Iuliia Gorshkova

The last time I found myself deep in the weeds of a knowledge engineering project, it was 2014. The mood in the air was one of polite dismissal. We were building a diagnostic system for industrial HVAC units, and my colleagues—brilliant data scientists all—were gently suggesting that our carefully curated ontology of mechanical failures and [...]

When we build complex software systems, we often talk about architecture, frameworks, and data structures. We obsess over database schemas and API contracts. Yet, when we step into the realm of Artificial Intelligence, specifically machine learning and knowledge representation, we encounter a different kind of challenge. It is not merely about organizing data; it is [...]

The landscape of manufacturing in Latin America is undergoing a profound transformation, marked by the gradual but determined integration of robotics into factory floors. This shift is not merely a response to global trends but a testament to the region’s ambition to enhance productivity, quality, and competitiveness in the face of mounting economic pressures. From [...]

For years, the dominant narrative surrounding large language models has focused on their ability to generate text. We measure their success in tokens per second, fluency, and the coherence of their paragraphs. While these metrics are useful for evaluating performance, they obscure a far more profound reality: these systems are not merely text generators. They [...]

Trust stands at the core of every meaningful relationship—this holds just as true for the evolving partnership between humans and autonomous robots. As robots steadily transition from industrial arms in factories to collaborative agents in hospitals, homes, and public spaces, understanding the fragile architecture of human-robot trust becomes a necessity. The landscape is shaped by [...]

There's a quiet revolution happening in the way we build and trust intelligent systems. For years, the dominant narrative around AI advancement has been one of scaling—more data, more parameters, more compute. We watched models grow from millions to trillions of parameters, solving problems that seemed impenetrable just a decade ago. Yet, as these systems [...]

The enigmatic world beneath the ocean’s surface holds secrets that have shaped civilizations and inspired countless myths. Among the most compelling treasures are shipwrecks and submerged sites—repositories of history often untouched for centuries. Today, the quest to understand and preserve underwater cultural heritage relies increasingly on the synergy between robotics and artificial intelligence (AI). This [...]

For years, the prevailing narrative around artificial intelligence, particularly in the realm of Large Language Models (LLMs), centered on their generative prowess. We marveled at the fluidity of text, the photorealism of images, and the coherence of code snippets generated from simple prompts. The underlying mechanism was often described as sophisticated pattern matching—a statistical leap [...]

The landscape of manufacturing in Europe has been rapidly evolving, with small and medium-sized enterprises (SMEs) at the heart of this transformation. Among the most significant catalysts for change are collaborative robots, or cobots, which have begun to find their place alongside human workers in factories, workshops, and assembly lines across the continent. The adoption [...]

The concept of an "agent" has captured the imagination of the software engineering community, particularly in the wake of large language models (LLMs). We envision autonomous entities capable of taking a vague instruction and executing a complex series of steps to achieve a goal. However, anyone who has spent time building these systems knows a [...]

In recent years, the integration of AI and robotics into renewable energy grids has rapidly shifted from experimental pilot projects to essential components in grid management. The transformation is particularly striking when considering the immense variability and complexity inherent in wind, solar, and other green energy sources. Where traditional grids relied on largely predictable, centralized [...]

When we talk about building intelligent systems, the terminology often drifts toward buzzwords that obscure the underlying mechanics. We hear "agent" and "LLM" used interchangeably, as if simply wrapping a language model in a loop automatically imbues it with agency. But the architectural differences between a recursive language model (RLM) pattern and a true agent [...]

Every engineer who has spent enough time with machine learning systems has seen it: the validation loss curve that plateaus, the model that learns a trivial shortcut, the reinforcement learning agent that finds a local optimum and refuses to leave it. It’s a moment of profound stagnation. The metrics stop moving, the training process hums [...]

For nearly a decade, the dominant narrative in artificial intelligence has been a relentless pursuit of scale. We watched parameters counts swell from millions to billions, and then to trillions. We saw training datasets expand from curated libraries to the near-totality of the public internet. The implicit assumption, often referred to as "scaling laws," suggested [...]

