![[The AI Show Episode 143]: ChatGPT Revenue Surge, New AGI Timelines, Amazon’s AI Agent, Claude for Education, Model Context Protocol & LLMs Pass the Turing Test](https://www.marketingaiinstitute.com/hubfs/ep%20143%20cover.png)
![From drop-out to software architect with Jason Lengstorf [Podcast #167]](https://cdn.hashnode.com/res/hashnode/image/upload/v1743796461357/f3d19cd7-e6f5-4d7c-8bfc-eb974bc8da68.png?#)
.jpg?#)
_ArtemisDiana_Alamy.jpg?#)
 (1).webp?#)
![Yes, the Gemini icon is now bigger and brighter on Android [U]](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2025/02/Gemini-on-Galaxy-S25.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![Apple Vision Pro 2 Allegedly in Production Ahead of 2025 Launch [Rumor]](https://www.iclarified.com/images/news/96965/96965/96965-640.jpg)
![New iOS 19 Leak Allegedly Reveals Updated Icons, Floating Tab Bar, More [Video]](https://www.iclarified.com/images/news/96958/96958/96958-640.jpg)
How do I use ChatGPT as a developer? Top 10 + 1 best usages.
In terms of computer software engineering, code AI or the so-called copilot coding apps (or what I like to call code companion Gen AI) are becoming more and more useful for everyone that wants to become a developer or improve their current programming skills. The problem with that is that if you do not get what Generative AI with an LLM does in terms of coding, you will end up hating it and with that the unwanted frustration and bad code produced. An overly-simplified description of how an LLM works is shown below: The main Generative part of the LLM gets fed with info from user input in the form of a generic or specific question/sentence. In that sentence the words are tokenized, means that are split and mapped to a linear 1D data structure (array, list). The text is then mapped to the corresponding values of words by order of which those have been tokenized (eg: 1,2,3..etc) so these are fed to the Pre-Trained A.I. models and then the textual A.I. language model will try to Transform input words to the statistical analogous using statistic series classification in the form of a set of numeric values (AI model weights). These values indicate and inform the Gen AI process of the used words importance (per LLM subject or category) so that it is able to respond with the closest answer to the naturally-set question. This process also gives the name of the most well known LLM used aka GPT (or Generative Pre-Trained Transformer) that most people use for nearly every purpose. In my opinion, this entire process is closely similar in how Google's site-ranking algorithm works to rank -and- add the top 10 most relevant sites per user's search prompt. Most basic thing that differs is the real-time data updates and interaction from Google instead of ChatGPT's pre-defined data. Replacing a Google search query with ChatGPT, that would be the equivalent to having 20 Chrome tabs open while googling on the web and writing up notes based on your top 3-4 most helpful sites that are closest to your subject. The complete set of notes written will be much more similar to a response from ChatGPT. Try it yourself. Many equivalent versions of text and subjects generation are available online. A fun example will also be this recreational site and this also. What this means in terms of using ChatGPT for general questions is that the phrasing of the sentence must be correct, the concept is added as a top priority in your phrase or sentence and also in some cases punctuation marks indicating pauses in a sentence or continuation from a previous sentence if not used correctly might produce different results of the ones expected. What this means, when you use ChatGPT for coding or when generating or adding code as a software developer, is that to produce the most appropriate result both you as a user and the text prompt must share the same amount of information so that the appropriate result is produced. This can easily be done in the form of a 'paired programming' session by noticing each others bugs and underlying code. In order to achieve this, you need to have a coding infrastructure with standards pre-set, all classes compiling and running properly with/without any UI parts and some sample code to start with to use as input for your questions. Using this method can achieve the necessary enhancements to your current coding style and infrastructure and minimize BOTH errors and debugging time, when lacking time, help or coding peers. This is without mentioning the time saved to trial-and-error new versions and checks on configuration files or missing SDKs and packages in your code. As an added bonus to this, here is a listing of the top 10 + 1 best possible use cases of ChatGPT for improving software developer work ChatGPT top 10 +1 uses for a software developer: #1. Generate a nice creative 404 static web page for the blocked responses of your web based solution. Easiest thing to be done even if you lack creativity but are good with words and story-making. #2. Write a framework or an API of a programming language while also applying fast-paced learning on the programming platform you already work on. This can be used as a learning tool for both senior and junior levels. #3. Text transcription as a software language or translating from one software development language to another. This can be used if a missing library in python needs to be in-place to handle similar code to your current code base that only supports JS packages. This also applies to IT administrators just in case they need to update some older automation scripts on Windows/Linux environment to PowerShell or Python for cross-compatibility or vice-versa. Some combinations of this (fromto) are shown below: Batch or Bash To PowerShell Batch Python PowerShell Bash or Python This can be easily done but I would not rely on it too much for large and complicated IT infras
In terms of computer software engineering, code AI or the so-called copilot coding apps (or what I like to call code companion Gen AI) are becoming more and more useful for everyone that wants to become a developer or improve their current programming skills.
The problem with that is that if you do not get what Generative AI with an LLM does in terms of coding, you will end up hating it and with that the unwanted frustration and bad code produced.
