ВММ

The article presents the results of a study on the possibilities of building software behavioral components based on large language models (LLMs) and their use in gaming systems. The subject of the research is the behavioral component of non-player characters (NPCs) in computer games, integrated with an LLM. The aim is to explore and analyze the features of applying LLMs to simplify NPC development. The study examines game AI types – reactive, state-driven, and learning-based.

This article presents a comparative analysis of automatic Solidity smart contract generation using large language models (LLMs) based on two approaches: natural language textual descriptions and formal algebraic specifications. The study analyzes smart contracts generated by LLMs (ChatGPT-4, Claude 3.7 Sonnet, DeepSeek-V3) as well as by the AI-based tool GitHub Copilot, evaluating their syntactic correctness, compliance with initial requirements, and security.

ctive methods to protect personal data in online texts. Existing anonymization methods often prove ineffective against complex LLM analysis algorithms, especially when processing sensitive information such as medical data. This research proposes an innovative approach to anonymization that combines k-anonymity and adversarial methods. Our approach aims to improve the efficiency and speed of anonymization while maintaining a high level of data protection.