The Future of AI
.png?width=720&height=512&name=Working%20of%20Retrieval%20Augmented%20Generation%20(RAG).png&w=720&resize=720,511&ssl=1 "Understanding Retrieval – Augmented Generation (RAG): A Beginner’s Guide")
Remember back in 2021 when searching for information online often felt like a bit of a chore? You’d open up a search engine, type in your query, and then sift through a sea of links, trying to extract the nuggets of information you needed. It was effective, sure, but it often felt like digging through a haystack to find a needle, especially when you had a tricky question or needed something really specific.
The Paris 2024 Olympics have come to a close, and one thing is clear: Artificial Intelligence (AI) has redefined the event in ways we’ve never seen before. This year, AI wasn’t just a behind-the-scenes player; it was at the forefront, driving innovations that transformed every facet of the Games. This year’s event was nothing short … Read more
Because of its deep learning and independent decision-making capacities, uses of AI Application in various business regions are seeing a relentless ascent in universality in certain enterprises. The idea of artificial intelligence or machines that mean to imitate human thinking is experiencing enthusiastic research and is a subject that is progressively being related to the Internet of … Read more
The ability of LLMs to execute commands through plain language (e.g. English) has enabled agentic systems that can complete a user query by orchestrating the right set of tools (e.g. ToolFormer, Gorilla). This, along with the recent multi-modal efforts such as the GPT-4o or Gemini-1.5 model, has expanded the realm of possibilities with AI agents. While this is quite exciting, the large model size and computational requirements of these models often requires their inference to be performed on the cloud. This can create several challenges for their widespread adoption. First and foremost, uploading data such as video, audio, or text documents to a third party vendor on the cloud, can result in privacy issues. Second, this requires cloud/Wi-Fi connectivity which is not always possible. For instance, a robot deployed in the real world may not always have a stable connection. Besides that, latency could also be an issue as uploading large amounts of data to the cloud and waiting for the response could slow down response time, resulting in unacceptable time-to-solution. These challenges could be solved if we deploy the LLM models locally at the edge.
Introduction With the huge advancements happening in the field of large language models (LLMs), models that can process multimodal inputs have recently been coming to the forefront of the field. These models can take both text and images as input, and sometimes other modalities as well, such as video or speech. Multimodal models present unique … Read more
AI and While You Were Out IRL. The speed and breadth of AI R&D these days is mind-boggling! This w/e I’ve been immersed IRL joys, including being trapped in airplanes, trains and automobiles. (Apologies for publishing this a day later than usual.) This issue is a bit like an AP News bulletin on what happened … Read more
In the United States and around the world, democracy is under threat. Anti-democratic attitudes have become more prevalent, partisan polarization is growing, misinformation is omnipresent, and politicians and citizens sometimes question the integrity of elections. With this backdrop, the MIT Department of Political Science is launching an effort to establish a Strengthening Democracy Initiative. In … Read more
We dive into the difference between frontend and backend in web programming. Table of Contents: Frontend vs Backend In web development, the terms “frontend” and “backend” represent two distinct and complementary sides of a web application. Each plays a crucial role in delivering the seamless digital experiences that users interact with every day, from online … Read more
Like almost any question about AI, “How does AI impact software architecture?” has two sides to it: how AI changes the practice of software architecture and how AI changes the things we architect. These questions are coupled; one can’t really be discussed without the other. But to jump to the conclusion, we can say that … Read more
Apache Airflow has become the de facto library for pipeline orchestration in the Python ecosystem. It has gained popularity, contary to similar solutions, due to its simplicity and extensibility. In this article, I will attempt to outline its main concepts and give you a clear understanding of when and how to use it. Why and … Read more