Artificial intelligence. Freefall. Dzhimsher Chelidze

If retrospectives are not conducted regularly, teams are not sufficiently aware of their mistakes and omissions, which makes it difficult to progress towards achieving order and efficiency.

      In addition, conducting regular retrospectives helps teams move from a situation of uncertainty to complex or simple ordered systems. Starting with simple, streamlined systems where rules and processes are easily defined and controlled, teams can gradually move to more complex systems where rules are more ambiguous and require more adaptation.

      So, flashbacks are an important part of the Agile process and help teams move from uncertainty to order and complex systems. They allow teams to recognize their mistakes and shortcomings, as well as see areas for improvement. Do not neglect regular retrospectives so that your team can maximize the potential of Agile and achieve high performance.

      I wish you successful work in applying Agile and continuous improvement of your processes! Be flexible and persistent and considerate”.”

      Well, and my post: “Why is Agile not eternal and not a panacea?”

      “In recent years, everyone declares that they are Agile.

      Let’s be honest: most people hide banal chaos under this. After all, Agile is not about the lack of planning. In addition, he is very sensitive to the implementation of certain rules and to the stability of the team, its motivation. If you don’t meet these conditions, don’t use Agile in the future.

      And using the same Scrum, Kanban or other approaches should lead to the absence of the need to implement Agile projects.

      But why?

      Let’s remember that Agile was originally designed to work and implement projects in a highly uncertain environment.

      There is even a special tool – model Kenevin, that helps you understand what situation you are in and what approach you need to choose, what to focus on. So, in ordered systems (simple or complex situations), Agile, on the contrary, is contraindicated, because it reduces the cost of achieving results. That is, Agile is effective in cases where you need to do – I don’t know what”. But it’s not about efficiency.

      Now let’s take a look at the retrospective. All approaches within Agile involve regular retrospectives, analysis of their work, and interaction with the client / customer / partner. In other words, the very logic of these tools is to get away from an uncertain situation and learn how to predict them and become more effective.

      If you constantly (every six-months or a year) change jobs or constantly launch new products, and do not replicate certain solutions (which is strange for a business), then yes, you need to be Agile.

      But if you have a segment in the AC, and you have worked with experience and expertise on typical approaches / products that need to be adjusted and adapted in a small part, then sooner or later you must move away from Agile and come to an ordered system where cascading or hybrid approaches are needed. These retrospectives should lead you to understand what customers want in 90%of cases and how the organization works.

      As a result, if you are Agile on an ongoing basis and everywhere, and not for the period of rebuilding / launching / adapting, then this may indicate that:

      – you are not following the Agile tools;

      – you haven’t found your product or niche, and you haven’t developed the necessary expertise;

      – you always have a unique product / project (which should be reflected in the high price of your services);

      – the organization is “sick” from the inside, and this way you mask high turnover, lack of work on processes, etc.

      What do you think about it?”

      The quality of neural network responses is more like a weak student who just picks up similar words, but doesn’t understand what he’s talking about. Could I get a similar post from the neural network? So that she can convey my meaning? Yes, of course, but I wrote my post in 25 minutes, and how long would it take me to try to achieve such a result from AI? And does it look like a really thinking intelligence? And in general, on Intelligence?

      The fact is that our thinking is strongly tied to ideas and images. That is, basically in thinking we use an approach from the general to the particular, we think in images, and then from some vague, but understandable to us at the unconscious level of abstractions we come to the smallest details. In parallel, we conduct a bunch of associations, completely tied again to images. It is not for nothing that there are so many metaphors, comparisons, allusions and word changes in human speech.

      Modern neural networks “think” quite differently. They simply do not know the concepts of “meaning”, “essence”, “idea”, as well as the process of reflection itself. The texts generated by the neural network look logical not because the neural network really understands what it is writing about, but because it is able to calculate which words are most often next to each other in the texts available for its training on a given topic. Pure mathematics based on calculating probabilities.

      However, for the sake of justice, we should also note significant progress in this direction. Now developers are trying to teach AI to think: it asks itself questions and, giving answers, draws conclusions. This is an imitation of an internal dialog to improve the quality of content, which is typical for models from Open AI at the end of 2024 and Yandex GPT 4 Pro RC.

      Here is an example of the response of the Yandex GPT 4 Pro RC model to the request” Write a post about why Agile is infinitely applied incorrectly. Emphasize that conducting retrospectives should lead away from the situation of uncertainty to the situation of complex ordered or simple ordered systems.”

      Yandex GPT 4 Pro RC Response: “Why Agile doesn’t Always Work: how retrospectives can help move from uncertainty to order.

      Agile is a flexible approach to project management that allows you to quickly adapt to changes and improve processes based on feedback. However, despite all the advantages, applying Agile without considering the context can lead to problems. In this post, we will look at why Agile should not be applied indefinitely and how retrospectives help to move from a situation of uncertainty to ordered systems.

      Problems of infinite Agile Application

      1. Lack of clear structure. Agile is based on the principles of flexibility and adaptability, which can lead to a lack of a clear structure and action plan. This can make it difficult to make decisions and manage risks.

      2. Complexity of evaluating results. Without a clear plan and criteria for evaluating results, it is difficult to determine how well the project is progressing. This may raise doubts about the effectiveness of the approach.

      3. Risk of losing control. The endless use of Agile can lead to a loss of control over the project. Without clear boundaries and constraints, the team may lose focus and start to deviate from the original goal.

      4. Inefficient use of resources. If the team is constantly adapting to new conditions, this can lead to inefficient use of resources. Instead of focusing on key tasks, the team will spend time making constant changes.

      5. Reduced team motivation. Constant adaptation and changes can cause stress and fatigue for the team. This can reduce motivation and productivity.

      How retrospectives help you move to streamlined systems

      Retrospectives are one of the key Agile tools that help the team analyze their work and identify areas for improvement. They allow us to move from a situation of uncertainty to more ordered systems, where processes and decisions become more predictable and manageable.

      Here are some ways that flashbacks can help:

      – Identifying problems and their solutions. Retrospectives allow you to identify problems that have arisen in the course of work, and find ways to solve them. This helps you avoid making mistakes again in the future.

      – Improve