Iuliia Gorshkova

Artificial Intelligence (AI) systems are rapidly transforming from tightly integrated monoliths into modular, flexible architectures that promise to accelerate innovation, reduce costs, and simplify scaling across diverse applications. The evolution toward modular AI architecture is not just a matter of engineering fashion: it is a direct response to the growing complexity, scale, and real-world deployment [...]

When you're in the thick of building an AI startup, it’s easy to get swept up in the model performance metrics. The excitement of pushing an F1 score from 92% to 94% consumes the engineering cycle. But for anyone who has sat across the table from a Series A investor or an enterprise procurement officer, [...]

Most AI systems today are brilliant at pattern recognition but terrible at understanding. They can generate fluent prose and write elegant code, yet they frequently hallucinate facts, misinterpret context, and fail to reason about the relationships between entities. This isn't a bug in the neural architecture; it's a fundamental limitation of statistical learning without a [...]

The conversation around AI careers often feels like a frantic scramble to catch a moving train. Headlines scream about automation taking jobs, while simultaneously, every company with a pulse is desperately hiring for "AI talent." For engineers and technical professionals trying to chart a course through the next five to ten years, the noise is [...]

Artificial intelligence systems have become integral to modern decision-making, touching everything from job recruitment and credit scoring to healthcare and criminal justice. While these technologies promise greater efficiency and objectivity, real-world deployments have shown that AI can inadvertently perpetuate or even amplify biases and discrimination. In recent years, several high-profile legal cases have brought this [...]

There's a specific kind of vertigo that hits when you watch a language model start chasing its own tail in a retrieval loop. You ask a nuanced question about, say, the thermodynamics of a specific Martian atmosphere simulation. The model retrieves a paper on atmospheric pressure. Good start. It then uses that context to ask [...]

There's a moment every builder of intelligent systems recognizes. It’s the quiet, slightly unsettling pause after the demo works. The model answered the question, the retrieval found the document, the code compiled. The metrics on the dashboard tick up. But the lingering question isn't "Does it work?" It's "How much do I trust this?" This [...]

China's approach to governing artificial intelligence often appears as a dense fog of policy documents and broad directives to the outside observer. For those of us building the systems, however, that fog resolves into something much more concrete: a set of architectural constraints and hard-coded responsibilities. The "Rules for the Management of Generative Artificial Intelligence [...]

The question of how to handle long documents with language models feels like one of the fundamental engineering challenges of our time. We have these incredibly capable "brains" in the form of LLMs, but they come with a fixed, often frustrating, context window. When you’re dealing with a 200-page technical manual, a sprawling legal deposition, [...]

The term “agentic AI” has recently graduated from academic papers and speculative blog posts into the lexicon of venture capital and startup accelerators. It is no longer a niche concept discussed in research labs; it is now a formal funding category, appearing on pitch decks, investment memos, and accelerator application forms with increasing frequency. This [...]

Embarking on a two-month sprint to transition from a generalist developer to an AI engineer feels, at first glance, like attempting to summit a mountain in running shoes. The landscape of artificial intelligence is vast, shifting, and often obscured by marketing jargon. Yet, for a working developer already fluent in the logic of code and [...]

Launching an AI product is a significant milestone for any team, representing months or even years of work. However, the journey from concept to market involves more than just developing a sophisticated algorithm. The transition from prototype to production, and ultimately to users, demands a systematic approach to legal, ethical, and technical due diligence. Overlooking [...]

The term started as an inside joke, a tongue-in-cheek descriptor for the feeling of riding an LLM’s autocomplete through a project. "Vibe coding" implies a shift from explicit instruction to intuitive flow: you describe a feeling, a direction, and the model fills in the gaps. It’s seductive because it works. For a certain class of [...]

If you are building an AI product in the United States right now, you are operating within a governance framework that doesn't look like the comprehensive, top-down legislation you might be used to in Europe. Instead, the US is currently taking what many experts are calling an "enforcement-first" approach. This means that rather than waiting [...]

