Difference between revisions of "Development"
m |
m (Text replacement - "http:" to "https:") |
||
| Line 5: | Line 5: | ||
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
}} | }} | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Software+Develop+ai+deep+learning Youtube] |
[https://www.quora.com/search?q=Software%20Develop%20ai%20ai%20bdeep%20learning ... Quora] | [https://www.quora.com/search?q=Software%20Develop%20ai%20ai%20bdeep%20learning ... Quora] | ||
| − | [ | + | [https://www.google.com/search?q=Software+Develop+ai+deep+learning ...Google search] |
[https://news.google.com/search?q=Software+Develop+ai+deep+learning ...Google News] | [https://news.google.com/search?q=Software+Develop+ai+deep+learning ...Google News] | ||
[https://www.bing.com/news/search?q=Software+Develop+ai+deep+learning&qft=interval%3d%228%22 ...Bing News] | [https://www.bing.com/news/search?q=Software+Develop+ai+deep+learning&qft=interval%3d%228%22 ...Bing News] | ||
| Line 34: | Line 34: | ||
* [[Service Capabilities]] | * [[Service Capabilities]] | ||
* [[AI Marketplace & Toolkit/Model Interoperability]] | * [[AI Marketplace & Toolkit/Model Interoperability]] | ||
| − | * [ | + | * [https://transmogrif.ai/ TransmogrifAI - workflows on Spark | Salesforce] ... [https://github.com/salesforce/TransmogrifAI GitHub] |
| − | * [ | + | * [https://oracle.github.io/graphpipe/#/ Graphpipe | Oracle] |
* [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)]] | * [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)]] | ||
* [[Journey to Singularity]] | * [[Journey to Singularity]] | ||
| Line 46: | Line 46: | ||
* [[Differentiable Programming]] | * [[Differentiable Programming]] | ||
* [[Git - GitHub and GitLab]] | * [[Git - GitHub and GitLab]] | ||
| − | * [ | + | * [https://kite.com/ Kite] works with the top Python editors; Atom, PyCharm, Sublime, VS Code and Vim |
| − | * [ | + | * [https://towardsdatascience.com/machine-learning-vs-traditional-programming-c066e39b5b17 Machine Learning vs Traditional Programming | Oleksii Kharkovyna - Towards Data Science - Medium] |
| − | * [ | + | * [https://qcon.ai/qconai2019/track/solving-software-engineering-problems-machine-learning Track: Solving Software Engineering Problems with Machine Learning | Cyril Magnin III - QCon.ai] |
* [[Algorithm Administration#Automated Learning|Automated Learning]] | * [[Algorithm Administration#Automated Learning|Automated Learning]] | ||
* [[Explainable / Interpretable AI]] | * [[Explainable / Interpretable AI]] | ||
| − | * [ | + | * [https://devblogs.microsoft.com/visualstudio/ai-assisted-developer-tools/ Re-imagining developer productivity with AI-assisted tools | Amanda Silver - Microsoft] ...AI-assisted IntelliSense GPT-2 transformer |
| − | * [ | + | * [https://modeling-languages.com/smart-modeling-tools-ai-software/ Smart modeling tools – AI to help you model better | Jordi Cabot - Modeling Languages] |
| − | * [ | + | * [https://medium.com/data-ops/a-great-model-is-not-enough-deploying-ai-without-technical-debt-70e3d5fecfd3 A Great Model is Not Enough: Deploying AI Without Technical Debt | DataKitchen - Medium] |
| − | * [ | + | * [https://ml4code.github.io/papers.html Machine Learning for Big Code and Naturalness | ML4code] ...Research on machine learning for source code. |
| − | * [ | + | * [https://www.metamaven.com/6-ways-machine-learning-transforms-software-development/ 6 Ways AI Transforms Software Development | Mariya Yao - MetaMaven] |
| − | * [ | + | * [https://modeling-languages.com/towards-a-dsl-for-ai-engineering-process-modeling/ Towards a DSL for AI Engineering Process Modeling | Sergio Morales - MOdeling LAnguages] |
| Line 70: | Line 70: | ||
# Developing a machine learning application is more iterative and explorative process than traditional software engineering. Learning / Testing / Validation of models is an upfront task | # Developing a machine learning application is more iterative and explorative process than traditional software engineering. Learning / Testing / Validation of models is an upfront task | ||
| − | <img src=" | + | <img src="https://miro.medium.com/max/1348/1*FBRBPCmTEM6MDvZ6VeYFAw.png" width="800" height="500"> |
| − | Developing a machine learning application is even more iterative and explorative process than software engineering. Machine learning is applied on problems that are too complicated for humans to figure out (that is why we ask a computer to find a solution for us!). [ | + | Developing a machine learning application is even more iterative and explorative process than software engineering. Machine learning is applied on problems that are too complicated for humans to figure out (that is why we ask a computer to find a solution for us!). [https://www.futurice.com/blog/differences-between-machine-learning-and-software-engineering/ Differences between machine learning and software engineering | Antti Ajanki - Futurice] |