An overly-simplified description of how an LLM works is shown below:
- The main Generative part of the LLM gets fed with info from user input in the form of a generic or specific question/sentence. In that sentence the words are tokenized, means that are split and mapped to a linear 1D data structure (array, list).
- The text is then mapped to the corresponding values of words by order of which those have been tokenized (eg: 1,2,3..etc) so these are fed to the Pre-Trained A.I. models and then the textual A.I. language model will try to Transform input words to the statistical analogous using statistic series classification in the form of a set of numeric values (AI model weights).
- These values indicate and inform the Gen AI process of the used words importance (per LLM subject or category) so that it is able to respond with the closest answer to the naturally-set question.
This process also gives the name of the most well known LLM used aka GPT (or Generative Pre-Trained Transformer) that most people use for nearly every purpose.
In my opinion, this entire process is closely similar in how Google's site-ranking algorithm works to rank -and- add the top 10 most relevant sites per user's search prompt.
Most basic thing that differs is the real-time data updates and interaction from Google instead of ChatGPT's pre-defined data.
Replacing a Google search query with ChatGPT, that would be the equivalent to having 20 Chrome tabs open while googling on the web and writing up notes based on your top 3-4 most helpful sites that are closest to your subject.
The complete set of notes written will be much more similar to a response from ChatGPT.
Try it yourself. Many equivalent versions of text and subjects generation are available online. A fun example will also be this recreational site and this also.
What this means in terms of using ChatGPT for general questions is that the phrasing of the sentence must be correct, the concept is added as a top priority in your phrase or sentence and also in some cases punctuation marks indicating pauses in a sentence or continuation from a previous sentence if not used correctly might produce different results of the ones expected.
What this means, when you use ChatGPT for coding or when generating or adding code as a software developer, is that to produce the most appropriate result both you as a user and the text prompt must share the same amount of information so that the appropriate result is produced.
This can easily be done in the form of a 'paired programming' session by noticing each others bugs and underlying code.
In order to achieve this, you need to have a coding infrastructure with standards pre-set, all classes compiling and running properly with/without any UI parts and some sample code to start with to use as input for your questions.
Using this method can achieve the necessary enhancements to your current coding style and infrastructure and minimize BOTH errors and debugging time, when lacking time, help or coding peers. This is without mentioning the time saved to trial-and-error new versions and checks on configuration files or missing SDKs and packages in your code.
As an added bonus to this, here is a listing of the top 10 + 1 best possible use cases of ChatGPT for improving software developer work
ChatGPT top 10 +1 uses for a software developer:
#1.
Generate a nice creative 404 static web page for the blocked responses of your web based solution. Easiest thing to be done even if you lack creativity but are good with words and story-making.
#2.
Write a framework or an API of a programming language while also applying fast-paced learning on the programming platform you already work on. This can be used as a learning tool for both senior and junior levels.
#3.
Text transcription as a software language or translating from one software development language to another. This can be used if a missing library in python needs to be in-place to handle similar code to your current code base that only supports JS packages. This also applies to IT administrators just in case they need to update some older automation scripts on Windows/Linux environment to PowerShell or Python for cross-compatibility or vice-versa. Some combinations of this (from<-->to) are shown below:
Batch or Bash <--> To PowerShell
Batch <--> Python
PowerShell <--> Bash or Python
This can be easily done but I would not rely on it too much for large and complicated IT infrastructures.
#4.
Use it as a data generator Tool (Json struct, Table struct). Some alternatives are to use POCO class generators built-in to Visual Studio or other Visual Studio extensions that first need to be downloaded/configured accordingly. Sample usage in ChatGPT shown below.
Chat prompt:
Provided the description of a table of a pet dog below, response with the corresponding layout as a JSON object, a Csharp class and as an SQL create table statement. Note: Add the most appropriate data types per column definition so those can be used in a codebase or IDE.
Pet Dog Table Columns:
ID
Name
Breed
Age
LastVetVisit
HasIdentificationTag
DangerousBreed
Chat response:
Here’s the requested information in JSON, C# class, and SQL format:
JSON Layout:
{
"PetDog": {
"ID": 1,
"Name": "Buddy",
"Breed": "Golden Retriever",
"Age": 3,
"LastVetVisit": "2024-06-15T00:00:00Z",
"HasIdentificationTag": true,
"DangerousBreed": false
}
}
using System;
public class PetDog
{
public int ID { get; set; }
public string Name { get; set; }
public string Breed { get; set; }
public int Age { get; set; }
public DateTime LastVetVisit { get; set; }
public bool HasIdentificationTag { get; set; }
public bool DangerousBreed { get; set; }
}
CREATE TABLE PetDog (
ID INT PRIMARY KEY AUTO_INCREMENT,
Name VARCHAR(100) NOT NULL,
Breed VARCHAR(100) NOT NULL,
Age INT NOT NULL CHECK (Age >= 0),
LastVetVisit DATETIME NOT NULL,
HasIdentificationTag BOOLEAN NOT NULL,
DangerousBreed BOOLEAN NOT NULL
);
This structure ensures proper data integrity and usability in a codebase or IDE. Let me know if you need modifications!