As the world’s agricultural demands intensify, farms are transforming into high-tech ecosystems, with robotics and artificial intelligence (AI) forging new frontiers. In the heart of this transformation lies a particular class of technology: edge AI systems. These are not the cloud-dependent algorithms of yesterday, but robust, responsive, and resilient solutions that allow machines to operate [...]

Memory, in the context of artificial intelligence, has long been treated as a passive reservoir—a linear tape where facts are stored and retrieved sequentially. We celebrate systems that can recall vast libraries of text, code, and images, assuming that recall equals intelligence. But this view is fundamentally incomplete. True reasoning isn’t just about retrieving what [...]

The intersection of artificial intelligence and robotics is rapidly redefining how machines perceive and interact with human emotions. Emotional AI, also known as affective computing, is a field dedicated to enabling machines to recognize, interpret, and respond to human emotional states. When embodied in humanoid robots, emotional AI not only transforms user experience but also [...]

The Challenge of Persistent, Grounded Reasoning For years, we have treated Large Language Models (LLMs) as brilliant but amnesiac savants. They possess the sum of human knowledge encoded in their weights, yet they lack a true, persistent memory of the specific interactions they have with us. When we ask an LLM to solve a complex, [...]

In the evolving landscape of sustainability, the partnership between robotics and the circular economy has become a driving force for innovation. As industries recognize the urgency of reducing waste and maximizing resource efficiency, robotics stands at the forefront, transforming how materials are recovered, sorted, and reintroduced into the production cycle. This symbiosis is not merely [...]

There’s a particular kind of frustration that settles in when a neural network fails. It’s not the anger of a broken tool, but the deep unease of a black box whispering secrets we cannot verify. We’ve all seen it: a model predicts a loan denial with 94% confidence, or flags a medical image as malignant, [...]

In recent years, the intersection of artificial intelligence and unmanned aerial vehicles has reshaped the landscape of humanitarian assistance. AI-powered drones are not simply tools of convenience; they are transforming the way communities respond to crises, from natural disasters to public health emergencies. With the capability to access remote locations, assess complex situations in real [...]

When we talk about artificial intelligence, particularly in the realm of Large Language Models (LLMs), the conversation often gravitates toward the immediate: the context window, the parameters, the sheer volume of data ingested. Yet, a persistent challenge in building robust, long-lived AI agents is the concept of memory. Most systems today rely on vector databases—essentially [...]

Soft robotics has rapidly evolved from a niche research field to a transformative force in medical engineering. In the context of minimally invasive surgery (MIS), the advent of soft robots has unlocked new possibilities for patient care, surgical safety, and procedural precision. Unlike their rigid counterparts, soft robots are constructed from compliant materials such as [...]

We need to talk about the memory crisis in modern AI. If you’ve spent any time tinkering with Large Language Models, you’ve likely hit the "amnesia wall." You can have a brilliant, context-aware conversation for twenty messages, and then you ask the model to recall a detail from message three, and it stares back at [...]

When we talk about vector search, the immediate mental image is often a flat, one-shot lookup: you embed a query, you embed your documents, and you perform a nearest-neighbor search in a high-dimensional space. It feels clean, mathematical, and efficient. But in practice, that simplicity often collapses under the weight of real-world complexity. The data [...]

For years, the promise of Large Language Models (LLMs) felt like a magic trick marred by a single, glaring flaw. We had systems capable of writing poetry, debugging code, and summarizing dense academic papers, yet they would confidently state that the capital of Australia is Sydney or invent legal precedents that never existed. This phenomenon, [...]

In the landscape of modern logistics, warehouses have become the nerve centers of global commerce. The drive toward greater efficiency, accuracy, and adaptability is unmistakable. Over the past decade, a profound shift has unfolded: robotics and artificial intelligence no longer sit at the periphery but have become central to warehouse operations. This article delves into [...]