A very and very convenient service with AI chatbots
Several popular neurones (GPT / Llama / Google PaLM) are gathered in one place, you can quickly create your own bots, and there is a large library of user bots for different tasks.
It's a pleasure to use. You can use it on the web or download the app for iOS or Android. It's called Poe.
#productivity #coding #copywriting
Several popular neurones (GPT / Llama / Google PaLM) are gathered in one place, you can quickly create your own bots, and there is a large library of user bots for different tasks.
It's a pleasure to use. You can use it on the web or download the app for iOS or Android. It's called Poe.
#productivity #coding #copywriting
Since this channel was conceived not only as a "media about AI in plain language" but also as a free library of AI services for various tasks, I think it would be a big mistake not to preserve Cursor here for history.
Yes, by the way, about the library, what is meant. The channel has a pinned post with hashtags that you can click on according to your request. In turn, I strive to assign appropriate hashtags to posts with services that fit into a particular category. Use them and share your feedback.
So, Cursor is an AI assistant that significantly speeds up the development process by offering smart autocomplete, automatic error correction, and overall code generation. It is an alternative to Visual Studio Code.
Several of my developer friends have repeatedly spoken enthusiastically about Cursor, saving, well, a lot of hours on programming. I'm not a developer myself, but I believe them, so let's confidently add it to the library.
#coding@TochkiNadAI
Yes, by the way, about the library, what is meant. The channel has a pinned post with hashtags that you can click on according to your request. In turn, I strive to assign appropriate hashtags to posts with services that fit into a particular category. Use them and share your feedback.
So, Cursor is an AI assistant that significantly speeds up the development process by offering smart autocomplete, automatic error correction, and overall code generation. It is an alternative to Visual Studio Code.
Several of my developer friends have repeatedly spoken enthusiastically about Cursor, saving, well, a lot of hours on programming. I'm not a developer myself, but I believe them, so let's confidently add it to the library.
#coding@TochkiNadAI
👍1
It's been a while since the last collection. Today, we're talking about AI tools for code. What to choose?
I recently came across a survey of developers, and here are the top AI assistants for 2025 that are currently in the game:
1. Cursor – An AI-first development environment where a chatbot is integrated into the IDE to assist right in the process of writing code.
2. GitHub Copilot – Your code companion, predicts lines and suggests functions directly in the IDE.
3. Anthropic Sonnet 3.7 – A powerful alternative with a focus on security and explanation of solutions.
4. Tabnine – Local code generation with privacy, perfect for corporate projects.
5. Mutable AI – Automatic documentation creation and code readability improvement.
For new readers: there is a pinned message on the channel, essentially a library of AI services for your various tasks. Browse through, you can navigate by hashtags and choose the tools you need.
#coding@TochkiNadAI
I recently came across a survey of developers, and here are the top AI assistants for 2025 that are currently in the game:
1. Cursor – An AI-first development environment where a chatbot is integrated into the IDE to assist right in the process of writing code.
2. GitHub Copilot – Your code companion, predicts lines and suggests functions directly in the IDE.
3. Anthropic Sonnet 3.7 – A powerful alternative with a focus on security and explanation of solutions.
4. Tabnine – Local code generation with privacy, perfect for corporate projects.
5. Mutable AI – Automatic documentation creation and code readability improvement.
For new readers: there is a pinned message on the channel, essentially a library of AI services for your various tasks. Browse through, you can navigate by hashtags and choose the tools you need.
#coding@TochkiNadAI
🔥1
This media is not supported in your browser
VIEW IN TELEGRAM
And since today is about GitHub.
Gemini has befriended GitHub
The assistant will be able to:
– read and explain code
– debug bugs
– generate new code fragments
But there's a catch. Only if you're on a paid plan ($20/month).
How it works:
1. Go to https://gemini.google.com
2. Click "+" in the query bar → "Import code"
3. Paste the link to a GitHub repository (up to 5000 files, no more than 100MB)
4. If necessary, link GitHub to your Google account
5. Enter a query → click "Submit"
Important: only one repository can be connected at a time. After importing, you can continue working even from your phone.
But don't forget – AI still makes mistakes, so manual checking is a must-have.
#coding@TochkiNadAI
Gemini has befriended GitHub
The assistant will be able to:
– read and explain code
– debug bugs
– generate new code fragments
But there's a catch. Only if you're on a paid plan ($20/month).