| Line 87: | Line 87: | ||
== <span id="AI Pair Programming Tools"></span>AI Pair Programming Tools == | == <span id="AI Pair Programming Tools"></span>AI Pair Programming Tools == | ||
| − | * [ | + | * [https://aidan-tilgner.medium.com/github-copilot-vs-openai-codex-which-should-you-use-ed67e53e00c0#:~:text=OpenAI%20Codex%20and%20GitHub%20Copilot%20are%20both%20models%20trained%20on,via%20their%20API%2C%20or%20Playground. GitHub Copilot vs OpenAI Codex. Which should you use? | Aiden Tilgner - Medium] |
| − | * [ | + | * [https://www.kdnuggets.com/2021/07/github-copilot-open-source-alternatives-code-generation.html GitHub Copilot Open Source Alternatives | Matthew Mayo -KDnuggets] |
| − | Today, AI-powered software development tools are allowing people to build software solutions using the same language that they use when they talk to other people. These AI-powered tools translate natural language into the programming languages that computers understand. [ | + | Today, AI-powered software development tools are allowing people to build software solutions using the same language that they use when they talk to other people. These AI-powered tools translate natural language into the programming languages that computers understand. [https://blogs.microsoft.com/ai/how-ai-makes-developers-lives-easier-and-helps-everybody-learn-to-develop-software/ How AI makes developers’ lives easier, and helps everybody learn to develop software | John Roach - Microsoft] |
=== [[ChatGPT]] | [[OpenAI]] for Development === | === [[ChatGPT]] | [[OpenAI]] for Development === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=OpenAI+ChatGPT+develop+program+python Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=OpenAI+ChatGPT+develop+program+python ...Google search] |
* [[ChatGPT]] | [[OpenAI]] | * [[ChatGPT]] | [[OpenAI]] | ||
| Line 128: | Line 128: | ||
=== Codex | [[OpenAI]] === | === Codex | [[OpenAI]] === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=OpenAI+Codex+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=OpenAI+Codex+machine+learning+artificial+intelligence ...Google search] |
| − | * [ | + | * [https://openai.com/blog/openai-codex/ OpenAI Codex] |
| − | * [ | + | * [https://beta.openai.com/playground Playground] |
| − | * [ | + | * [https://openai.com/api/ OpenAI's API] |
| − | * [ | + | * [https://arxiv.org/abs/2107.03374 Evaluating Large Language Models Trained on Code | Mark Chen et al.] |
Codex, a [[Generative_Pre-trained_Transformer_(GPT)]] language model fine-tuned on publicly available code from [[Microsoft]]'s [[Git - GitHub and GitLab|GitHub]]. Codex requires that you access it via their API, or Playground. Create your own fine-tuned [[OpenAI]] model by feeding it training data from files; then would be able to generate much more accurate and detailed responses; understanding the context of a file and generate very accurate, but specific code completion based on the file. Codex powers [[Microsoft]]'s GitHub Copilot. | Codex, a [[Generative_Pre-trained_Transformer_(GPT)]] language model fine-tuned on publicly available code from [[Microsoft]]'s [[Git - GitHub and GitLab|GitHub]]. Codex requires that you access it via their API, or Playground. Create your own fine-tuned [[OpenAI]] model by feeding it training data from files; then would be able to generate much more accurate and detailed responses; understanding the context of a file and generate very accurate, but specific code completion based on the file. Codex powers [[Microsoft]]'s GitHub Copilot. | ||
| Line 146: | Line 146: | ||
=== <span id="Microsoft Copilot"></span>Microsoft Copilot === | === <span id="Microsoft Copilot"></span>Microsoft Copilot === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=GitHub+Copilot+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=GitHub+Copilot+machine+learning+artificial+intelligence ...Google search] |
* [[Microsoft]] | * [[Microsoft]] | ||
==== Visual Studio Code ==== | ==== Visual Studio Code ==== | ||
| − | * [ | + | * [https://copilot.github.com/ GitHub Copilot |] [[Microsoft]] |
| − | * [ | + | * [https://github.com/github/copilot-docs/tree/main/docs#getting-started Getting Started |] [[Microsoft]] |
