🌐 Codestral ROS2 Gen: Network Scanner Extension Now Available!
⚡️Here it is - the second release of Codestral ROS2 Gen with a powerful new feature: the NetworkScanner!
🔍 What's New in This Release
The NetworkScanner module with efficient network discovery capabilities:
• Fast ICMP-based scanning for host discovery
• Asynchronous packet handling for optimized performance
• Configurable scan parameters (timeout, interval, etc.)
• Seamless integration with the existing ROS2 generation pipeline
🛠 How It Works
The NetworkScanner uses optimized ICMP echo requests (pings) to detect active hosts on a network. It employs an innovative approach with:
• Synchronous packet sending for precise timing control
• Asynchronous response collection for efficient handling
• Smart timeout management for reliable results
• Clean ROS2 message publishing for network status information
🧪 Key Components
• network_scanner.py: Core scanning orchestration
• network_host.py: Host state management
• scan_operation.py: Context-managed scanning operations
• network_parser.py: Network targets parsing
Full codebase documentation is available on projects's GitHub pages 📙
🚀 Try It Yourself
The detailed example documentation shows how to generate your own network scanner nodes. You can even use the standalone
This extension builds upon core generation system, demonstrating how the Codestral generator can create complex, functional ROS2 components with system-level interactions. 🤖
#ROS2 #AI #NetworkScanning #Robotics #CodeGenerating #Codestral
⚡️Here it is - the second release of Codestral ROS2 Gen with a powerful new feature: the NetworkScanner!
🔍 What's New in This Release
The NetworkScanner module with efficient network discovery capabilities:
• Fast ICMP-based scanning for host discovery
• Asynchronous packet handling for optimized performance
• Configurable scan parameters (timeout, interval, etc.)
• Seamless integration with the existing ROS2 generation pipeline
🛠 How It Works
The NetworkScanner uses optimized ICMP echo requests (pings) to detect active hosts on a network. It employs an innovative approach with:
• Synchronous packet sending for precise timing control
• Asynchronous response collection for efficient handling
• Smart timeout management for reliable results
• Clean ROS2 message publishing for network status information
🧪 Key Components
• network_scanner.py: Core scanning orchestration
• network_host.py: Host state management
• scan_operation.py: Context-managed scanning operations
• network_parser.py: Network targets parsing
Full codebase documentation is available on projects's GitHub pages 📙
🚀 Try It Yourself
The detailed example documentation shows how to generate your own network scanner nodes. You can even use the standalone
nscan command-line tool for quick testing! This extension builds upon core generation system, demonstrating how the Codestral generator can create complex, functional ROS2 components with system-level interactions. 🤖
#ROS2 #AI #NetworkScanning #Robotics #CodeGenerating #Codestral
GitHub
GitHub - lexmaister/codestral_ros2_gen: Generate ROS2 elements (nodes, interfaces, etc) with Codestral AI model
Generate ROS2 elements (nodes, interfaces, etc) with Codestral AI model - lexmaister/codestral_ros2_gen
⚡1🤯1
AI & Robotics Lab pinned «🌐 Codestral ROS2 Gen: Network Scanner Extension Now Available! ⚡️Here it is - the second release of Codestral ROS2 Gen with a powerful new feature: the NetworkScanner! 🔍 What's New in This Release The NetworkScanner module with efficient network discovery…»
🤩 Just tested Qwen 2.5-Omni and wow - it's impressive!
This free model accepts audio and video alongside text and images, plus it responds with both text and voice. We're just one step away from truly real-time AI conversation now - only need to cut down that input/response delay. Worth checking out here.
#QwenAI #MultimodalAI
This free model accepts audio and video alongside text and images, plus it responds with both text and voice. We're just one step away from truly real-time AI conversation now - only need to cut down that input/response delay. Worth checking out here.
#QwenAI #MultimodalAI
⚡1🆒1
👨🔬Testing Results: ROS2 Network Scanner Generation
I want to share the results from my test of ROS2 Network Scanner generation example.
