VERSES AI (VRSSF) provided its Q4 corporate update, highlighting significant progress in its Genius™ product development and research achievements. The company released an enhanced version of Genius to beta program participants, featuring improved reasoning, planning capabilities, and user experience. Research milestones include preliminary results from the Atari 10K Challenge, where VERSES’ Active Inference-based models achieved comparable or better performance than state-of-the-art systems while using 90% less data, 96% less compute, and resulting in 97% smaller models.
The company also reported successful results in outperforming OpenAI’s o1-Preview in the Mastermind code-breaking test, with 100% accuracy versus 71%, 140 times faster performance, and significantly lower costs. Commercial projects, including a smart city partnership with Analog for taxi fleet management in Abu Dhabi, are progressing on schedule, with most beta users expected to convert to commercial engagements in 2025.
VERSES AI (VRSSF) ha fornito un aggiornamento aziendale del Q4, evidenziando progressi significativi nello sviluppo del prodotto Genius™ e nei risultati della ricerca. L’azienda ha rilasciato una versione migliorata di Genius ai partecipanti al programma beta, con capacità di ragionamento e pianificazione potenziate e un’esperienza utente migliore. I traguardi della ricerca includono risultati preliminari dalla Atari 10K Challenge, dove i modelli basati su Active Inference di VERSES hanno ottenuto prestazioni comparabili o superiori rispetto ai sistemi all’avanguardia, utilizzando il 90% in meno di dati, il 96% in meno di potenza di calcolo e risultando in modelli il 97% più piccoli.
L’azienda ha anche riportato risultati positivi nel superare o1-Preview di OpenAI nel test di risoluzione del codice Mastermind, con un’accuratezza del 100% contro il 71%, prestazioni 140 volte più veloci e costi significativamente più bassi. I progetti commerciali, inclusa una partnership per una smart city con Analog per la gestione della flotta di taxi ad Abu Dhabi, stanno procedendo secondo programma, con la maggior parte degli utenti beta prevista a convertirsi in impegni commerciali nel 2025.
VERSES AI (VRSSF) proporcionó su actualización corporativa del Q4, destacando avances significativos en el desarrollo del producto Genius™ y los logros en investigación. La empresa lanzó una versión mejorada de Genius a los participantes del programa beta, que cuenta con capacidades de razonamiento y planificación mejoradas y una experiencia de usuario superior. Los hitos de investigación incluyen resultados preliminares del Atari 10K Challenge, donde los modelos basados en Active Inference de VERSES lograron un rendimiento comparable o mejor que los sistemas de vanguardia, utilizando un 90% menos de datos, un 96% menos de cálculo y resultando en modelos un 97% más pequeños.
La empresa también informó resultados exitosos al superar el o1-Preview de OpenAI en la prueba de resolución de códigos Mastermind, con una precisión del 100% frente al 71%, un rendimiento 140 veces más rápido y costos significativamente más bajos. Los proyectos comerciales, incluida una asociación para una ciudad inteligente con Analog para la gestión de flotas de taxis en Abu Dhabi, están avanzando según lo previsto, con la mayoría de los usuarios beta esperados para convertirse en compromisos comerciales en 2025.
VERSES AI (VRSSF)는 Q4 기업 업데이트를 제공하며, Genius™ 제품 개발 및 연구 성과에서의 중요한 진행 상황을 강조했습니다. 회사는 검색이 개선된 사용자 경험과 더불어 향상된 추론 및 계획 기능을 자랑하는 Genius의 최신 버전을 베타 프로그램 참가자에게 출시했습니다. 연구 이정표에는 Atari 10K Challenge의 예비 결과가 포함되며, VERSES의 Active Inference 기반 모델은 데이터 사용량을 90% 줄이고, 컴퓨팅 용량을 96% 줄이며, 결과적으로 97% 더 작은 모델을 생성하면서 최첨단 시스템과 유사하거나 더 나은 성능을 달성했습니다.