There's a particular kind of frustration that settles in when you're debugging a complex system—not just a single function, but a sprawling architecture of interacting services, state machines, and data pipelines. You trace a request through the logs, watch it hop from microservice to microservice, and suddenly you're staring at a decision that makes no [...]

The Illusion of Invincibility When we first start building autonomous agents, there is a heady phase where everything feels like magic. You string together a few API calls, hook up a function calling schema, and suddenly your code can "decide" to check the weather, book a flight, or query a database. It feels invincible. Until, [...]

There's a peculiar hum in the air for those of us who've been building software for a while. It's the sound of the ground shifting beneath our feet. The vocabulary we relied on—API, SDK, database, server—feels insufficient for the world we're now architecting. We're not just connecting services anymore; we're trying to bottle lightning, to [...]

The EU AI Act is a sprawling piece of legislation, dense with legal definitions and phased enforcement. For engineers and product managers, reading it feels less like parsing a spec and more like translating a foreign document where every paragraph has potential runtime errors. The challenge isn't just understanding the regulation; it’s mapping abstract compliance [...]

Artificial intelligence has rapidly evolved into a defining technology of our era, shaping industries, economies, and even our daily conversations. As its capabilities expand, so too do the risks and uncertainties associated with its deployment. Among regulators and policymakers, a recurring question arises: how can we foster innovation while safeguarding fundamental rights and minimizing societal [...]

When engineers talk about "Recursive Language Models" or "RLMs," they are rarely referring to a single, formally defined architecture. The term has become a shorthand—a label applied to a family of agentic patterns that extend the capabilities of Large Language Models (LLMs) beyond simple, single-turn inference. It is a misnomer, in a sense, because the [...]

If you've been building AI systems for a while, you know the feeling. You spend months perfecting a Retrieval-Augmented Generation (RAG) pipeline, tuning prompts, and chunking documents, only to watch the industry pivot overnight. What worked in 2023—careful prompt engineering, rigid state machines, and monolithic model calls—feels like a relic by mid-2025. The shift hasn't [...]

Artificial Intelligence (AI) has become an undeniable force in creative industries, research, and technology. Today, generative AI models—capable of producing text, images, music, and even code—are reshaping the boundaries of authorship and ownership. As these systems gain the ability to autonomously create content, profound legal and ethical questions emerge: who owns the output of generative [...]

Artificial intelligence is rapidly transforming nearly every aspect of society, from healthcare and education to finance and government services. As AI systems become increasingly sophisticated and embedded in daily life, the question of how best to regulate their development and deployment has become central to public debate. Australia, like many nations, faces the complex challenge [...]

Artificial intelligence is reshaping societies worldwide, and Brazil stands at a pivotal moment regarding its regulation, adoption, and integration into the legal system. As Latin America's largest country, Brazil faces unique challenges: a diverse population, deep economic contrasts, and a rapidly evolving technological landscape. The national conversation about AI blends aspirations for innovation with the [...]

Artificial intelligence has made remarkable strides in recent years, yet beneath the surface of every smart assistant, image recognition system, or language model lies a critical foundation: data storage. The architecture that governs how data is stored, accessed, and protected forms the backbone of every AI application. As AI systems grow in both capability and [...]

Artificial intelligence has rapidly evolved from a research field into a cornerstone of modern digital infrastructure. As AI permeates critical sectors such as healthcare, finance, transportation, and defense, its security implications have become a central concern for governments worldwide. The dual-use nature of AI—capable of both beneficial and malicious applications—necessitates robust regulatory frameworks to mitigate [...]

Artificial intelligence is rapidly transforming industries, unlocking new possibilities and creating profound challenges for developers. Among the most intricate considerations is the legal framework that governs the use, distribution, and commercialization of AI-based products. Developers embarking on the journey from prototype to commercial release must navigate a maze of licenses, copyrights, and contractual obligations. Understanding [...]