After running 30 iterations of generating the ROS2 Network Scanner:
• Total test duration: ~6 hours 15 minutes
• Average successful generation time: ~2 minutes per attempt
• Distribution of attempts: Right-skewed (median: 4, mean: 6.7)
This means that, on average, the generator produces working code in about 13 minutes - quite reasonable performance for automated code generation in my opinion!
Failure Analysis
Looking at where generation stopped, the distribution clearly demonstrates the generator's stability:
• Over 80% stopped at the testing stage
• ~15% were successful attempts
• Only about 5% failed during the PARSING or GENERATION stages
Test Coverage Patterns
Examining the test pass rates revealed two distinct patterns:
• Basic functionality (7 tests): Node startup with valid/invalid parameters and handling overlapping scans using
• Advanced scenarios (9 tests): Including handling invalid JSON format in the
This suggests that generating code with specific behavior for edge cases remains challenging.
I've included all metrics and analysis notebooks in my project repository, so feel free to explore the data yourself!
#ROS2 #AI #NetworkScanning #Robotics #CodeGenerating #Codestral #testing
I want to share the results from my test of ROS2 Network Scanner generation example.
After running 30 iterations of generating the ROS2 Network Scanner:
• Total test duration: ~6 hours 15 minutes
• Average successful generation time: ~2 minutes per attempt
• Distribution of attempts: Right-skewed (median: 4, mean: 6.7)
This means that, on average, the generator produces working code in about 13 minutes - quite reasonable performance for automated code generation in my opinion!
Failure Analysis
Looking at where generation stopped, the distribution clearly demonstrates the generator's stability:
• Over 80% stopped at the testing stage
• ~15% were successful attempts
• Only about 5% failed during the PARSING or GENERATION stages
Test Coverage Patterns
Examining the test pass rates revealed two distinct patterns:
• Basic functionality (7 tests): Node startup with valid/invalid parameters and handling overlapping scans using
nscan utility• Advanced scenarios (9 tests): Including handling invalid JSON format in the
node <-> nscan interface and managing outdated scan resultsThis suggests that generating code with specific behavior for edge cases remains challenging.
I've included all metrics and analysis notebooks in my project repository, so feel free to explore the data yourself!
#ROS2 #AI #NetworkScanning #Robotics #CodeGenerating #Codestral #testing
🔥2
💡Using AI for Coding - Part 1: Choose the White or Black Box
For maximum effectiveness when using AI to develop code, I recommend one of two opposite approaches. In my experience, these contrasting methods yield better results than any compromise solution.
⬜️ 1. The White Box: Pair Programming
In this approach, you effectively take on both 'driver' and 'navigator' roles simultaneously. The key principle is maintaining full control and visibility over all code because, ultimately, it's yours.
AI serves as an extremely helpful partner for discussing specific aspects of code architecture, design patterns, optimization techniques, and similar topics. However, never reduce yourself to a simple 'driver' who only performs copy-paste operations. This is a dead end that will quickly turn your codebase into a total mess!
⬛️ 2. The Black Box: Test-Driven Development
This is the approach I'm currently experimenting with in my AI code generator project. With this method, you might not even look at the final code you're developing at all. Instead, your main focus shifts to creating:
• Proper prompts
• Appropriate AI-model settings
• Comprehensive test suites
These elements together ensure your code works as expected, without you needing to understand every implementation detail.
Why Extremes Work Better
So we have two distinct cases: the white box with full control over code development, or the black box where you control only inputs and outputs. My experience suggests that any kind of "gray box" approach will be less efficient, primarily impacting your development skills and time investment.
Adopting a mixed "gray box" approach often gives you the worst of both worlds. Instead of boosting productivity, this middle ground typically creates unnecessary complexity and duplicates work without delivering the real benefits of either pure approach. You'll find yourself juggling opposing strategies rather than fully leveraging the strengths of either method.
What are your thoughts on these approaches? I'd be very interested in your comments 😁
#Thoughts #Experience
For maximum effectiveness when using AI to develop code, I recommend one of two opposite approaches. In my experience, these contrasting methods yield better results than any compromise solution.