회사는 또한 OpenAI의 o1-Preview를 Mastermind 코드 해독 테스트에서 100% 정확도로 71%에 비해 성과를 개선하고, 140배 더 빠른 성능과 상당히 낮은 비용으로 제공했다고 보고했습니다. 아부다비에서 택시 플릿 관리에 대한 Analog와의 스마트 시티 파트너십을 포함한 상업 프로젝트는 일정에 따라 진행되고 있으며, 대부분의 베타 사용자가 2025년에 상업적 계약으로 전환될 것으로 예상됩니다.
VERSES AI (VRSSF) a fourni sa mise à jour d’entreprise pour le quatrième trimestre, mettant en avant des progrès significatifs dans le développement de son produit Genius™ et ses réalisations en matière de recherche. L’entreprise a lancé une version améliorée de Genius aux participants du programme bêta, avec des capacités de raisonnement et de planification améliorées et une meilleure expérience utilisateur. Les jalons de la recherche incluent des résultats préliminaires du Atari 10K Challenge, où les modèles basés sur l’Active Inference de VERSES ont atteint une performance comparable ou meilleure que les systèmes de pointe tout en utilisant 90% moins de données, 96% moins de puissance de calcul et aboutissant à des modèles 97% plus petits.
L’entreprise a également annoncé des résultats positifs en surpassant l’o1-Preview d’OpenAI dans le test de déchiffrement du code Mastermind, avec une précision de 100% contre 71%, une performance 140 fois plus rapide et des coûts considérablement réduits. Les projets commerciaux, y compris un partenariat pour une ville intelligente avec Analog pour la gestion de flotte de taxis à Abu Dhabi, avancent comme prévu, la plupart des utilisateurs de la version bêta étant attendus pour se convertir en engagements commerciaux en 2025.
VERSES AI (VRSSF) hat sein Q4-Firmenupdate bereitgestellt und dabei bedeutende Fortschritte in der Produktentwicklung von Genius™ und den Forschungsergebnissen hervorgehoben. Das Unternehmen hat eine verbesserte Version von Genius an die Teilnehmer des Beta-Programms veröffentlicht, die verbesserte Denk- und Planungsfähigkeiten sowie eine verbesserte Benutzererfahrung bietet. Zu den Forschungsmeilensteinen gehören erste Ergebnisse aus der Atari 10K Challenge, bei der die auf Active Inference basierenden Modelle von VERSES eine vergleichbare oder bessere Leistung gegenüber hochmodernen Systemen erbrachten und dabei 90% weniger Daten, 96% weniger Rechenleistung benötigten und 97% kleinere Modelle erzielten.
Das Unternehmen berichtete auch über erfolgreiche Ergebnisse, die OpenAIs o1-Preview im Mastermind-Codeknacker-Test mit 100% Genauigkeit im Vergleich zu 71% übertrafen, 140-mal schnellere Leistung und deutlich niedrigere Kosten. Kommerzielle Projekte, einschließlich einer Partnerschaft für eine Smart City mit Analog zur Verwaltung einer Taxi-Flotte in Abu Dhabi, kommen planmäßig voran, und die meisten Beta-Nutzer werden voraussichtlich 2025 in kommerzielle Engagements umschwenken.
Positive
Genius beta program showing strong commercial potential with majority of users expected to convert to paying customers in 2025
Demonstrated superior performance vs OpenAI’s o1-Preview with 100% accuracy (vs 71%), 140x faster speed, and 5260x lower cost
Achieved comparable or better performance than state-of-the-art systems using 90% less data and 96% less compute in Atari benchmark
Extended exclusive contract with Chief Scientist Professor Karl Friston
Quarter Highlights Product, Research, and Commercial Milestones
VANCOUVER, British Columbia, Dec. 31, 2024 (GLOBE NEWSWIRE) — VERSES AI Inc. (CBOE:VERS) (OTCQB:VRSSF) (“VERSES” or the “Company”), a cognitive computing company specializing in next generation intelligent systems, provides a corporate update.
“Our mission is to unleash a new class of intelligent autonomous agents that are both more reliable and more efficient. Today, the research and product investments we’ve made are proving their worth—just as the diminishing returns of scaling data and compute, alongside the unreliability of traditional deep and reinforcement learning, are becoming widely recognized,” said Gabriel René, founder and CEO of VERSES.
