en “Proyecciones actuales, necesidades del equipo y algún borrador general de lógica”.
El draft de la NBA de 2025 está programado para tener lugar durante dos días, con la primera ronda programada para el miércoles 25 de junio a partir de las 7 pm ET, y la segunda ronda se presentará el jueves 26 de junio.
Como inversionista en Alphabet (Googl), he notado la creciente narrativa: que Google está en “declive administrado”, amenazado por el rápido aumento de OpenAi con ChatGPT. Esta perspectiva, popularizada en podcasts y medios de comunicación, pinta el alfabeto como hinchado, lento y vulnerable a ser superado. Sin embargo, creo que estas afirmaciones son prematuras.
En lugar de simplemente enfrentar la competencia, Alphabet está evolucionando en silencio su negocio de búsqueda con Gemini AI. Lejos de disminuir, la compañía parece estar fortaleciendo su ventaja competitiva, posicionándose para un crecimiento sostenido y un rendimiento superior a largo plazo.
Alphabet ha lanzado la experiencia generativa de búsqueda (SGE), una actualización de IA para incorporar directamente a los resultados de búsqueda tradicionales. A diferencia de ChatGPT, que se ejecuta independientemente del comportamiento de búsqueda típico, el SGE dirigido por Gemini se integra perfectamente en la página de búsqueda convencional que todos hemos conocido durante décadas.
En la última actualización trimestral de Alphabet para el año fiscal 2025, SGE ya tiene más de 1.500 millones de usuarios activos cada mes, lo que sirve como evidencia de una adopción extremadamente rápida. Está claro para mí que Alphabet comprende bien a sus usuarios: en lugar de reinventar completamente la experiencia de búsqueda, la han mejorado, aprovechando décadas de experiencia y datos del usuario. Esta versión híbrida profundiza la confianza del usuario, proporcionando una experiencia de usuario atractiva al tiempo que limita los incentivos para que los usuarios migren a productos y servicios competitivos.
Otro aspecto significativo de la integración de Géminis de Google es la clara presencia de monetización. Alphabet mantuvo a propósito la publicidad en la mezcla de SGE. Justo en las respuestas de búsqueda generadas por IA, obtiene respuestas patrocinadas relevantes y ubicaciones de productos. Esto mantiene intacto el precioso modelo de chasis publicitario de Google sin romper los ingresos de él. Por ejemplo, la búsqueda de “mejores auriculares en ejecución” presenta recomendaciones y anuncios de productos patrocinados prominentemente.
Los informes más recientes de Alphabet muestran aumentos año tras año de dos dígitos en los ingresos publicitarios de búsqueda, lo que confirma que esta estrategia de monetización funciona bien para el alfabeto. Gemini aumenta la experiencia de búsqueda del usuario, verificando esta estrategia de monetización sin restar el flujo de ingresos del alfabeto central. Por lo tanto, no solo mantiene el flujo de caja actual de Google, sino que también potencialmente abre oportunidades adicionales para publicidad altamente específica, solidificando el liderazgo del Alphabet.
Operai, aunque emocionante para el mercado con búsqueda impulsada por IA a través de ChatGPT, enfrentará limitaciones estructurales más significativas en comparación con el alfabeto. Parece que la mayor parte de la monetización OpenAI gira en torno a suscripciones o tarifas de aplicación, que es mucho menos lucrativa, pegajosa y sostenible que el modelo de ingresos publicitarios de Alphabet. Esta será potencialmente una desventaja competitiva a largo plazo para OpenAI cuando compite con el alfabeto, que está respaldada por un capital financiero más profundo e infraestructura.
Dicho esto, creo que hay suficiente espacio para muchos jugadores exitosos en esta industria. Los modelos de Openai no deben subestimarse, y actualmente es la compañía líder del mercado para la IA generativa. El campo todavía está abierto a jugar, y veo muchas compañías dominantes ganando en grande, con Google y OpenAi reclamando el centro de atención de manera similar.
Dicho esto, el alfabeto enfrenta desafíos significativos en la gestión de los costos sustanciales asociados con la operación de la infraestructura informática necesaria para Géminis. Es probable que la búsqueda impulsada por IA sea significativamente más costosa que la búsqueda tradicional, lo que podría ejercer presión a largo plazo sobre los márgenes de ganancias. Para mitigar esto, Alphabet debe continuar diversificando sus flujos de ingresos. Waymo, parte del segmento de “otras apuestas”, ofrece una vía prometedora. Su servicio autónomo de transporte ya está operativo en partes de los EE. UU., Aunque enfrenta una fuerte competencia de la red emergente de autonomía de Tesla (TSLA).
También hay incertidumbre en torno al comportamiento del usuario. Como herramientas de IA, incluida las propias chatbots basadas en suscripción de Google, la tracción gana, podrían comenzar a desviar el tráfico lejos de la búsqueda tradicional. Este cambio podría reducir los ingresos impulsados por AD y conducir a una presión de margen adicional, lo que potencialmente obliga al alfabeto a inclinarse más en modelos basados en suscripción similares a CHATGPT. Como resultado, se puede justificar algún grado de compresión múltiple de valoración a largo plazo.
Aún así, estos riesgos parecen manejables cuando se ven a la luz de la fuerte historia de Alphabet de adaptar su modelo de negocio para generar rendimientos duraderos a largo plazo a medida que los mercados evolucionan.
En Wall Street, Googl tiene una calificación de compra de consenso fuerte, basada en 29 compras, nueve retención y cero ventas en los últimos tres meses. El precio objetivo promedio de Googl es de $ 199.14, lo que indica un potencial de aumento del 15% en los próximos 12 meses.
La narración de que Alphabet está en “declive administrado” me parece una reacción exagerada a cambios más amplios en el panorama tecnológico. En verdad, Alphabet está aprovechando activamente su vasta red de distribución, activos de datos patentados e infraestructura de monetización madura para forjar una posición defendible en el ecosistema de IA en evolución.
En lugar de mostrar signos de debilidad, Alphabet está ejecutando una evolución estratégica, metódicamente y sin fanfarria prematura. Para los inversores de crecimiento a largo plazo que buscan innovación y resiliencia, Gemini es un fuerte indicador de que el alfabeto sigue siendo una fuerza formidable. No es solo mantener el ritmo del cambio; Se está posicionando para entregar alfa sostenido y de alta calidad en un mercado que se transforma rápidamente.
Descargo de responsabilidad y divulgación
¿Busca una plataforma de negociación? Echa un vistazo a los mejores corredores en línea de Tipranks y encuentre el corredor ideal para sus operaciones.
Informar un problema
Remove.bg: La Revolución en la Edición de Imágenes que Debes Conocer
Cómo Comenzar a Utilizar ChatGPT: Una Guía Completa para Principiantes
Startups de IA en EE.UU. que han recaudado más de $100M en 2024
Cómo Empezar con Popai.pro: Tu Espacio Personal de IA – Guía Completa, Instalación, Versiones y Precios
Deepgram: Revolucionando el Reconocimiento de Voz con IA
Perplexity aplicado al Marketing Digital y Estrategias SEO
Curso de Inteligencia Artificial de UC Berkeley estratégico para negocios
Google Gemini: Guía Completa para Comenzar a usarlo y ganar tiempo en nuestras tareas diarias
Inside the OpenAI-DeepSeek Distillation Saga & Alibaba’s Most Powerful AI Model Qwen2.5-Max
De ChatGPT a mil millones de agentes
