In the past, due to limited hardware performance and compiler capabilities, programmers had to develop software with hardware limitations in mind. As hardware has advanced and compilers have added numerous functionalities, most programmers no longer need to consider hardware. Thanks to this, software development productivity has increased dramatically. Abstraction, in other words, means not needing to specify the concrete implementation details. Now, programmers are often not required to explicitly define what sorting algorithm to use, how memory should be managed, or how network communication should be handled, among other details.…

Recent years have marked the era of language models and AI. AI is becoming essential across all fields, driven by significant performance improvements. In certain domains, AI now surpasses human capabilities. It looks like advances in AI can solve all the existing problems. Nevertheless, greater intelligence alone does not solve every problem. Language models are central to intelligent software but require auxiliary tools, such as MCPs (Model Context Protocols), for accessing the web, temporary memory, and so on.…

Neural networks are black boxes, and this characteristic is shared by language models, multimodal models, and even agent systems built on neural networks. A black box means that we fundamentally cannot know the reasoning process that leads to a particular output. This makes it difficult to predict the consequences of changes to the model. Until recently, everything seemed to work well, but now problems are starting to surface. Excessive flattery, hallucinations, and abnormal behaviors are appearing even in top-tier AI services.…