Equational

The latest generation of machine learning is of magical education value: They can "show you that something is possible". They are quick: New concepts can be explored in seconds. They are very powerful. Best to show by example. This post-Xmas 2022 week I am refreshening my natural language processing skills. Therefore I start my learning sessions with the following request: Can you tell me the little red riding hood story while including the phrase structure name and the most important phrase structure properties of each phrase structure of the story. https://chat.openai.com/chat responds with:  Sure! Here is the story of Little Red Riding Hood, with the phrase structure name and the most important phrase structure properties included for each phrase structure: Once upon a time, there was a little girl (noun phrase) who lived in a village (noun phrase) near the forest (noun phrase). She had a red hooded cloak (noun phrase), which she always wore (verb phrase, finite, past ten...

 This how I tend to look at management ownership in agile development ( see previous blog entry for more on the alternate views of agile ): Where: The CTO owns technology and most often engineering teams. The Engineering Manager may be an inwards looking CTO and also own technology and engineering teams, but is often less owning technology and more owning agile processes and engineering teams. The Product Owner owns the team's product vision and possibly the customer strategy. She/he is a member of the development team or has a representative that is part of the development team. The Technical Product Owner owns the customer view of technology, may be a full fledged product owner, or may be a support member of a larger product owner team. Individuals become more and more key enablers as your product and technology base become more advanced. A Servant Leader is then a manager (e.g. engineering manager) that helps individuals contribute in independence yet within orchestrated flows. ...

This is how I scale agile towards business and towards technology.: Where: In the center we have an agile process that blends team process and product process. To the right we have a business process that ties into the product process. To the left we have a technology process (expertise process to be general) that ties into the team process. To be honest, this is my minimal theoretical business to technology agile process. In practice, a specific agile process is chosen, with process steps and process artefacts. People like to say that agile is about people, not process. Yet people need to communicate, and the common vocabulary for that is given by a process. Deepening in to the product business view (right side above): Where: The core agile process (blue) delivers features and deliverables that are part of a product and business goals. These deliverables are picked-up by customers The features and deliverable sustain (or not) the customers competitivity within its market segment The p...

  My end of 2022 predictions for software development: Structure of code becomes more important than code Partial code becomes more valuable than finalized code Proprietary code gains in value Contextual programming gains in traction IDEs become ever more ML driven And therefore: Dynamic typing gains over static typing Duck-typing grows in value IDE security and spyware become an ever more important topic Functional programming is still the more powerful programming paradigm Proprietary IDE with in-house ML engines will grow in importance All original content copyright James Litsios, 2022. 

Some recommendations to improve your interactions with an ML based system, such as a ML chat like ChatGPT https://chat.openai.com/chat : Structure your requests Structure your requests in a way that is explicit and large in structure. This will help the ML algorithm "unroll" your request and provide a more structured and in-depth response. Avoid using too much implicit structure, as this may confuse the ML.  Rephrase your request with previous reply content  Rephrase your request using words and themes from the previous replies, as the ML may provide additional content to explain its inability to respond. By using these words and themes, you can bring your request into a form that the ML can provide response content for. Change the content order within your request Try changing the order of the structure of your requests, as the ML's approach to the response may be overly constrained by the input order.  Use analogies to structure your request Use analogies to struct...