“Our Genius product has evolved rapidly this quarter, and we are excited to transition from beta to its commercial phase in 2025,” René continued. “Its unique combination of active inference and learning, as highlighted in today’s announcement on the Atari benchmarks, enables a new class of agents capable of reliably automating real-time decision-making, reducing errors, and maximizing efficiency for enterprises—from software applications to robotic automation. By design, Genius goes beyond intelligent systems available today and has the potential to become a disruptive force in next-generation autonomous intelligent systems,” concluded Mr. René.
Quarterly Highlights include:
Genius™ Rollout
“Being able to explicitly model the cause-effect relationships of complex systems and quantify uncertainty means we can generate something not possible with traditional ML tools – results that are reliable, explainable, and assurance ready,” said Andy Tasker, CEO of Prodigii.
VERSES released an update of its flagship product, Genius, to beta program participants earlier this month, which includes powerful, enhanced reasoning and planning capabilities, comprehensive model explainability, and support tools to accelerate onboarding. The latest release improves user experience by providing a new model editing interface with simplified tutorials and deployment processes based on initial feedback from early beta users. This release is initially available to select beta partners and machine learning practitioners. As Genius functionality evolves we expect to expand the number and variety of user personas and use cases in 2025.
Research Milestones
“As anticipated, we’re thrilled to share groundbreaking early results from the Atari 10k Challenge,” said Hari Thiruvengada, Chief Technology Officer of VERSES.
VERSES Atari 10K Challenge is an aggressive variant of the Atari 100K benchmark that aims to meet or exceed human-level performance across multiple Atari games using just 10k frames (90% less data) and a fraction of the compute with a single generalizable architecture than industry-leading approaches. Preliminary results demonstrate that VERSES Active Inference-based, Bayesian models can achieve comparable or better performance than state-of-the-art reinforcement learning models such as the #1 ranked BBF (Bigger, Better, Faster) from Google’s Deepmind and other deep learning transformer-based models that power OpenAI, Anthropic and Meta’s to LLM’s and all Generative AI models across multiple games using 90% less data, 96% less compute and resulting in models that are up to 97% smaller in size, which is key to operating on low-power devices. In addition, VERSES model performance was conducted on the equivalent of a CPU vs the GPU architecture required for the other algorithms.
“We believe this marks an historic shift for the AI industry at large,” stated Thiruvengada. “We have demonstrated that it is technically feasible to leverage Bayesian approaches at scale, tackling complex challenges like Atari with significantly reduced compute and sample sizes. Simultaneously, we are integrating these advanced capabilities into Genius, ensuring that we deliver a user-friendly and accessible solution for our customers. This is just the beginning of what we can accomplish together.”
A more comprehensive update on Atari results is forthcoming.
The Atari benchmarks come on the heels of VERSES sharing results demonstrating how an agent, powered by Genius, outperformed OpenAI’s o1-Preview, considered the industry-leading reasoning model on the code-breaking test Mastermind. Genius consistently outperformed o1-Preview by reliably solving the code 100% of the time vs. o1-Preview’s 71% accuracy rate while performing 140 times faster and costing 5260 times less. A detailed breakdown of the results can be found here.
Commercial Projects
The initial smart city project in partnership with Analog for simulating taxi fleet management in Abu Dhabi is progressing well and the discovery phase is on schedule.
“We are pleased that a majority of Genius beta users are expected to convert to commercial engagements in 2025,” said James Hendrickson, Chief Operating Officer. “We also have several new projects in a variety of different market segments that are in the scoping phase with contracting expected in Q1.”
Corporate and Operational Updates
As the Company anticipates scaling product and commercial operations, we have made several investments to shore up personnel and organizational processes.
VERSES extended Professor Karl Friston’s exclusive contract as Chief Scientist. The multi-year contract builds on the success of both research and product development and includes incentives tied to future milestones and deliverables.
VERSES researchers attended the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024) held in Vancouver, Canada. Three full papers from VERSES were accepted and seven were included in various workshops with topics spanning, among other areas, active inference, predictive coding, embodied agents, and robotics. Professor Karl Friston presented at the NeuroAI workshop entitled “The three faces of AI,” and participated in a panel discussion on the fusion of AI and Neuroscience with fellow AI pioneer Yoshua Bengio.
