(1) About GitHub Copilot Chat - GitHub Docs
(2) Brandolini’s Law - Brandolini's law - Wikipedia
(3) lawyer-used-chatgpt-in-court-and-cited-fake-cases-a-judge Lawyer Used ChatGPT In Court—And Cited Fake Cases. A Judge Is Considering Sanctions
Hi @simon_tomes Here is an article from own experienes exhibtitng in AI
For example
2.25+ Generative AI Use Cases in Intelligent Automation to Optimise Ops
- Summarise the main takeaways from the article. What are the essential concepts, tools, or methodologies discussed?
The essential AI practices are
Usione Cases: Harnessing The Power Of Generative AI in Intelligent Automation - Contract Management
Automatically extract key terms , obligatins from the contracts, analyse the compaince with legal requirements
3.Generate alerts using RPA for dates non-compliance issues
3.What are the challenges or opportunities?
Challenges are auotmation and skills and undertsnading of AI and knowlwegde of domain specific
Basic undertsnaidng and upskilling in RPA , Gen AI
Generative AI Powered
Intelligent Automation
And implementing in Testing on Low Code No Code as per the bussiness reuirement
I cheated and asked ChatGPT to generate an article for me, and shamelessly published it on my blog.
I also wrote about my reflections while completing days 1 - 3 of the 30 days challenge here, which I listed some other articles that I found useful (all have already been posted in here)
1 Like
Artificial Intelligence in Software Testing : Impact, Problems, Challenges and Prospect (arxiv.org)
The main point from this article are:
AI Impact: The paper discusses the significant impact of AI on software testing, enhancing automation and efficiency in various testing activities within the Software Testing Life Cycle (STLC).
Challenges: It identifies challenges such as the test oracle problem, data availability, adaptiveness to data, and exhaustive search spaces that affect the generality of AI applications in software testing.
Techniques Applied: A range of AI techniques like machine learning, neural networks, and genetic algorithms are applied across different testing activities to optimize and improve testing processes.
Future Prospects: The study anticipates further integration of AI in software testing, leading to more autonomous systems, cost reduction, and improved software quality .
The use of AI in software testing can significantly enhance the efficiency and effectiveness of testing processes. For instance, AI can automate repetitive tasks, allowing testers to focus on more complex aspects of testing that require human reasoning. This could potentially lead to faster identification of bugs and errors, improving the overall quality of the software.
However, the application of AI in testing also presents challenges. For instance, substantial data is required for AI training, and setting up AI systems can be complex. Despite these challenges, the potential benefits of AI in testing are immense and worth exploring.
In terms of opportunities, AI opens up new possibilities for predictive analytics in software testing. By analyzing past test data, AI can predict potential problem areas in the software, allowing testers to proactively address these issues. This could lead to more robust and reliable software products.
Ooh yeah, that would be pretty snazzy! Great idea. 
As someone who invested time and money into building a tool for exploratory testers who take notes, it would’ve been very cool to have explored the tech to see what’s possible. Sadly we were building it before the “AI explosion”.
1 Like
Summary of key take aways:
What is AI in Testing: IAI is changing the game for QA practices. Basically, AI brings in the potential to make testing more efficient, accurate, and thorough.
Creating Tests Automatically: AI tools can create test cases instantly, saving testers from the grunt work of writing scripts. These tools use smart techniques like machine learning to suss out potential test scenarios from code.
Running Tests and Keeping Them Up-to-Date: AI can help prioritize tests based on how risky they are and how they’ve performed in the past.
Spotting Bugs : AI is great at picking up on oddities in how software behaves, which can be a sign of bugs.
Challenges and Opportunities: The hurdles of bringing AI into testing, and needing skilled testers to make it work.
Applying this to my own project:
Better Test Coverage: AI-powered test generators could help make sure to check all the nooks and crannies of software.
Saving Time and Effort: Automating routine testing tasks with AI could free up time to focus on the trickier parts of testing.
Quicker bug finding : AI might catch bugs that slip past us during manual testing.
1 Like
The article provides an in-depth exploration of AI testing, highlighting its significance, techniques, benefits, challenges, and best practices. Here are the main takeaways:
- Definition of AI Testing:
- AI testing involves evaluating system functionality, performance, and reliability with AI assistance.
- It enhances traditional testing methods through AI technologies like machine learning and natural language processing.
- Techniques and Benefits of AI in Testing:
- AI enables faster and smarter test creation, data generation for data-driven testing, effortless test maintenance, and enhanced visual testing.