| − | * [ | + | * [https://medium.com/@rishirebel/all-about-github-copilot-a7121122eef4 All About Github Copilot | Rishikesh Chandra - Medium] |
| − | * [ | + | * [https://www.geeksforgeeks.org/how-to-install-github-copilot-on-vscode/?ref=rp How to Install GitHub Copilot on VSCode? | GeeksforGeeks] |
| − | * [ | + | * [https://davegebler.com/post/php/i-tried-github-copilot-and-it-s-the-best-thing-ever I Tried GitHub Copilot and it's the Best Thing Ever | Dave Gebler] |
Copilot writes code alongside you in your text editor. The extensions for Copilot are available for Noevim, JetBrains, Visual Studio Code, and in the cloud on [[Git - GitHub and GitLab|GitHub Codespaces]]. GitHub Copilot is really only usable in Visual Studio Code, [[Microsoft]]’s IDE, or [[Git - GitHub and GitLab|GitHub]] Codespaces if you’re into the whole Cloud IDE. Model trained on the GPT-3 language prediction model created by OpenAI. | Copilot writes code alongside you in your text editor. The extensions for Copilot are available for Noevim, JetBrains, Visual Studio Code, and in the cloud on [[Git - GitHub and GitLab|GitHub Codespaces]]. GitHub Copilot is really only usable in Visual Studio Code, [[Microsoft]]’s IDE, or [[Git - GitHub and GitLab|GitHub]] Codespaces if you’re into the whole Cloud IDE. Model trained on the GPT-3 language prediction model created by OpenAI. | ||
| Line 172: | Line 172: | ||
=== CodeWhisperer | [[Amazon]] === | === CodeWhisperer | [[Amazon]] === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=CodeWhisperer+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=CodeWhisperer+machine+learning+artificial+intelligence ...Google search] |
| − | * [ | + | * [https://aws.amazon.com/visualstudiocode/ AWS Toolkit for Visual Studio Code |] [[Amazon]] |
| − | * [ | + | * [https://techcrunch.com/2022/06/23/amazon-launches-codewhisperer-its-ai-pair-programming-tool/?guccounter=1 Amazon launches CodeWhisperer], a GitHub Copilot-like AI pair programming tool | Frederic Lardinois - TechCrunch |
[[Amazon]] CodeWhisperer, a machine learning (ML)–powered service that helps improve developer productivity by generating code recommendations based on developers’ comments in natural language and their code in the IDE. It’s now available in preview as part of the AWS IDE Toolkit, which means developers can immediately use it right inside their preferred IDEs, including Visual Studio Code, IntelliJ IDEA, PyCharm, WebStorm and [[Amazon]]’s own AWS Cloud 9. Support for the AWS Lambda Console is also coming soon. Tool can autocomplete entire functions based on only a comment or a few keystrokes. [[Amazon]] trained the system, which currently supports Java, [[Javascript]] and [[Python]], on billions of lines of publicly available open source code and its own codebase, as well as publicly available documentation and code on public forums. | [[Amazon]] CodeWhisperer, a machine learning (ML)–powered service that helps improve developer productivity by generating code recommendations based on developers’ comments in natural language and their code in the IDE. It’s now available in preview as part of the AWS IDE Toolkit, which means developers can immediately use it right inside their preferred IDEs, including Visual Studio Code, IntelliJ IDEA, PyCharm, WebStorm and [[Amazon]]’s own AWS Cloud 9. Support for the AWS Lambda Console is also coming soon. Tool can autocomplete entire functions based on only a comment or a few keystrokes. [[Amazon]] trained the system, which currently supports Java, [[Javascript]] and [[Python]], on billions of lines of publicly available open source code and its own codebase, as well as publicly available documentation and code on public forums. | ||
| Line 184: | Line 184: | ||
=== Captain Stack === | === Captain Stack === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Captain+Stack+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=Captain+Stack+machine+learning+artificial+intelligence ...Google search] |
| − | * [ | + | * [https://github.com/hieunc229/copilot-clone Captain Stack] ...Code suggestion for VSCode |
This feature is somewhat similar to [[Git - GitHub and GitLab|GitHub]] Copilot's code suggestion. But instead of using AI, it sends your search query to Google, then retrieves StackOverflow answers and autocompletes them for you. | This feature is somewhat similar to [[Git - GitHub and GitLab|GitHub]] Copilot's code suggestion. But instead of using AI, it sends your search query to Google, then retrieves StackOverflow answers and autocompletes them for you. | ||
