\u041b\u044e\u0431\u043e\u043f\u044b\u0442\u043d\u044b\u0435 \u043f\u0440\u0438\u043c\u0435\u0440\u044b \u0438\u0433\u0440 \u0432\u044b\u043b\u043e\u0436\u0438\u043b sama \u0432 \u043d\u043e\u0432\u044b\u0439 GPT-5.4<\/b><\/p>\n
\u041c\u0435\u043d\u044f \u043f\u0440\u044f\u043c\u043e \u0437\u0430\u0446\u0435\u043f\u0438\u043b\u043e. \u041d\u043e \u0432\u043e \u043f\u0440\u043e\u043c\u043f\u0442\u044b \u0442\u0430\u043c \u0435\u0441\u0442\u044c \u043d\u0435 \u0432\u0441\u0435. \u041d\u0430\u043f\u0438\u0441\u0430\u043d\u043e:<\/p>\n
\u041d\u0443 \u0442\u0435 \u0438\u0442\u0435\u0440\u0430\u0446\u0438\u043e\u043d\u043d\u043e! \u0410 \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u043d\u0443\u0436\u043d\u043e \u0438\u0442\u0435\u0440\u0430\u0446\u0438\u0439? \u042f \u0434\u0443\u043c\u0430\u044e \u0437\u0430 2 \u043c\u0435\u0441\u044f\u0446\u0430 \u0442\u0430\u043a\u043e\u0435 \u0443\u0436\u0435 \u043e\u0441\u0438\u043b\u044e.<\/p>\nTactical RPG created with GPT\u20115.4 over multiple turns, using Playwright Interactive for browser playtesting and image generation for the game\u2019s visual style, characters, and thematic asset set. The game features turn-based combat on a grid map, with systems for movement, actions, positioning, and encounter flow, alongside a presentation layer refined through iterative UI and shader work. Image generation was used to create characters and Playwright was used to validate the interface, inspect and refine UI behavior, and support iterative edits as the game\u2019s combat, visuals, and overall feel were tuned over multiple rounds.<\/code><\/p>\n