- Tools like Katalon, TestCraft, Applitools, and Testim Automate offer AI-powered features such as autonomous test script generation, self-healing mechanisms, and visual testing.
- Challenges and Best Practices:
- AI testing poses challenges like non-deterministic results, human bias in data, and complexity in AI systems.
- Best practices include clearly defining objectives, using high-quality training data, and leveraging data-driven testing.
- Role of ChatGPT in Testing: ChatGPT assists in prompt engineering and problem decomposition, augmenting testers’ capabilities in automating repetitive tasks.
- Demand for Skilled QA Engineers: The rise of AI testing intensifies the demand for QA engineers skilled in AI prompt engineering and utilizing vast volumes of input data.
Overall, the article emphasizes the transformative potential of AI in software testing, encouraging its adoption to enhance efficiency, accuracy, and innovation in testing practices.
In my testing context, there are clear potential uses for AI-driven testing techniques and tools to enhance efficiency and effectiveness. Here’s how the insights from the article apply:
- Test Creation and Maintenance: AI-enabled test script generation can expedite the process of creating test cases, especially for complex scenarios. This would save time and effort for testers, allowing them to focus on more strategic aspects of testing.
- Data Generation for Testing: AI can be leveraged to generate diverse and comprehensive test data for data-driven testing scenarios. This would streamline the testing process and ensure better test coverage without manual intervention.
- Challenges and Opportunities:
- One challenge would be understanding and validating AI model behavior, ensuring that the AI-powered testing tools provide accurate and reliable results.
- Another challenge is integrating AI-driven testing tools into existing testing processes and workflows seamlessly, ensuring smooth adoption and usage by the testing team.
- However, the opportunities presented by AI in testing are immense. By embracing AI technology, my team can enhance testing efficiency, improve test coverage, and deliver higher-quality software products to our clients.
Overall, the insights from the article highlight the potential benefits of integrating AI into testing processes, and I believe there are ample opportunities to leverage AI-driven testing techniques and tools in our projects to achieve better outcomes.
Personal Reflections: The insights from the article resonate strongly with my testing context. There are clear opportunities to leverage AI-driven testing techniques and tools to enhance efficiency and effectiveness in our projects. The potential uses of AI in test creation, data generation, and visual testing automation could significantly streamline our testing processes and improve the quality of our deliverables. However, there are challenges such as understanding AI model behavior and integrating AI-driven tools into our existing workflows seamlessly. Despite these challenges, I believe that embracing AI technology in testing holds immense potential to elevate our testing practices and deliver better outcomes for our clients.
1 Like
Hi 
I read article How AI can change Software Testing? It is an interesting prediction on AI’s impact on the future of Testing.
This article explores AI’s role in functional test automation, addressing challenges faced by QA engineers in manual testing. It says how traditional QA methods are time-consuming, especially for complex applications, leading to difficulties in meeting deadlines and ensuring full test coverage. Automated Testing, including tools like Selenium WebDriver, has alleviated some challenges, but AI presents opportunities for further streamlining the process.
AI optimizes testing by accelerating timelines, sorting through code quickly, and providing accurate results without human errors. It also offers better automation, adapting to code changes and identifying defects efficiently. Additionally, AI enhances understanding of client requirements, aids in detecting code flaws, and improves test automation with platforms like ChatGPT.
While AI integration in testing is ongoing, it promises to enhance accuracy and speed, allowing testers to focus on creating better testing methods and ensuring a seamless user experience. However, manual testing remains crucial alongside AI advancements.
Link: How AI can help Software Testing | BrowerStack | BrowserStack
3 Likes
Nice one, @mirekdlugosz. Always good to break the instructions as testers. 
And thanks for considering the history. I like how you’ve taken a step back to discover how we’ve got to where we’ve got. I think that context matters. I appreciate your summary too!
1 Like
Yikes! Sorry it seems to have disappeared. Thanks for coming back to share!
Article reviewed - QA Automation in 2024: Intelligent, fast, reliable, and affordable amidst growing technological complexity (marlabs.com)
The article explains that automated and manual testing together is best for thoroughly checking software. It talks about new ways of testing software quickly and cheaply, like testing early in development (if only I could convince others of the value!), not needing to code for some tests (beware of what the marketing materials declare), and using artificial intelligence (AI) to make testing smarter. Automation helps test many things fast and find problems early, saving time and money. It’s getting more important as technology grows more complicated!!