| Line 196: | Line 196: | ||
=== GPT-Code-Clippy (GPT-CC) === | === GPT-Code-Clippy (GPT-CC) === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=GPT-Code-Clippy+GPT-CC+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=GPT-Code-Clippy+GPT-CC+machine+learning+artificial+intelligence ...Google search] |
| − | * [ | + | * [https://github.com/CodedotAl/gpt-code-clippy GPT-Code-Clippy (GPT-CC)] |
an open source version of [[Git - GitHub and GitLab|GitHub]] Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from [[Git - GitHub and GitLab|GitHub]]. | an open source version of [[Git - GitHub and GitLab|GitHub]] Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from [[Git - GitHub and GitLab|GitHub]]. | ||
=== Second Mate === | === Second Mate === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Second+Mate+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=Second+Mate+machine+learning+artificial+intelligence ...Google search] |
| − | * [ | + | * [https://github.com/samrawal/emacs-secondmate Second Mate] |
An open-source, mini imitation of [[Git - GitHub and GitLab|GitHub]] Copilot using EleutherAI GPT-Neo-2.7B (via Huggingface Model Hub) for Emacs. | An open-source, mini imitation of [[Git - GitHub and GitLab|GitHub]] Copilot using EleutherAI GPT-Neo-2.7B (via Huggingface Model Hub) for Emacs. | ||
=== Clara-Copilot VSCode === | === Clara-Copilot VSCode === | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Clara-Copilot+VSCode+machine+learning+artificial+intelligence Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=Clara-Copilot+VSCode+machine+learning+artificial+intelligence ...Google search] |
| − | * [ | + | * [https://github.com/badboysm890/clara-copilot Clara-Copilot Code] |
This feature is somewhat similar to [[Git - GitHub and GitLab|GitHub]] Copilot's code suggestion. But instead of using AI, it sends your search query to Google, then retrieves StackOverflow answers and autocompletes them for you. | This feature is somewhat similar to [[Git - GitHub and GitLab|GitHub]] Copilot's code suggestion. But instead of using AI, it sends your search query to Google, then retrieves StackOverflow answers and autocompletes them for you. | ||
== Life Cycle == | == Life Cycle == | ||
| − | [ | + | [https://www.youtube.com/results?search_query=SDLC+machine+learning+artificial+intelligence+Software+Development+Life+Cycle Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=SDLC+machine+learning+artificial+intelligence+Software+Development+Life+Cycle ...Google search] |
* [[AIOps / MLOps]] | * [[AIOps / MLOps]] | ||
| − | * [ | + | * [https://www.devteam.space/blog/ai-development-life-cycle-explained/ AI Development life cycle: Explained | Aran Davies - DevTeam.Space] |
| − | * [ | + | * [https://www.kdnuggets.com/2017/10/data-science-systems-engineering-approach.html Data Science –The need for a Systems Engineering approach | Ajit Jaokar - KDnuggets] |
| − | * [ | + | * [https://www.guru99.com/software-development-life-cycle-tutorial.html SDLC (Software Development Life Cycle) Tutorial: What is, Phases, Model | Guru99] |
| − | * [ | + | * [https://www.jeremyjordan.me/ml-projects-guide/ Organizing machine learning projects: project management guidelines | Jeremy Jordan] |
| − | * [ | + | * [https://medium.com/luminovo/the-deep-learning-toolset-an-overview-b71756016c06 The Deep Learning Toolset — An Overview | Timon Ruban - luminovo.ai - Medium] |
| − | * [ | + | * [https://www.slideshare.net/WillyDevNET/how-ai-will-change-software-development-and-applications How AI Will Change Software Development And Applications | Diego Lo Giudice - Forrester] |
| − | * [ | + | * [https://dzone.com/articles/artificial-intelligence-in-testing-tools-and-advan Artificial Intelligence in Testing: Tools and Advantages | Mitul Makadia - DZone] |
| − | <img src=" | + | <img src="https://www.aisoma.de/wp-content/uploads/2019/03/ML_Workflow-1024x717.jpg" width="600"> |
<youtube>Ofvt4-gr8m0</youtube> | <youtube>Ofvt4-gr8m0</youtube> | ||
| Line 243: | Line 243: | ||
== Agile == | == Agile == | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Agile+machine+learning Youtube search...] |
| − | [ | + | [https://www.google.com/search?q=Agile+machine+learning ...Google search] |
| − | * [ | + | * [https://hackernoon.com/ai-based-framework-for-agile-project-management-jc1xi3xwh AI-Based Framework for Agile Project Management | Sandeep Aspari - Hackernoon] |
| − | * [ | + | * [https://analyticsindiamag.com/effective-ai-agile-project-management/ How To Achieve Effective AI-Powered Agile Project Management | Martin F.R - Analytics India] |