Additionally, the Company operationalized research with standardized test environments, frameworks and more robust support for cloud services like Amazon Web Services. There has also been a focus on formalizing and improving knowledge transfer efficiency between research and product in order to help prioritize research efforts based on demand as well as the productization of research.
About VERSES
VERSES is a cognitive computing company building next-generation intelligent software systems modeled after the wisdom and genius of Nature. Designed around first principles found in science, physics and biology, our flagship product, Genius, is a suite of tools for machine learning practitioners to model complex dynamic systems and generate autonomous intelligent agents that continuously reason, plan, and learn. Imagine a Smarter World that elevates human potential through technology inspired by Nature. Learn more at verses.ai, LinkedIn, and X.
On behalf of the Company
Gabriel René, Founder & CEO, VERSES AI Inc.
Press Inquiries: press@verses.ai
Investor Relations Inquiries
U.S., Matthew Selinger, Partner, Integrous Communications, mselinger@integcom.us 415-572-8152
Canada, Leo Karabelas, President, Focus Communications, info@fcir.ca 416-543-3120
When used in this press release, the words “estimate”, “project”, “belief”, “anticipate”, “intend”, “expect”, “plan”, “predict”, “may” or “should” and the negative of these words or such variations thereon or comparable terminology are intended to identify forward-looking statements and information. Although VERSES believes, in light of the experience of their respective officers and directors, current conditions and expected future developments and other factors that have been considered appropriate, that the expectations reflected in the forward-looking statements and information in this press release are reasonable, undue reliance should not be placed on them because the parties can give no assurance that such statements will prove to be correct. The forward-looking statements and information in this press release include, among other things, statements regarding potential future smart city projects, and the ability of the Company to satisfy the intended goals and objectives of the current smart city project.
There are risks and uncertainties that may cause actual results to differ materially from those contemplated in those forward-looking statements and information. In making the forward-looking statements in this news release, the Company has applied various material assumptions. By their nature, forward-looking statements involve known and unknown risks, uncertainties and other factors which may cause our actual results, performance or achievements, or other future events, to be materially different from any future results, performance or achievements expressed or implied by such forward-looking statements. There are a number of important factors that could cause VERSUS’ actual results to differ materially from those indicated or implied by forward-looking statements and information. Such factors may include, among other things, the ability of the Company to negotiate contracts for future smart city projects, or the ability of the Company to achieve the intended goals and objectives of the current smart city project. The Company undertakes no obligation to comment on analyses, expectations or statements made by third parties in respect of its securities or its financial or operating results (as applicable).
Additionally, forward-looking statements involve a variety of known and unknown risks, uncertainties and other factors which may cause the actual plans, intentions, activities, results, performance or achievements of the Company to be materially different from any future plans, intentions, activities, results, performance or achievements expressed or implied by such forward-looking statements. Such risks include, without limitation: the risk that the Company will be unsuccessful in negotiating contracts for future smart city projects; and that the Company may not be able to achieve the intended goals and objectives of the current smart city project. VERSES cautions that the foregoing list of material factors is not exhaustive. When relying on VERSES’ forward-looking statements and information to make decisions, investors and others should carefully consider the foregoing factors and other uncertainties and potential events. VERSES has assumed that the material factors referred to in the previous paragraph will not cause such forward-looking statements and information to differ materially from actual results or events. However, the list of these factors is not exhaustive and is subject to change and there can be no assurance that such assumptions will reflect the actual outcome of such items or factors. The forward-looking information contained in this press release represents the expectations of VERSES as of the date of this press release and, accordingly, are subject to change after such date. VERSES does not undertake to update this information at any particular time except as required in accordance with applicable laws.
FAQ
What are the key performance metrics of VERSES AI (VRSSF) Genius platform compared to OpenAI?
VERSES AI’s Genius platform demonstrated 100% accuracy vs OpenAI’s o1-Preview’s 71% in the Mastermind code-breaking test, performing 140 times faster and costing 5260 times less.
How did VERSES AI (VRSSF) perform in the Atari 10K Challenge?