⬜️ 1. The White Box: Pair Programming
In this approach, you effectively take on both 'driver' and 'navigator' roles simultaneously. The key principle is maintaining full control and visibility over all code because, ultimately, it's yours.
AI serves as an extremely helpful partner for discussing specific aspects of code architecture, design patterns, optimization techniques, and similar topics. However, never reduce yourself to a simple 'driver' who only performs copy-paste operations. This is a dead end that will quickly turn your codebase into a total mess!
⬛️ 2. The Black Box: Test-Driven Development
This is the approach I'm currently experimenting with in my AI code generator project. With this method, you might not even look at the final code you're developing at all. Instead, your main focus shifts to creating:
• Proper prompts
• Appropriate AI-model settings
• Comprehensive test suites
These elements together ensure your code works as expected, without you needing to understand every implementation detail.
Why Extremes Work Better
So we have two distinct cases: the white box with full control over code development, or the black box where you control only inputs and outputs. My experience suggests that any kind of "gray box" approach will be less efficient, primarily impacting your development skills and time investment.
Adopting a mixed "gray box" approach often gives you the worst of both worlds. Instead of boosting productivity, this middle ground typically creates unnecessary complexity and duplicates work without delivering the real benefits of either pure approach. You'll find yourself juggling opposing strategies rather than fully leveraging the strengths of either method.
What are your thoughts on these approaches? I'd be very interested in your comments 😁
#Thoughts #Experience
🔥2
AI & Robotics Lab pinned «💡Using AI for Coding - Part 1: Choose the White or Black Box For maximum effectiveness when using AI to develop code, I recommend one of two opposite approaches. In my experience, these contrasting methods yield better results than any compromise solution.…»
💻 Using AI for Coding - Part 2: Workflow
Previous part: Choose the White or Black Box
In this chapter I focus on how to effectively use AI as your "programmer buddy." The main idea is that while AI knows tremendously much, only humans can set meaningful goals and choose the right path to achieve them.
When working on a project, my workflow follows these steps.
1. Architecture Consideration
Start by discussing ideas and the overall project architecture without writing any code. The outcome of this stage is a Block Diagram of the main logic. For all subsequent stages, it's very useful to keep this diagram in the model's context.
2. Defining Project Structure
Still without coding, discuss how to best divide functionality between modules and classes. This produces a structure of main modules and their relationships - either as a diagram or text description. This structure should also remain in the model's context during later stages.
3. Main Logic Implementation
The first step involving actual coding implements only the basic skeleton:
• Main logic with class drafts
• Error propagation
• Logging
• Testing framework
• Metrics handling
With AI assistance, I select the best patterns for code organization. This is also the time for research to explore new technologies and approaches. The result is a working prototype that demonstrates both the core functionality and crucial supporting elements like error handling and logging. The first basic tests also appear at this stage.
4. Main Development
Only after the prototype proves it can properly solve the task do I begin the main coding phase. Here I finalize the project structure beyond the main modules and classes, and create a proper test suite with high coverage.
In my experience, tests are best developed after a module or class is nearly complete. This requires a good playground to run and debug all elements separately - which is why creating a proper structure with modularity, logging, and error handling in the previous step is so important.
AI is very helpful at this stage for answering specific questions and quickly finding the causes of errors. While it's tempting to let AI create tests, there's a catch: AI can produce professional-looking test suites, but you may spend much more time making them work properly than if you created them yourself one by one, only consulting AI for specific questions.
5. Deployment
It's important to think about deployment from the early stages: will the project be deployed as a binary, a package, or perhaps simply cloned from GitHub without building? This consideration helps organize code more effectively.
This overview describes how I'm trying to use AI effectively for developing code in a "white box" manner. AI is tremendously helpful, but it can't eliminate fundamental design stages: architecture planning, block diagrams, prototyping, and release iterations remain essential across all engineering disciplines - mechanical, electrical, software, and beyond.
What do you think about this approach? I'd be pleased to hear your thoughts in the comments!
Previous part: Choose the White or Black Box
In this chapter I focus on how to effectively use AI as your "programmer buddy." The main idea is that while AI knows tremendously much, only humans can set meaningful goals and choose the right path to achieve them.
