AI & Robotics Lab
19 subscribers
75 photos
28 videos
9 files
108 links
Explore AI code generation, robotics, and ROS with original projects and hands-on guides. Follow along as I share my experience, code samples, and tips for building intelligent systems.
Download Telegram
😁1😱1
Forwarded from AI Post — Artificial Intelligence
OpenAI o3-mini scored 92% in OpenAI Research Engineer interviews. 👀

When do you think OpenAI will stop hiring research engineers and start relying on their own AI models?

@aipost 🪙 | Our X 🥇
Please open Telegram to view this post
VIEW IN TELEGRAM
👍1
ROS2: Modular & Resilient Node Parameters

In ROS2, each node controls its own settings, creating a system that’s both modular and remarkably resilient. What’s more, ROS2 comes with a rich array of built-in methods for managing parameters, making your nodes even more flexible and robust:

Decentralized Control:
Each node declares and manages its own parameters, creating a plug-and-play architecture that minimizes risk and enhances robustness.

Dynamic Adjustments:
Built-in APIs let you update parameters on the fly—no need for restarts. Change callbacks ensure that live updates are smoothly integrated into your node performance.

Extensive Built-In Methods:
ROS2 provides a variety of tools, from dynamic parameter handling to advanced introspection methods. This extensive toolkit offers everything needed—from automatic type checks to seamless integration of new configurations—making error handling and system adaptation straightforward.

Intuitive Organization:
Use namespaced parameters, coupled with thorough inline documentation, to keep configurations neat and scalable. This clarity not only aids team collaboration but also simplifies long-term maintenance.

Streamlined Configuration Management:
Centralized YAML or launch files allow you to manage settings consistently across development, testing, and production environments without fuss.

Real-Time Monitoring:
Built-in introspection tools and logging capabilities keep you informed of parameter changes as they happen, ensuring that your system remains agile and well-monitored.

This node-centric approach, enhanced by an impressive suite of built-in methods, emphasizes modularity and resilience—empowering you to build dynamic, high-performance ROS2 applications with ease and confidence.

#ROS #knowledge
🔥1
Media is too big
VIEW IN TELEGRAM
Working with Parameters in ROS2: A Quick Example

1️⃣ Defining Parameters:
Using ParameterDescriptor, we define parameters like focal_length with details such as:
- Type: PARAMETER_DOUBLE
- Description: "Focal length in mm"
- Range: 1.0 to 100.0, step 0.1

2️⃣ Access & Modify Parameters:
- Use the CLI with commands like ros2 param get/set.
- Alternatively, use a GUI to adjust values in real time for better flexibility and usability.

3️⃣ Error Handling:
ROS2 comes with built-in methods to validate parameters based on their descriptors. For example, if you try setting focal_length to 40.44 (which doesn't match the step size of 0.1), you get a precise error:
"Setting parameter failed: The value is not close enough to a valid step."

❗️This means ROS2 ensures parameters strictly follow the defined constraints—like ranges, step increments, and types—without requiring custom validation logic in your code.

#ROS #knowledge #example
1
This media is not supported in your browser
VIEW IN TELEGRAM
Salesforce: We don't need any more software engineers this year...
🤔2
Media is too big
VIEW IN TELEGRAM
📢 Use Mistral's Latest Coding Model for Free in Your Work!

Recently, Mistral announced their newest code-specific LLM - Codestral 25.01. The best part? You can get an API key absolutely free and start using it right away in popular tools like VS Code through Continue - one of the most popular AI coding assistants!

Get instant code suggestions, explanations, and completions right in your editor. 🚀

#FreeTool
1
🤖 Playing with Codestral Model API via Postman 🛠

Now that we have access to the Codestral Model API, let's explore it using REST API requests to see how it responds to different parameters! For this purpose, I recommend using Postman - a free tool that provides convenient features for working with APIs 🔧

🚀 Getting Started:
- Create a workspace in Postman
- Create a collection inside it to store your requests

🔌 Available Endpoints:
- Fill-in-the-middle: https://codestral.mistral.ai/v1/fim/completions
- Chat: https://codestral.mistral.ai/v1/chat/completions

💻 Let's experiment with the chat endpoint using a POST request. We'll modify the parameters from the API docs to focus on a coding task: generating a function to calculate Fibonacci numbers.

🔑 Authorization: For authorization, you'll need a Codestral API key (see my previous post for instructions on obtaining one). Pro tip: store such sensitive data in variables!

⚙️ Testing: After sending the modified request, you can observe the model's response. All model parameters are customizable to fine-tune the output.