Source: Artificial Intelligence in Software Testing | Benefits and its Trends
I brief, from one online article (though sometimes with the grammatical errors, I do wonder if AI had been used to write it 
).
Self-driven ai code that can generate new scripts, detect tiny changes in code and adapt with appropriate test steps
Improved accuracy
Increased test coverage
Further improve user experience
Saving time and money (always a corporate must)
Faster to market
I wonder though, how far are we from writing algorithms that operate like a genuine user accessing information, and thus, replacing humans in testing?
Source: https://www.itconvergence.com/blog/how-can-ai-provide-benefits-for-software-testing/#:~:text=Artificial%20intelligence%20can%20be%20used,in%20a%20User%20Interface%20update.
7 Key benefits for application of AI in software testing.
Key Points/Summary: The article talks about how AI in software testing can aid the tester to deliver better results in less time and in a more cost effective manner.
I read this article.
The article describes the benefits of AI testing and some tools that enable it.
The key takeaways for me the benefits of AI testing are:
- it’s easier to generate test data and test cases
- it’s easier to maintain test cases and update them
- it can be used to do visual testing, which would not be as efficient as with regular tools
Hi Katie
On the article you’ve shared on the second image “Role of AI in Quality Assurance: Test Cases for Autonomous QA” the author is saying “AI explores path a human would never think of and intelligently refines exploration to maximize coverage” Is there clues on how that could be done?
1 Like
Link:
The article I read talks about how AI is changing the way we can test software. It explains that even though technology is advancing rapidly, traditional testing methods are struggling to keep up. AI offers a solution to this problem.
The article breaks down how AI is currently being used in testing. It mentions that AI is helping with some tasks, but it’s not being fully utilized yet. There are different levels of AI integration in testing, ranging from basic assistance to completely changing how testing is done.
There are lots of opportunities for AI to improve testing, like generating tests automatically and finding bugs faster. But there are also challenges, like making sure AI models are accurate and having enough good data for them to learn from. - In short, we are only scratching the surface of AI testing currently.
In my own experience with testing, I can see how AI could help make things faster and more accurate.
For example:
AI could automatically generate test cases or help find bugs in the code. But there are also things to watch out for, like making sure the AI is reliable and understanding how to use it effectively.
Overall, the article has given me some good ideas for how AI could improve testing in my projects. Super excited to see where we head from here.
1 Like
I am a bit late to the party, but I found an article exploring the role of Artificial Intelligence (AI) in revolutionizing software quality assurance (QA) through AI software testing. Key takeaways include:
- Introduction to AI Testing: AI Testing represents a significant advancement in software quality assurance. It leverages AI technologies and algorithms to optimize various aspects of the testing process, leading to enhanced efficiency, accuracy, and overall testing effectiveness.
- Benefits of AI in Testing: Incorporating AI into testing processes enhances accuracy, expands test coverage, efficiently creates tests, and streamlines test maintenance. AI algorithms improve accuracy through pattern recognition and data analysis, ensure dynamic test coverage, accelerate test cycles, and adapt testing strategies based on software changes.
- AI-Powered Tools for Testing: Leading AI-powered testing tools like Functionize, Katalon, Applitools, and Testim integrate advanced AI technologies into their systems, offering capabilities such as adaptive automation, smart test generation, visual AI precision, and self-healing test automation.
- Career Insights in AI Testing: Career opportunities in AI testing require a blend of traditional software testing knowledge and understanding of AI principles, with roles such as AI Test Engineers, AI Quality Assurance Analysts, and AI ethics and bias testing specialists offering diverse opportunities in the rapidly evolving field.
Article URL: AI Software Testing: The Ultimate Guide | Functionize
1 Like
Artificial Intelligence in Software Testing | Benefits and its Trends (xenonstack.com)
Artificial Intelligence saved time + Money = Faster delivery to Market.
Testing using it can be done steadily without much human intervention.
With the help of it automated tools in software testing, there will be high productivity.
It testing tools can help to increase the scope of tests that result in an overall improvement of software quality. Increases the Overall test coverage.
AI bot scan understand the client’s requirement properly and can produce the code for hundreds of test cases much more quickly than a human tester.
1 Like
Found this linkedin Article by Siddharth Shukla https://www.linkedin.com/pulse/revolutionizing-quality-assurance-exploring-ais-role-testing-shukla-ez4fc%3F.
This a very good read for a novice like me.
Summary: This article give a brief about Gen AI use-cases in testing.
Also give 2 good example of using Chat-GPT API to Test data generation and it’s LLM model for Test result Analysis.