VERSES AI achieved comparable or better performance than state-of-the-art systems while using 90% less data, 96% less compute, and producing models that are 97% smaller in size.
When will VERSES AI (VRSSF) transition Genius from beta to commercial phase?
VERSES AI plans to transition Genius from beta to its commercial phase in 2025, with the majority of beta users expected to convert to commercial engagements.
What progress has VERSES AI (VRSSF) made in its smart city project?
The initial smart city project with Analog for taxi fleet management in Abu Dhabi is progressing well, with the discovery phase on schedule.
Cuando el CEO de Google, Sundar Pichai, suba al escenario en la Conferencia de desarrolladores de Google I/O 2025 la próxima semana para entregar sus comentarios de apertura, espere que dos cartas dominen la discusión: la IA.
La inteligencia artificial se ocupa de gran parte del enfoque en Google en estos días, con características de IA que llegan a través de múltiples productos, proyectos centrados en la IA que capturan gran parte de la atención y predicciones del público sobre el futuro de la IA que asume muchos de los pronunciamientos públicos de la compañía.
Ya sea que se dé cuenta o no, la inteligencia artificial está en todas partes. Se encuentra detrás de los chatbots con los que hablas en línea, las listas de reproducción que transmites y los anuncios personalizados que aparecen en tu desplazamiento. Y ahora está tomando una personalidad más pública. Piense en Meta AI, que ahora está integrado en aplicaciones como Facebook, Messenger y WhatsApp; o Géminis de Google, trabajando en segundo plano en las plataformas de la compañía; o Apple Intelligence, lanzando a través de iPhones ahora.
AI tiene una larga historia, volviendo a una conferencia en Dartmouth en 1956 que primero discutió la inteligencia artificial como una cosa. Los hitos en el camino incluyen Eliza, esencialmente el primer chatbot, desarrollado en 1964 por el informático del MIT Joseph Weizenbaum y, saltando 40 años, cuando la función de autocompleta de Google apareció por primera vez en 2004.
Luego llegó 2022 y el ascenso de Chatgpt a la fama. Los desarrollos generativos de IA y los lanzamientos de productos se han acelerado rápidamente desde entonces, incluidos Google Bard (ahora Gemini), Microsoft Copilot, IBM Watsonx.ai y los modelos de LLAMA de código abierto de Meta.
Desglosemos qué es la IA generativa, cómo difiere de la inteligencia artificial “regular” y si la Generación AI puede estar a la altura de las expectativas.
IA generativa en pocas palabras
En esencia, la IA generativa se refiere a sistemas de inteligencia artificial que están diseñados para producir un nuevo contenido basado en patrones y datos que han aprendido. En lugar de solo analizar números o predecir tendencias, estos sistemas generan salidas creativas como texto, música de imágenes, videos y código de software.
Algunas de las herramientas de IA generativas más populares en el mercado incluyen:
El principal entre sus habilidades, ChatGPT puede crear conversaciones o ensayos similares a los humanos basados en algunas indicaciones simples. Dall-E y MidJourney crean obras de arte detalladas a partir de una breve descripción, mientras que Adobe Firefly se centra en la edición y el diseño de imágenes.
Chatgpt / captura de pantalla por cnet
Ai eso no es generativo
No toda la IA es generativa. Si bien Gen AI se enfoca en crear contenido nuevo, la IA tradicional se destaca por analizar datos y hacer predicciones. Esto incluye tecnologías como el reconocimiento de imágenes y el texto predictivo. También se usa para soluciones novedosas en:
Ciencia
Diagnóstico médico
Pronóstico del tiempo
Detección de fraude
Análisis financiero para pronósticos e informes
La IA que venció a los grandes campeones humanos en el ajedrez y el juego de mesa no fue una IA generativa.
Es posible que estos sistemas no sean tan llamativos como la Generación AI, pero la inteligencia artificial clásica es una gran parte de la tecnología en la que confiamos todos los días.
¿Cómo funciona Gen AI?
Detrás de la magia de la IA generativa hay modelos de idiomas grandes y técnicas avanzadas de aprendizaje automático. Estos sistemas están capacitados en grandes cantidades de datos, como bibliotecas completas de libros, millones de imágenes, años de música grabada y datos raspados de Internet.