When working on a project, my workflow follows these steps.
1. Architecture Consideration
Start by discussing ideas and the overall project architecture without writing any code. The outcome of this stage is a Block Diagram of the main logic. For all subsequent stages, it's very useful to keep this diagram in the model's context.
2. Defining Project Structure
Still without coding, discuss how to best divide functionality between modules and classes. This produces a structure of main modules and their relationships - either as a diagram or text description. This structure should also remain in the model's context during later stages.
3. Main Logic Implementation
The first step involving actual coding implements only the basic skeleton:
• Main logic with class drafts
• Error propagation
• Logging
• Testing framework
• Metrics handling
With AI assistance, I select the best patterns for code organization. This is also the time for research to explore new technologies and approaches. The result is a working prototype that demonstrates both the core functionality and crucial supporting elements like error handling and logging. The first basic tests also appear at this stage.
4. Main Development
Only after the prototype proves it can properly solve the task do I begin the main coding phase. Here I finalize the project structure beyond the main modules and classes, and create a proper test suite with high coverage.
In my experience, tests are best developed after a module or class is nearly complete. This requires a good playground to run and debug all elements separately - which is why creating a proper structure with modularity, logging, and error handling in the previous step is so important.
AI is very helpful at this stage for answering specific questions and quickly finding the causes of errors. While it's tempting to let AI create tests, there's a catch: AI can produce professional-looking test suites, but you may spend much more time making them work properly than if you created them yourself one by one, only consulting AI for specific questions.
5. Deployment
It's important to think about deployment from the early stages: will the project be deployed as a binary, a package, or perhaps simply cloned from GitHub without building? This consideration helps organize code more effectively.
This overview describes how I'm trying to use AI effectively for developing code in a "white box" manner. AI is tremendously helpful, but it can't eliminate fundamental design stages: architecture planning, block diagrams, prototyping, and release iterations remain essential across all engineering disciplines - mechanical, electrical, software, and beyond.
What do you think about this approach? I'd be pleased to hear your thoughts in the comments!
⚡2
AI & Robotics Lab pinned «💻 Using AI for Coding - Part 2: Workflow Previous part: Choose the White or Black Box In this chapter I focus on how to effectively use AI as your "programmer buddy." The main idea is that while AI knows tremendously much, only humans can set meaningful…»
🌱 Can You Simulate Organic Life with ROS Nodes? Absolutely! ✨
I've been exploring the idea of using ROS2 nodes not just for robots, but as building blocks for simulating organic life—and the results are super promising!
Why is this approach interesting?
• Each ROS node acts like a "cell" or "organ," handling one function (movement, sensing, decision-making, etc.).
• The distributed, modular nature of ROS is perfect for mimicking how biological systems work together in real life.
• Nodes communicate via topics and services—very much like cells communicate through signals in nature.
• With ROS’s flexibility, you can easily scale up complexity, experiment with emergent behavior, and create fantastically detailed digital creatures.
What’s possible?
• Model complex, bio-inspired behaviors (think neural signals, homeostasis, swarming).
• Use ROS tools like Gazebo for 3D, physics-based environments.
• Mix and match algorithms in Python or C++ for rich, dynamic "organisms."
• Great for experimenting with concepts from biology, robotics, or artificial life.
Challenges?
Real-world biology is still way more complicated, but ROS nodes give us an amazing, practical starting point. Visualization and detailed modeling might need extra tools, but the pathway is wide open for creativity.
Bottom line: Using ROS nodes to simulate organic forms is not just possible—it’s a powerful, scalable way to blend robotics, biology, and AI. Can't wait to see where this leads!
🔧 Interested in the project or have questions? Join the discussion and let's build some digital life together!
#ROS2 #AI #BioInspired #OrganicSimulation #Robotics
I've been exploring the idea of using ROS2 nodes not just for robots, but as building blocks for simulating organic life—and the results are super promising!
Why is this approach interesting?
• Each ROS node acts like a "cell" or "organ," handling one function (movement, sensing, decision-making, etc.).
