Как научить ИИ писать в вашем стиле: система контента с Claude и Obsidian
The speaker explains how to export content from a Telegram channel using the desktop version of Telegram to gather posts for content analysis. They recommend using the desktop version over mobile apps because it offers more functionality and export capabilities.
Summary
The speaker demonstrates a process for extracting content from a Telegram channel that contains a mix of text and video posts. They emphasize the importance of using Telegram's desktop version rather than mobile applications, explaining that the desktop version can be downloaded from the official Telegram website and offers more software-like functionality compared to standard mobile or OS applications. The export process involves navigating to the channel, accessing a three-button menu, and selecting 'export chat history.' The speaker details the export configuration, noting that they disable most options and focus specifically on JSON format for the file output. They configure the export to include all messages from the channel's inception to the current date. The speaker mentions that this export process typically takes 4-5 minutes to complete, though they don't execute it during this demonstration. This appears to be part of a larger workflow for analyzing or working with content data, likely related to training AI systems to understand writing styles based on historical posts.
About this episode
Как научить ИИ писать в вашем стиле: система контента с Claude и Obsidian В этой серии видео я покажу, как выстроить полноценную систему создания контента с помощью AI агента, который пишет именно в вашем стиле, а не выдаёт безликие тексты. Я делюсь реальной схемой, которую сам использую для телеграм, Threads и Instagram — с выгрузкой контента, базой знаний в Obsidian и обучением агента на ваших паттернах. Никаких сложных технических знаний не нужно — просто повторите шаги и получите систему, которая работает на вас. #claudecode #obsidian #копирайтинг #openclaw #codex
Key Insights
- The speaker claims that Telegram's desktop version provides more functionality than mobile applications and resembles software more than typical OS applications
- The speaker demonstrates that Telegram channels can export their entire message history in JSON format through a simple three-step process
- The speaker reveals that the export process for complete chat history typically requires 4-5 minutes to complete
Topics
Transcript
Everything I need to do is go to my channel, where I publish some content and upload all these posts. You see, they alternate here, some text posts, some video posts. And here, as we see, all my posts are also divided into text and video. That is, we must upload these posts. How to do this as simply as possible? I recommend using not the Telegram application, but the desktop version for Telegram. It looks a little different, it is downloaded from the official Telegram site. Just type in the search for the desktop version of Telegram and download it from the official Telegram site. It looks a little different, that is, it does not look like an application…
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.