Los desarrolladores de IA, desde gigantes tecnológicos hasta nuevas empresas, son conscientes de que la IA es tan buena como los datos que lo alimenta. Si se alimenta de datos de baja calidad, la IA puede producir resultados sesgados. Es algo con lo que incluso los jugadores más grandes en el campo, como Google, no han sido inmunes.
La IA aprende patrones, relaciones y estructuras dentro de estos datos durante el entrenamiento. Luego, cuando se le solicita, aplica ese conocimiento para generar algo nuevo. Por ejemplo, si le pide a una herramienta Gen AI que escriba un poema sobre el océano, no solo extrae versos preescritos de una base de datos. En cambio, está usando lo que aprendió sobre la poesía, los océanos y la estructura del lenguaje para crear una pieza completamente original.
Chatgpt / captura de pantalla por cnet
Es impresionante, pero no es perfecto. A veces los resultados pueden sentirse un poco apagados. Tal vez la IA malinterpreta su solicitud, o se vuelve demasiado creativo de una manera que no esperaba. Puede proporcionar con confianza información completamente falsa, y depende de usted verificarla. Esas peculiaridades, a menudo llamadas alucinaciones, son parte de lo que hace que la IA generativa sea fascinante y frustrante.
Las capacidades generativas de IA están creciendo. Ahora puede comprender múltiples tipos de datos combinando tecnologías como el aprendizaje automático, el procesamiento del lenguaje natural y la visión por computadora. El resultado se llama IA multimodal que puede integrar alguna combinación de texto, imágenes, video y habla dentro de un solo marco, ofreciendo respuestas más contextualmente relevantes y precisas. El modo de voz avanzado de ChatGPT es un ejemplo, al igual que el proyecto Astra de Google.
Desafíos con IA generativa
No hay escasez de herramientas de IA generativas, cada una con su talento único. Estas herramientas han provocado la creatividad, pero también han planteado muchas preguntas además del sesgo y las alucinaciones, como, ¿quién posee los derechos del contenido generado por IA? O qué material es un juego justo o fuera de los límites para que las compañías de IA los usen para capacitar a sus modelos de idiomas; vea, por ejemplo, la demanda del New York Times contra Openai y Microsoft.
Otras preocupaciones, no son asuntos pequeños, implican privacidad, responsabilidad en la IA, los profundos profundos generados por IA y el desplazamiento laboral.
“Escribir, animación, fotografía, ilustración, diseño gráfico: las herramientas de IA ahora pueden manejar todo eso con una facilidad sorprendente. Pero eso no significa que estos roles desaparezcan. Simplemente puede significar que los creativos deberán mejorar y usar estas herramientas para amplificar su propio trabajo”, Fang Liu, profesor de la Universidad de Notre Dame Dame y Coeditor-Chief de las transacciones de ACM en las transacciones de Probabilista, contó el aprendizaje en el poderoso de la máquina probabilística, le dijo a Cetnet.
“También ofrece una forma para las personas que tal vez carecen de la habilidad, como alguien con una visión clara que no puede dibujar, pero que puede describirlo a través de un aviso. Así que no, no creo que interrumpa a la industria creativa. Con suerte, será una co-creación o un aumento, no un reemplazo”.
Otro problema es el impacto en el medio ambiente porque la capacitación de grandes modelos de IA utiliza mucha energía, lo que lleva a grandes huellas de carbono. El rápido ascenso de la Generación AI en los últimos años ha acelerado las preocupaciones sobre los riesgos de la IA en general. Los gobiernos están aumentando las regulaciones de IA para garantizar el desarrollo responsable y ético, especialmente la Ley de IA de la Unión Europea.
Recepción de IA generativa
Muchas personas han interactuado con los chatbots en el servicio al cliente o han utilizado asistentes virtuales como Siri, Alexa y Google Assistant, que ahora están en la cúspide de convertirse en Gen AI Power Tools. Todo eso, junto con las aplicaciones para ChatGPT, Claude y otras herramientas nuevas, es poner ai en sus manos. Y la reacción pública a la IA generativa se ha mezclado. Muchos usuarios disfrutan de la conveniencia y la creatividad que ofrece, especialmente para cosas como escribir ayuda, creación de imágenes, soporte de tareas y productividad.