API documentation

#CodestralAPI #Tutorial
2
🌟 Mind-blowing Magic of Modern LLM Image Recognition! 🌟

I've found Claude 3.5 Sonnet by Anthropic to be very effective for my daily tasks.

Pro Tips: 📱 Not familiar with a new app/website? Just take a screenshot and ask about your questions! 💻 Debugging troubles? Snap your IDE screen and ask what's wrong! ⚡️ Struggling with bash? No need for explanations - just share the screenshot, and the AI often understands the issue instantly!

It's truly impressive how these tools are transforming our approach to problem-solving. We're living in fascinating times!
🔥2
🤖 Why Learn Programming in the AI Era?

Yes, AI can write code as well as humans now. We can simply copy-paste its solutions and problem is done! But is this the way we want to go?

👋 Here's the smarter way:
• Programming itself is a creative journey that trains your brain and brings satisfaction.
• Understanding code lets you collaborate with AI effectively - you can discuss approaches, evaluate solutions, and guide the AI toward better results.

💪 With coding knowledge, you can:
• customize AI-generated solutions,
• spot potential issues,
• break down complex problems,
• make informed architectural decisions.

Think of AI as your smart coding buddy! It can help you level up from a regular developer to a tech architect - it's a unique opportunity that's only possible today. But to seize it, you need to be at your best and keep growing your skills!🚀

We should be the ones who direct AI, not the ones who blindly follow it. What do you think?

#Programming #AI #CodingLife #TechEducation
1👍1
ROS2 Nodes Factory

I'm excited to share a project I've been working on recently: a ROS2 nodes factory! 🛠

After taking a short break from my regular posts, I've been focused on developing a framework that can automatically generate ROS2 components using AI. The project, called Codestral ROS2 Generator, is now available on my GitHub page.

⚠️ What makes this project special?

The framework follows a "test-driven coding" philosophy - you simply define your ROS2 interfaces and write tests for how your node should behave. Then the generator, powered here by Mistral's Codestral latest model, creates code that satisfies those requirements.

For example, I've included a working implementation of a service that calculates object height (remember my previous experiments with this). The generator was able to create a fully functional ROS2 service node that passes all 14 tests.

🚀 Getting started

📓Project's README and Example instruction explain how to setup and use the generator - you can try it in action.
📔 The documentation explains the system architecture and guides you through creating custom ROS2 nodes for your specific needs.

The project integrates with Mistral AI's powerful Codestral model to understand ROS2 concepts and generate appropriate code. While my previously described method for getting Codestral API keys is not supported yet, you can obtain a free experimental key from the API Keys section of La Plateforme, which works perfectly with this project (also it allows to try any other Mistral models).

🤝 Contributions welcome

I'd love to collaborate with anyone interested in improving this framework. Whether you want to add support for more ROS2 components, improve the code generation, or enhance the examples, contributions are very welcome!

Happy generating! Let me know if you try it out!

#ROS #Codestral #CodeGenerating
1🔥1
AI & Robotics Lab pinned «ROS2 Nodes Factory I'm excited to share a project I've been working on recently: a ROS2 nodes factory! 🛠 After taking a short break from my regular posts, I've been focused on developing a framework that can automatically generate ROS2 components using…»
Codestral ROS2 Generator tech description.

👋 I've just published a detailed technical overview in Russian of my Codestral ROS2 Generator project - an AI-powered solution that automatically generates ROS2 components (nodes, services, actions) using the Codestral model.

💡The article covers:
- Complete project architecture.
- Key classes and their interactions.
- The generation workflow from prompt to tested code.
- Performance metrics and evaluation.

Check out the full technical breakdown on my blog: Let's Go Design

#CodeGenerating #ROS #Codestral
🔥1🆒1
We'll see...
Forwarded from AI Post — Artificial Intelligence
Media is too big
VIEW IN TELEGRAM
"By 2027... AI will be autonomous enough to replicate a software engineer's job."

Replit CEO Amjad Masad discusses AI agents mastering software engineering. SWE-bench shows rapid progress: from GPT-3 (22%) to Anthropic's latest (~70%) today. Benchmark saturation by 2027 suggests AI autonomy in coding.

He predicts AI agents will be able to build 20% of SaaS within a year.

@aipost 🪙 | Our X 🥇
Please open Telegram to view this post
VIEW IN TELEGRAM
👍1
Forecasts are getting more and more optimistic 🤔
🆒1
Forwarded from AI Post — Artificial Intelligence
This media is not supported in your browser
VIEW IN TELEGRAM
Anthropic CEO, Dario Amodei

AI coding capabilities will reach a "very serious" level by the end of 2025 — and may match the best human coders by late 2026

@aipost 🪙 | Our X 🥇
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥1