GitHub anticipates that in the coming years, 80% of the world’s code will be generated by AI [1]. Although it is difficult to find exact information on the number of sold GitHub Copilot licenses, it is undeniable that we are observing a change in the way organizations and programmers themselves create new IT solutions. At Inero, we are working on many projects simultaneously, so we are eager to test the latest solutions that are designed to optimize teamwork, deliver solutions faster and better.

In this article, we will talk about our experiences with GitHub Copilot.

What is GitHub Copilot?

GitHub Copilot is a tool designed for programmers, utilizing an advanced language model (known as LLM – Large Language Model) tailored for the analysis and understanding of source codes. A set of appropriate plugins and tools, allows for the optimization of the software development process, providing programmers with automatic coding hints and completions, suggestions, syntax analysis, and even generating documentation. Developed by Microsoft, the tool is based on artificial intelligence and was created to enhance the productivity of programmers and improve the quality of the source code.

Further than Closer, Slowly Towards the Goal

The use of GitHub Copilot in most cases allows us to speed up programming work, importantly, not only in creating the code itself but also in more tedious tasks. For example, since we started testing GitHub Copilot in our team, we have visited StackOverflow much less frequently. Copilot accelerates work when our programmers need to generate relatively simple and repetitive code that can be easily assessed as correct at first glance.

• • Copilot greatly speeds up work with regular expressions and certainly optimizes the time for writing repetitive code.
  • Copilot is also an effective tool for generating code documentation, essentially being able to almost entirely do it for us. Of course, the generated content always needs to be verified, but we haven’t encountered significant errors. Usually, we add more details to the result, however, in many cases Copilot is sufficient. Documenting, for example, a single block of code, when it’s quite extensive, can take approximately even a minute. With Copilot, this can be done in a few, up to several seconds, depending on whether we need to elaborate on the content.
  • From the perspective of experienced programmers, the use of this solution can be described as an advanced Intellisense working in Line-By-Line mode. The programmer, starting to create a block of code, further uses Copilot’s suggestions. In such a case, the verification is immediate and if something is wrong, we correct it ourselves right away. When Copilot suggests a larger block of code, e.g., 10-15 lines, then analyzing whether this code does exactly what it should, can take more time than writing it independently. Especially since among these 15 lines, 14 might be correct, but one is erroneous and needs to be identified.
  • From the perspective of a less experienced programmers, the reception of this solution may be different. Writing code takes them more time than it does for an experienced developers, so Copilot seems helpful. However, during the analysis of code from Copilot, the user might not notice at all if something is amiss – the problem might only be detected during a code review conducted by a more experienced person.
  • After some time, we get used to Copilot sending us suggestions, so it’s necessary to learn how to work with this tool. Initially, these suggestions can disrupt the rhythm of normal line-by-line code writing. Instead of continuing to write, we stop to read the proposed suggestions. However, in the plugin’s configuration, it’s possible to disable continuous prompting and leave only key shortcut-based prompting – here the decision depends on the programmer, who can choose the degree of “support” that suits them best.
  • When we work on more complicated functionalities, for example, using a new library, Copilot can guide us in some way. Its suggestions in such cases can be accurate and even if they are not fully correct, they allow for a quicker understanding of how to reference the library, which otherwise would require analyzing the documentation.

Comment from the CEO of Inero Software

Andrzej Chybicki: Measuring the effectiveness of using Copilot from a management perspective is difficult – we don’t have objective indicators telling us whether and to what extent the investment in the license has shortened the time spent on the software projects we are entrusted with. That’s the first point. Secondly, some clients express concerns about the security of code analyzed by AI, especially in projects related to cybersecurity or involving sensitive data processing. Hence, we encounter situations where using Copilot is not advisable.

What advantages and disadvantages have we noticed?

Analyzing the experiences of our team, we can identify the pros and cons of using GitHub Copilot.

Will we continue to use GitHub Copilot at Inero? Definitely yes.

The use of GitHub Copilot in daily work brings many benefits. However, it’s important not to lose vigilance and not to fully rely on its suggestions. It’s crucial to continuously monitor the code prepared with this tool. The development of the technology, which Microsoft is working on, will surely bring many updates and improvements in the coming months.

[1] https://github.blog/2023-02-14-github-copilot-for-business-is-now-available/

Artykuł GitHub Copilot – review of pros and cons in a programmer’s work pochodzi z serwisu Inero Software - Software Consulting.

The end of the year is a time for summaries. In the world of IT, many interesting things have happened, so in this article, we decided to focus on AI. The development of artificial intelligence and its media presence accelerated to an unprecedented scale. Tools based on Large Language Models (LLMs) have been popularized and made widely available to users from various industries, not just technological ones. We decided to summarize the year with Andrzej Chybicki, the CEO of Inero Software. Here is the list he identified as the key 5 events of the past year. 

Fact 1: OpenAI – artificial intelligence becomes widely accessible 

OpenAI played a tremendous role in popularizing the field of artificial intelligence in the context of human language understanding. In 2022, they released ChatGPT, and in the following months, they presented new, improved models. These advancements not only improved the performance of existing applications but also opened new avenues for AI in healthcare, environmental science, administration, marketing, and more.  

In 2023, ChatGPT saw remarkable advancements, featuring enhanced learning algorithms for improved accuracy and nuanced conversations, personalized user interactions, expanded language support for global accessibility, and broader application integration. OpenAI emphasized ethical considerations and bias reduction, incorporated real-time learning for up-to-date content, improved multimedia interaction capabilities, and boosted the tool’s robustness and reliability. Additionally, ChatGPT was tailored for specific industries, providing specialized functionalities and knowledge, marking a significant leap in AI technology and user-centric applications. 

Expert Insight 

OpenAI was the first widely recognized large language model. In the coming years, we are likely to see various versions of LLMs designed for specific applications – in fact, this has been happening for a few months now. OpenAI, despite being a pioneer, at least in terms of recognizability, is not always considered the best model for everything. The direction of development is certainly popularization in a similar way as it was with computers (i.e., LLMs like PCs) and specialization, meaning specialized language models designed for specific applications or even entities or people.  

Fact 2: GitHub Copilot – a leader in AI/LLM implementation 

One of the key roles in the development of artificial intelligence is played by Microsoft, which collaborates with OpenAI. Over the past year, Microsoft has continued to refine its vision of Microsoft Copilot. Let’s focus on the solution for developers: GitHub Copilot. In 2023 it underwent significant changes and enhancements. Here are the key updates: 

In 2023, GitHub Copilot introduced several significant enhancements to bolster its role in AI-driven software development. The GitHub Copilot Chat, now generally available and powered by OpenAI’s GPT-4, provides more accurate code suggestions and explanations, using natural language to aid developers in various languages. This feature is integrated with both the GitHub platform and its mobile app, supporting coding, pull requests, and documentation. Additionally, GitHub Copilot Enterprise was introduced to tailor the tool to specific organizational needs, helping developers quickly adapt to their organization’s codebase and streamline tasks like documentation and pull request reviews, aimed at boosting enterprise-level productivity and security. The GitHub Copilot Partner Program was launched, integrating Copilot with various third-party developer tools and services, thereby creating a broad ecosystem that enhances the capabilities of developers using AI. Finally, GitHub unveiled new AI-powered security features in its Advanced Security suite, including a real-time vulnerability prevention system and application security testing features to detect and remediate code vulnerabilities and secrets, further securing the software development process. 

Expert Insight 

Thanks to its collaboration with OpenAI, Microsoft became a leader in AI/LLM implementation worldwide in 2023. Microsoft’s strategy in this area is based on using the LLM model to support (but not replace) as many activities and processes using Microsoft products as possible. Particularly important was ensuring an appropriate level of SLA (aligned with other Azure services) and data security. Among the most significant changes, apart from the mentioned GitHub Copilot (which aims to support developers in coding), are Copilot plugins available in practically all of this company’s flagship products (Word, Excel, PowerPoint, Outlook). 

In December 2023, Microsoft also presented the CoPilot Studio solution, which enables the creation of low-code/no-code IT systems with significant support from the OpenAI model. This effectively allows for the easy expansion of existing Azure low-code solutions such as Azure Agents with conversational bots or AI-supported database adapters. Although CoPilot Studio is not yet available in its final form, Microsoft clearly communicates development directions and the advantages that developers, engineers, and users can experience from its use. From the presentations of Microsoft representatives, it can be inferred that Microsoft’s goal is to lower the entry threshold for creating and implementing new advanced AI solutions, as using low-code platforms does not require as deep technical knowledge as traditional coding. We can expect widespread interest in these solutions not only from the largest companies using MS Azure in the coming years. Currently, among experts, the question is not “whether to use AI” but how to implement it to not fall behind the competition. Those entities that create a coherent strategy for incorporating AI-based products into their processes in the coming years will be able to significantly benefit from the revolution that is already taking place. 

Fact 3: The European AI Act: A Regulatory Milestone 

On 14 June 2023, the European Parliament adopted its negotiating position on the AI Act. Parliament’s priority is to make sure that AI systems used in the EU are safe, transparent, traceable, non-discriminatory and environmentally friendly. Parliament also wants to establish a technology-neutral, uniform definition for AI that could be applied to future AI systems. The AI Act sets different rules for different AI risk levels. 

The new rules establish obligations for providers and users depending on the level of risk from artificial intelligence. While many AI systems pose minimal risk, they need to be assessed. 

Unacceptable risk 

Unacceptable risk AI systems are systems considered a threat to people and will be banned. They include: 

• Cognitive behavioral manipulation of people or specific vulnerable groups: for example voice-activated toys that encourage dangerous behavior in children 
• Social scoring: classifying people based on behavior, socioeconomic status or personal characteristics 
• Real-time and remote biometric identification systems, such as facial recognition 

Some exceptions may be allowed: For instance, “post” remote biometric identification systems where identification occurs after a significant delay will be allowed to prosecute serious crimes but only after court approval. 

High risk 

AI systems that negatively affect safety or fundamental rights will be considered high-risk and will be divided into two categories: 

1) AI systems that are used in products falling under the EU’s product safety legislation. This includes toys, aviation, cars, medical devices and lifts. 

2) AI systems falling into eight specific areas that will have to be registered in an EU database: 

• Biometric identification and categorisation of natural persons 
• Management and operation of critical infrastructure 
• Education and vocational training 
• Employment, worker management and access to self-employment 
• Access to and enjoyment of essential private services and public services and benefits 
• Law enforcement 
• Migration, asylum and border control management 
• Assistance in legal interpretation and application of the law. 

All high-risk AI systems will be assessed before being put on the market and also throughout their lifecycle. For more information, visit the European Parliament website. 

*source: https://www.europarl.europa.eu 

Expert Insight 

Ensuring security and confidentiality of data is certainly one of the most important issues concerning the implementation of AI solutions. Many experts indicate that despite the good intentions of the European Commission, the proposed solutions may contribute to reducing the competitiveness of the domestic AI market, which in effect will increase the distance between Europe and leaders in this field (i.e., the USA and China). I personally share these concerns. Here, a good example might be the similar situation that occurred about 15 years ago when cloud computing was being implemented. At that time, the EU also created a regulation governing the rules of access and data confidentiality (GDPR), which to this day is the regulatory basis in this area. At the same time, the largest solutions that most in the EU use are those developed in the USA, where the priority was the free development of technology, and only secondarily the legal framework. Unfortunately, many indications suggest that a similar situation might occur with AI. 

Fact 4: Gemini: new model from Google 

Without a doubt, the launch of Gemini was the most prominent premiere in the latter part of 2023, generating significant buzz. It is a result of large-scale collaborative efforts by teams across Google. It was built from the ground up to be multimodal, which means it can generalize and seamlessly understand, operate across, and combine different types of information including text, code, audio, image, and video. 

Gemini 1.0 was trained to recognize and understand text, images, audio, and more at the same time, so it better understands nuanced information and can answer questions relating to complicated topics. This makes it especially good at explaining reasoning in complex subjects like math and physics. 

During the presentation on the release of the Gemini API for developers, a lot of time was dedicated to AI Studio, a browser-based, free tool for code creation. The second focus was on Vertex AI, a more advanced program that allows for “both training and deploying ML (machine learning) models and AI applications.” Google offers the option to transfer a preliminary project developed in AI Studio to Vertex AI, to add additional features available within the larger platform of Google Cloud. 

Expert Insight 

Google has officially joined the large language model (LLM) race. The most intriguing aspect of what they propose is that their model will operate in three versions: Ultra (the most feature-rich), Pro, and Nano, with the latter being designed for mobile phones. It’s still unclear whether Nano will run entirely on client devices (smartphones) or if it will simply be a thin client and a kind of extension of Google Assistant. It’s also worth emphasizing that Google, like Microsoft, will offer Gemini services as elements of its flagship products, such as Google Sheets, Google Docs, and others. 

Fact 5: Advancements in Natural Language Processing (NLP) 

2023 witnessed remarkable progress in the field of Natural Language Processing. Researchers and companies globally made significant strides in improving the accuracy and versatility of NLP models. These advancements have led to more sophisticated understanding and the generation of human language by machines, paving the way for more intuitive and natural human-computer interactions. This year saw the deployment of advanced NLP in various applications, from customer service chatbots to complex data analysis tools, revolutionizing how we interact with technology daily. This progress in NLP technology not only enhanced existing applications but also opened new possibilities for AI in fields such as education, content creation, and multilingual communication. 

Expert Insight 

AI technologies are increasingly breaking the barrier of understanding natural language, gradually blurring the line between structured data previously used in IT systems and human knowledge. It seems that the creation of AGI (Artificial General Intelligence), a machine matching or even surpassing the average human in many aspects, is now just a matter of time. The challenge for the world of science, business, and politics will now be to direct the development of AI in a way that serves the broadly understood humanity and does not cause threats that many (probably rightly) fear. 

The last 12 months have been rich in interesting AI releases. The presentation of new large language models has opened up a range of possibilities for their implementation in everyday tasks, both in programming work and creative teams. European authorities are trying to keep up with these changes and adapt legal regulations to be in line with the current technological situation. In the coming months, we will certainly see more premieres, as leading players like Google and Microsoft compete to create solutions that utilize artificial intelligence. 

Artykuł A year under the sign of artificial intelligence development pochodzi z serwisu Inero Software - Software Consulting.

Experts predict that the market for software utilizing artificial intelligence (AI) to automate tasks and generate content in response to user commands will nearly quadruple by the year 2027. How can you benefit from this growth and prepare your team for new challenges and projects? CEO of Inero Software, Andrzej Chybicki, has shared his extensive experience and observations. In the following interview, he discusses how to manage remote teams in the IT services market and whether he foresees the advent of “teams of the future”.

Marta Kuprasz: I would like to ask you, as an experienced leader of a team of developers, how do you organize the work of distributed teams that are working on several projects? Additionally, I’m curious about your perspective on whether there’s a crisis in the IT services market and whether significant changes are on the horizon. To start from the beginning: For six years, you and Waldemar Korłub have been building Inero Software. During this time, you have refined processes related to managing a team of programmers. How do you approach the topic of implementing a new project and dividing tasks?

Andrzej Chybicki: The pandemic has changed the approach to remote work. What was previously rarely used has become fashionable and acceptable to both sides. Both employees and we – employers have noticed many advantages of this solution, such as lower labor costs, convenience, access to a larger pool of specialists, and time savings. There are also, of course, disadvantages. After a few years of such cooperation, we see that it is definitely more difficult to build interpersonal relationships when there is a lack of a common office, conversations, and meetings. The situation has made it possible for employees to lose the sense that they are part of a team, that they are building something together. We decided to create a process and culture, the combination of which helped us build a good framework for cooperation between the parties. We know that conversations are not only an exchange of information but also relationships, which is why we included regular project meetings in our work schedule. These are sometimes tedious but necessary processes of code quality verification, meetings monitoring progress, planning that takes into account the needs of our clients. During these meetings, we discuss what we expect from the team, while also collecting feedback from our programmers. I believe that a clear definition of responsibilities is more important than ongoing micromanagement. It is key that everyone knows how their actions affect the entire project. Awareness of these issues is extremely important.

“We decided to create a process and culture, the combination of which helped us build a good framework for cooperation between the parties. “

It’s also essential to set clear, realistic goals for a given project, which are delegated to individual teams or people. The team must be aware of how to implement a given idea and who is responsible for each area. Transparency in communication is, in my opinion, very important, especially among young people working remotely. Importantly, it should work both ways, i.e., we make our programmers aware that they also need to clearly communicate problems, delays, and errors, that occur in every project.

MK: What tools do you use for work planning and task assignment?

AC: In this, tools like Jira and GitLab help, but it must be remembered that they do not create the quality of services – that is our task. In long-term cooperation with a client, regularity and a developed action scheme are key. For several years now, methodologies such as Scrum and Agile have been widely used, which give technology teams the ability to work in a structured, yet appropriately flexible formula. They can define business needs and translate them into specific actions that are then implemented at the client’s site. However, I believe that entrusting project management to someone who only knows methodologies is a mistake. At Inero, we assume that managing a technology project is a skill, but knowledge of the domain to which the implementation pertains is also necessary. We know our weaknesses and strengths, so it is natural that we more often undertake projects in which we have the knowledge, in which we have access to industry experts because very often this purely theoretical knowledge is not enough. We focus on solutions whose applications we understand, such as logistics or the digital health industry.

“At Inero, we assume that managing a technology project is a skill, but knowledge of the domain to which the implementation pertains is also necessary.”

MK: So, how do you assemble a team of specialists in such a way that they complement each other at every stage of the project?

AC: Remember that a team consists of people with different skills, experiences, and processes they are already trained in. That’s why it’s so important to set clear, realistic goals for a given project, which are then transferred to individual team members. Everyone must be aware of how to implement a given idea and who is responsible for which area.

And probably most importantly: When we have a balanced team, meaning there are younger people who make mistakes, who may not always be able to handle all tasks, project management plays a crucial role. The team leader must catch these things and assign subsequent tasks that are still on the edge of possibility because they are an opportunity for further learning. However, it is essential not to have a tendency to find fault when something doesn’t work. We don’t forcibly look for problems. We should focus on the solution that will allow us to avoid a similar mistake next time. It is our role to motivate employees. By giving a challenging task, we want to get to know the new employee, his capabilities, and find out how he reacts to being confronted with a problem that may exceed his abilities. It’s better to understand his approach to problem-solving than to solve the problem itself. See if he communicates the difficulties he encounters and how he copes in a situation where he doesn’t know what to do.

“By giving a challenging task, we want to get to know the new employee, his capabilities, and find out how he reacts to being confronted with a problem that may exceed his abilities. “

I would like to add one more note here. There is something that can be called cognitive bias. Young programmers often want to prove themselves in projects, they are ambitious, they want to achieve success as quickly as possible. This is understandable. However, I sometimes see that they take on too many tasks and, as a result, find it hard to meet deadlines. We must take this into account when planning. In summary, when planning a team’s work, we must look at it as a whole, being aware that this is something that is supposed to function for a long time, without forgetting about the employees.

MK: Do you take employee turnover into account when planning a project?

AC: As a technology company, Inero provides value by offering structured and comprehensive software development services. When we establish a collaboration, we always think of it as a long-term relationship. In such a time frame, team turnover is natural, both on our side and on the client’s side. When we start a project, we assume that turnover will occur, so from the beginning, we strive to build a knowledge base for the project – a collection of experiences, facts, documents, multimedia, procedures, and information. We often use tools like GitLab (Wiki section) or Jira for this purpose. We record important data there, which will be necessary for a new team member to smoothly transition into the project.

“We have learned to automate repeatable procedures, and this applies to integrating new employees into the team.”

We have learned to automate repeatable procedures, and this applies to integrating new employees into the team, whether it’s front-end developers, back-end developers, cybersecurity matters, or others. For example, it includes a database of ready-made software solutions such as project templates or sample solutions. When integrating new team members, we assign them the task of analyzing and modifying these solutions in their first weeks of work. This is not so much to bring business value, but to teach them how we design solutions, how we solve specific technological problems, and how we approach problem analysis. We care about having an efficient way of transferring knowledge within the team. This translates into the quality and cost of our services.

MK: Recently, we have seen a growing interest in the topic of artificial intelligence. It influences many fields. Is this also visible in the industry in which Inero operates? Will “teams of the future” emerge soon?

AC: Undoubtedly, what has happened in the field of AI over the last 2-3 years, especially when OpenAI launched its new product, followed by Google’s Palm system and solutions available at HuggingFace, carries immense potential and can change the way new solutions are developed. We are closely monitoring how Copilot works. We use it in selected internal projects where we have no doubts related to SLA (Service Level Agreement), copyright, and code analysis.

” We are closely monitoring how Copilot works. We use it in selected internal projects where we have no doubts related to SLA, copyright, and code analysis.”

For sure, tasks related to the use of artificial intelligence already constitute a significant part of the projects carried out by our team – I would even say that currently, it’s more than half of all our work. The biggest challenge associated with AI is the ability to quickly adapt to changes and understand trends in this highly dynamic market. Those who adapt quickly will undoubtedly gain a lot, especially in areas supporting routine tasks, such as back-office operations, data analysis, predictive analysis, the use of conversational bots, and knowledge analysis (documents, contracts, emails, etc.). These are the areas of business activities that, in our opinion, have the greatest potential for transformation in the coming years. In the context of these projects, we see Inero not only as a team of developers but also as advisors. We try to identify trends, present conclusions, and communicate them to our clients and partners, indicating what deserves special attention in the coming months and years in the context of their business needs or development plans. We share our insights, which we believe will be applicable in a year, two, or five years.

MK: Have you noticed that there’s a crisis in the IT services market? How do you perceive what’s happening?

AC: For those who have recently become interested in software development, the situation where developers are not in high demand and don’t have a queue of orders may seem shocking. However, the years 2010-2015 were similar. Back then, the main advantage of programmers from our region was relatively low rates (compared to those in the USA or DACH countries). As a result of market changes post-COVID, the globalization of IT, and the convergence of salaries, the rates of our programmers are no longer as attractive to partners from the West. Therefore, we need to think differently about the value we want to deliver. For example, at Inero, we offer a product-service bundle where, on one hand, we provide services for our programmers, but on the other, we also offer ready-made logistics products that are part of a comprehensive IT offer. Additionally, we offer the entire process of creating IT solutions in the BOT model, not just our programmers on an hourly basis. In other words, the market is seeking balance after the turbulent years of 2021-2023 – it’s necessary to create new values and offer them.

Should you have any proposals or concepts you’d like to discuss, please feel free to reach out to me at your earliest convenience. I am very interested in exploring potential opportunities together.

Andrzej Chybicki, PhD Eng.
CEO, Inero Software Sp. z o. o.
andy@inero-software.com

Artykuł Andrzej Chybicki: The use of Artificial Intelligence already constitutes a significant part of the projects carried out by our team pochodzi z serwisu Inero Software - Software Consulting.