How it works:
1. Go to https://gemini.google.com
2. Click "+" in the query bar → "Import code"
3. Paste the link to a GitHub repository (up to 5000 files, no more than 100MB)
4. If necessary, link GitHub to your Google account
5. Enter a query → click "Submit"
Important: only one repository can be connected at a time. After importing, you can continue working even from your phone.
But don't forget – AI still makes mistakes, so manual checking is a must-have.
#coding@TochkiNadAI
And right now OpenAI has introduced Codex!
This is an agent, an assistant for developers.
- Codex is trained on billions of lines of code
- Integrates with GitHub, operates in the cloud, each task is performed separately
- Understands more than a dozen programming languages
- Can write, explain, and fix code
- Works in editors, terminal, websites — anywhere
Here details
Here try
#coding@TochkiNadAI
#Agents@TochkiNadAI
This is an agent, an assistant for developers.
- Codex is trained on billions of lines of code
- Integrates with GitHub, operates in the cloud, each task is performed separately
- Understands more than a dozen programming languages
- Can write, explain, and fix code
- Works in editors, terminal, websites — anywhere
Here details
Here try
#coding@TochkiNadAI
#Agents@TochkiNadAI
It's been a while since we've talked about vibe coding.
And vibe-agenting!)
So, Warp is now a full-fledged environment with agents.
They've called it ADE – Agentic Development Environment and launched version 2.0.
In short – Warp 2.0 consists of four things:
Code. An engine that understands large repositories, shows diffs, and has topped Terminal‑Bench and SWE‑bench.
Agents. Launched by task, can work autonomously, but you can always intervene.
Terminal. All the familiar features remain: auto-completion, mouse, hotkeys.
Drive. A shared space for prompts, variables, and notes that can be shared with the team or agents.
Prices are quite standard: 0 / 15 / 40 $.
#coding@TochkiNadAI
And vibe-agenting!)
So, Warp is now a full-fledged environment with agents.
They've called it ADE – Agentic Development Environment and launched version 2.0.
In short – Warp 2.0 consists of four things:
Code. An engine that understands large repositories, shows diffs, and has topped Terminal‑Bench and SWE‑bench.
Agents. Launched by task, can work autonomously, but you can always intervene.
Terminal. All the familiar features remain: auto-completion, mouse, hotkeys.
Drive. A shared space for prompts, variables, and notes that can be shared with the team or agents.
Prices are quite standard: 0 / 15 / 40 $.
#coding@TochkiNadAI
This media is not supported in your browser
VIEW IN TELEGRAM
How to Create a Native iOS App with Kiro in a Few Hours
I came across an example of using AWS Kiro, a new AI-IDE with AI agents and MCP servers.
The author of the video JeredBlu created a fully functional Swift app for iOS, integrated with Apple Health and Apple Watch, in just a few hours. He wanted to manually add missed workouts if Apple Watch didn't count them.
The process:
First, he described the task in Kiro using spec-driven development mode, forming detailed technical specifications and a plan. Then, through the MCP servers, AI agents gathered the necessary documentation, looked for real cases, and broke the task into separate steps. The design, task list, and then the code with tests and Apple Health integration were automatically generated. When bugs or errors occurred, AI agents quickly fixed them, learning from mistakes through embedded memory. Within a couple of hours, a fully operational application was created.
Kiro + MCP 🤌
Full video
Waitlist Kiro
#coding@TochkiNadAI
#agents@TochkiNadAI
I came across an example of using AWS Kiro, a new AI-IDE with AI agents and MCP servers.
The author of the video JeredBlu created a fully functional Swift app for iOS, integrated with Apple Health and Apple Watch, in just a few hours. He wanted to manually add missed workouts if Apple Watch didn't count them.
The process:
First, he described the task in Kiro using spec-driven development mode, forming detailed technical specifications and a plan. Then, through the MCP servers, AI agents gathered the necessary documentation, looked for real cases, and broke the task into separate steps. The design, task list, and then the code with tests and Apple Health integration were automatically generated. When bugs or errors occurred, AI agents quickly fixed them, learning from mistakes through embedded memory. Within a couple of hours, a fully operational application was created.
Kiro + MCP 🤌
Full video
Waitlist Kiro
#coding@TochkiNadAI
#agents@TochkiNadAI