• The distributed, modular nature of ROS is perfect for mimicking how biological systems work together in real life.
• Nodes communicate via topics and services—very much like cells communicate through signals in nature.
• With ROS’s flexibility, you can easily scale up complexity, experiment with emergent behavior, and create fantastically detailed digital creatures.
What’s possible?
• Model complex, bio-inspired behaviors (think neural signals, homeostasis, swarming).
• Use ROS tools like Gazebo for 3D, physics-based environments.
• Mix and match algorithms in Python or C++ for rich, dynamic "organisms."
• Great for experimenting with concepts from biology, robotics, or artificial life.
Challenges?
Real-world biology is still way more complicated, but ROS nodes give us an amazing, practical starting point. Visualization and detailed modeling might need extra tools, but the pathway is wide open for creativity.
Bottom line: Using ROS nodes to simulate organic forms is not just possible—it’s a powerful, scalable way to blend robotics, biology, and AI. Can't wait to see where this leads!
🔧 Interested in the project or have questions? Join the discussion and let's build some digital life together!
#ROS2 #AI #BioInspired #OrganicSimulation #Robotics
⚡2
Forwarded from AI Post — Artificial Intelligence
Please open Telegram to view this post
VIEW IN TELEGRAM
🤯1
⚡️Get an AI software engineer that works for you 24/7. Only $20k/year!
😁2
Forwarded from Technology News
OpenAI Admits Newer Models Hallucinate Even More 🌍✨
Read Full Article
#OpenAI #AIhallucination #machinelearning #artificialintelligence #technews
Read Full Article
#OpenAI #AIhallucination #machinelearning #artificialintelligence #technews
The Left Shift
OpenAI Admits Newer Models Hallucinate Even More
In a technical report, the company said “more research is needed” to explain why hallucinations increase as reasoning capabilities scale
⚡2
Forwarded from AI Post — Artificial Intelligence
Anthropic's Chief Information Security Officer, Jason Clinton, predicts that AI-powered virtual employees will begin operating within corporate networks in the next year. These AI entities would possess their own "memories," roles, and even corporate accounts and passwords, offering a level of autonomy surpassing current AI agents. This advancement could revolutionize workplace efficiency, automating tasks and processes beyond today's capabilities
Its coming. It’s just a year away.
@aipost
Please open Telegram to view this post
VIEW IN TELEGRAM
⚡1
AI & Robotics Lab
🌱 Can You Simulate Organic Life with ROS Nodes? Absolutely! ✨ I've been exploring the idea of using ROS2 nodes not just for robots, but as building blocks for simulating organic life—and the results are super promising! Why is this approach interesting?…
Media is too big
VIEW IN TELEGRAM
⚡️They're Alive! 🐢
Simple Kinesis Turtle Simulation.
Experience virtual "life" in action as turtles move dynamically inside a simulated environment in temperature field. This project uses ROS2 and the classic
What is Kinesis?
Kinesis describes a non-directional movement response to stimuli, commonly observed in living organisms. In biology, it's how simple creatures respond randomly to environmental changes—think of a bug moving faster in open sunlight to find shelter.
🤖This is the first part of simulating organic movements, and ROS has proven to be incredibly convenient for developing such dynamic behaviors.
Want to Join or Read the Code?
Check out the project repository:👉 Project's GitHub Page
#ROS2 #Turtlesim #OrganicSimulation
Simple Kinesis Turtle Simulation.
Experience virtual "life" in action as turtles move dynamically inside a simulated environment in temperature field. This project uses ROS2 and the classic
turtlesim application to bring simple, engaging bio-inspired behaviors to life.What is Kinesis?
Kinesis describes a non-directional movement response to stimuli, commonly observed in living organisms. In biology, it's how simple creatures respond randomly to environmental changes—think of a bug moving faster in open sunlight to find shelter.
🤖This is the first part of simulating organic movements, and ROS has proven to be incredibly convenient for developing such dynamic behaviors.
Want to Join or Read the Code?
Check out the project repository:👉 Project's GitHub Page
#ROS2 #Turtlesim #OrganicSimulation
👍2🔥1