Mientras tanto, en la encuesta global de IA 2024 de McKinsey, el 65% de los encuestados dijo que sus organizaciones usan regularmente IA generativa, casi el doble de la cifra reportada solo 10 meses antes. Industrias como la atención médica y las finanzas están utilizando Gen AI para racionalizar las operaciones comerciales y automatizar tareas mundanas.
Como se mencionó, existen preocupaciones obvias sobre la ética, la transparencia, la pérdida de empleos y el potencial del mal uso de los datos personales. Esas son las principales críticas detrás de la resistencia a aceptar la IA generativa.
Y las personas que usan herramientas de IA generativas también encontrarán que los resultados aún no son lo suficientemente buenos para el tiempo. A pesar de los avances tecnológicos, la mayoría de las personas pueden reconocer si el contenido se ha creado utilizando Gen AI, ya sean artículos, imágenes o música.
AI ha secuestrado ciertas frases que siempre he usado, por lo que debo autocorrectar mi escritura a menudo porque puede parecer una IA. Muchos artículos escritos por AI contienen frases como “en la era de”, o todo es un “testimonio de” o un “tapiz de”. La IA carece de la emoción y la experiencia que viene, bueno, ser una vida humana y viviente. Como explicó un artista en Quora, “lo que AI hace no es lo mismo que el arte que evoluciona de un pensamiento en un cerebro humano” y “no se crea a partir de la pasión que se encuentra en un corazón humano”.
AI generativa: vida cotidiana
La IA generativa no es solo para técnicos o personas creativas. Una vez que obtienes la habilidad de darle indicaciones, tiene el potencial de hacer gran parte del trabajo preliminar por ti en una variedad de tareas diarias.
Digamos que está planeando un viaje. En lugar de desplazarse por páginas de resultados de búsqueda, le pide a un chatbot que planifique su itinerario. En cuestión de segundos, tiene un plan detallado adaptado a sus preferencias. (Ese es el ideal. Por favor, verifique siempre sus recomendaciones).
Un propietario de una pequeña empresa que necesita una campaña de marketing pero que no tiene un equipo de diseño puede usar una IA generativa para crear imágenes llamativas e incluso pedirle que sugiera copia publicitaria.
Chatgpt / captura de pantalla por cnet
Gen Ai está aquí para quedarse
No ha habido un avance tecnológico que haya causado tal boom desde Internet y, más tarde, el iPhone. A pesar de sus desafíos, la IA generativa es innegablemente transformadora. Está haciendo que la creatividad sea más accesible, ayudando a las empresas a racionalizar los flujos de trabajo e incluso inspirar formas completamente nuevas de pensar y resolver problemas.
Pero quizás lo más emocionante es su potencial, y estamos rascando la superficie de lo que estas herramientas pueden hacer.
Preguntas frecuentes
¿Cuál es un ejemplo de IA generativa?
ChatGPT es probablemente el ejemplo más popular de IA generativa. Le das un aviso y puede generar texto e imágenes; Código de escritura; Responder preguntas; resumir el texto; borrador de correos electrónicos; y mucho más.
¿Cuál es la diferencia entre la IA y la IA generativa?
La IA generativa crea contenido nuevo como texto, imágenes o música, mientras que la IA tradicional analiza los datos, reconoce patrones o imágenes y hace predicciones (por ejemplo, en medicina, ciencia y finanzas).
Si busca “CHATGPT” en su navegador, es probable que se tope en sitios web que parecen estar alimentados por OpenAI, pero no lo son. Uno de esos sitios, chat.chatbotapp.ai, ofrece acceso a “GPT-3.5” de forma gratuita y utiliza marca familiar.
Pero aquí está la cosa: no está dirigida por OpenAi. Y, francamente, ¿por qué usar un GPT-3.5 potencialmente falso cuando puedes usar GPT-4O de forma gratuita en el actual ¿Sitio de chatgpt?
This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.