Local AI is free, fast & secure!
So today we're introducing hf-mount: attach any storage bucket, model or dataset from @huggingface as a local filesystem.
This is a game changer, as it allows you to attach remote storage that is 100x bigger than your local machine's disk. This is also perfect for Agentic storage!!
Let's go!
@PNCBank_Help Hello, I have my business account blocked, phone support is with high demand so I can't talk with anybody at the bank. We need a business representative phone number to call asap. Can you please provide me a business number to talk with somebody instead of automatic machine?
@Minucha01@frascafrasca Yo estoy en la misma, y por ahora la respuesta q tengo es: experimenta sin parar nuevas herramientas y nuevas IAs, aprende mas rapido y mas autonomo, puede construir arriba de tecnologias y plataformas 10 veces mas rapido.
En realidad es muy loco pensar que mañana la mayoría de los desarrolladores del mundo podrán trabajar de forma más eficiente que el día de hoy, por el simple hecho de que una IA se ha actualizado.
Diría que nunca habíamos vivido un progreso tecnológico con un ritmo de mejora tan rápido y que tuviera una aplicabilidad tan inmediata.
De una semana a otra, actualizas el modelo y pum, todo funciona mejor. Y así en muchísimos sectores.
@frascafrasca Así es! Nuestra industria todavía está dormida. Muchos colegas me dicen “ahora cuando pase el humo/hype de la IA”. Es para analizar. Probaste v0? Recomiendo para arrancar a prototipos e iterar ideas en segundos. Si es algo “choto” puede ya quedar productivo
Had a blast at #CommunityOverCode in Denver! Reconnected with old friends, met new ones, and had great convos. Thanks to the organizers and everyone for an amazing event! Bonus: Loved the engaging talks and feedback on my Skywalking Copilot presentation!
Estamos a menos de una semana de este #webinar de @ChiletecOrg que contará con la participación de @fbaptista. Si te gusta la innovación y te interesan las nuevas tecnologías, este evento es para ti. En este hilo 👇 te dejamos la info completa y el link de registro
I stand corrected: GPT-4o does NOT natively process video stream. The blog says it only takes image, text, and audio. That's sad, but the principle I said still holds: the right way to make a video-native model efficient is to co-develop the streaming codec on edge device.
Gemini seems to treat video as first-class citizen. Let's see how Google I/O goes tomorrow.
@AndrewYNg We developed and have been using https://t.co/ZrWRveNFac to build copilots for these iterative workflows with users. We see a huge potential in implementing copilots that allow users to interact in more efficient ways with existing web apps.
@OpenAI@tszzl This is interesting, hadn't heard this before.
@ilyasut: "The Open in openAI means that everyone should benefit from the fruits of AI after its built, but it's totally OK to not share the science)"
We have added support for the new Anthropic Claude 3 models. Evaluating assistants with various suppliers and various models is necessary in many projects for reasons of effectiveness and cost efficiency. #GeneXus https://t.co/FlGkXwbIul @Globant