Как я переехал с Claude на ChatGPT и собрал нового агента в Telegram (Codex Claw )
The speaker demonstrates creating a Telegram bot by finding the official bot creator, generating an API key, and connecting it to their CloudBot system. The installation process took approximately 16 minutes and provided step-by-step instructions in Russian.
Summary
The speaker walks through the technical process of setting up a Telegram bot integration. They begin by navigating to Telegram to find the official bot creation tool (referred to as 'Fuzzer'), where they create a new bot by providing a name and username, then copying the generated API key. After obtaining the necessary credentials, they return to their existing instruction set and insert a prompt, noting they are using version 3 of their system. The speaker expresses satisfaction that this new system provides feedback in Russian, contrasting it favorably with their previous CloudBot experience which only displayed information in English, making it difficult to understand the process. The installation of what they call 'CloudBot code' or 'Cloud Code' took approximately 16 minutes to complete, processing through an 800-line instruction set. The speaker suggests that they have since improved and corrected both the instruction and prompt, which should result in significantly reduced installation time for future deployments.
Key Insights
- The speaker successfully migrated from their previous CloudBot system to a new ChatGPT-based agent integrated with Telegram
- The new system provides real-time feedback in Russian, which the speaker found significantly more user-friendly than the English-only interface of the previous CloudBot
- The initial installation process required processing an 800-line instruction set and took approximately 16 minutes to complete
- The speaker has iteratively improved both the instruction set and prompts based on their experience, expecting faster installation times in future deployments
- The technical setup involves standard Telegram bot creation procedures including bot naming, username assignment, and API key generation through Telegram's official bot creation tool
Topics
Transcript
Now we create a bot in Telegram. To do this, we need to go to Telegram. In Telegram, find the official bot Fuzzer, open it, click Create New Bot. Here you need to write the name of the bot, username and copy this key that you use. Key API. I click Copy, copied this key. In principle, I can probably close it for now, if I need it, I will go ahead. And now I have everything ready. I have a bot, I have an instruction, I have everything ready to connect my CloudBot. I go back to our instruction and insert a prompt here. I copy this prompt and add it here. What is said in this prompt? The…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Игорь Зуевич
Сравнение Claude Code, Gemini и Codex — тесты на контент, анализ и изображения
The speaker is comparing AI coding assistants — Claude Code, Gemini, and Codex — by testing their ability to create image-generation agents. Each tool is being evaluated on how well it writes prompts and structures sub-agents for text-to-image and image-to-image tasks.
Экономия токенов и контекстного окна: настройка памяти нейросети – Compact сжатие контекстного окна
The transcript explains the 'Compact' command in AI agent sessions, which compresses the entire conversation history to reduce context window usage without switching sessions. It also covers related commands for full history clearing and automatic triggers for compact execution. The speaker recommends configuring automatic notifications or auto-execution when the context window reaches a certain threshold.
HR-агент на Claude Code: создаёт других сотрудников сам по запросу
The video demonstrates setting up a Telegram HR bot using Claude Code, walking through the process of creating a bot via BotFather, obtaining a Telegram user ID, and letting the code automatically generate the HR agent. The presenter shows how the system initializes itself by installing dependencies and launching the bot with minimal manual configuration.
Живые скиллы для Claude Code, Gemini и Codex | Как настроить super skills для ИИ агентов
The video explains how to create 'living' or 'super' skills for AI agents like Claude Code, Gemini, and Codex that self-update based on user feedback. The presenter demonstrates how these skills collect feedback after each task, store it in log files, and periodically incorporate that feedback into the skill's core instructions. This approach reduces token consumption and ensures skills continuously improve over time.
Планировщик для ИИ агента: 50 идей и готовые файлы для Claude, Codex и Gemini
The speaker describes their use of a scheduling/routing tool called Routins, which they compare to N8N, to automate daily delivery of curated YouTube videos on topics like Gemini and Claude. The system runs autonomously, collecting videos and generating concise summaries of their content without manual intervention.