| − | * [ | + | * [https://content.intland.com/blog/using-artificial-intelligence-to-boost-agile/devops-efficiency?hs_amp=true Using Artificial Intelligence to Boost Agile/DevOps Efficiency | Kristof Horvath] |
| − | * [ | + | * [https://readwrite.com/2019/05/08/ai-based-framework-for-agile-project-management/amp/ AI-Based Framework for Agile Project Management | Stephanie Donahole - ReadWrite] |
| − | * [ | + | * [https://www.infoq.com/news/2019/04/monte-carlo-agile-estimation Web-Based Monte Carlo Simulation for Agile Estimation] |
| − | * [ | + | * [https://www.lean.org/LeanPost/Posting.cfm?LeanPostId=856 Lean Management Meets Artificial intelligence, Machine Learning, the Internet of All Things | Andrew Quibell - The Lean Post] |
| − | * [ | + | * [https://www.tastycupcakes.org/ TastyCupcakes.org] ... Fuel for Invention and Learning |
| − | * [ | + | * [https://www.innovationgames.com Innovation Games] ... Creating Breakthrough Products Through Collaborative Play |
| − | * [ | + | * [https://www.excella.com/ Excella] ... Solve for today, evolve for tomorrow. |
| − | * [ | + | * [https://www.adventureswithagile.com/ Adventures with Agile] ... a professional community of practice |
| − | AI has changed software development by exposing human perception, definition, and execution of programming. ...Future programmers won’t maintain complex repositories, analyze running times or create intricate programs. They’ll collect, sanitize, label, analyze, and visualize data feeding neural networks. [ | + | AI has changed software development by exposing human perception, definition, and execution of programming. ...Future programmers won’t maintain complex repositories, analyze running times or create intricate programs. They’ll collect, sanitize, label, analyze, and visualize data feeding neural networks. [https://dzone.com/articles/9-ways-to-implement-artificial-intelligence-and-ag 9 Ways To Implement Artificial Intelligence and Agile-Powered Management in Software Development | Chandresh Patel - DZone] |
...Introduce machine Learning (ML) techniques into your Software Development Life Cycle (SLDC) as follows: | ...Introduce machine Learning (ML) techniques into your Software Development Life Cycle (SLDC) as follows: | ||
| − | 1. <b>Coding [[Assistants]]: </b> Most of a developer’s time is spent debugging code and reading the documentation. With smart coding [[Assistants|assistant]] implemented using ML, developers can get quick feedback and recommendations based on the codebase, saving a lot of time. Great examples include [ | + | 1. <b>Coding [[Assistants]]: </b> Most of a developer’s time is spent debugging code and reading the documentation. With smart coding [[Assistants|assistant]] implemented using ML, developers can get quick feedback and recommendations based on the codebase, saving a lot of time. Great examples include [https://www.codota.com/ Java’s Codota] and [https://kite.com/ Python’s Kite]. |
2. <b>Automatic Coding Refactoring: </b> It is important to have clean code because it makes collaboration a lot easier. Maintenance of clean code is also orders of magnitude easier than unclean code. Here's the deal; whenever an organization scales, refactoring becomes a painful necessity. With ML, it is easy to analyze code and optimize for performance by identifying potential areas for refactoring. | 2. <b>Automatic Coding Refactoring: </b> It is important to have clean code because it makes collaboration a lot easier. Maintenance of clean code is also orders of magnitude easier than unclean code. Here's the deal; whenever an organization scales, refactoring becomes a painful necessity. With ML, it is easy to analyze code and optimize for performance by identifying potential areas for refactoring. | ||
Revision as of 09:30, 28 March 2023
Youtube ... Quora ...Google search ...Google News ...Bing News
- Case Studies
- Development ...AI Pair Programming Tools ... Analytics ... Visualization ... Diagrams for Business Analysis
- AIOps/MLOps
- Python ... Generative AI with Python ... Javascript ... Generative AI with Javascript ... Game Development with Generative AI
- Assistants ... Hybrid Assistants ... Agents ... Negotiation ... LangChain
- Prompt Engineering (PE) ...PromptBase ... Prompt Injection Attack
- Generative AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's BingAI ... You ...Google's Bard ... Baidu's Ernie
- Natural Language Processing (NLP) ...Generation ...LLM ...Tools & Services
- Attention Mechanism ...Transformer Model ...Generative Pre-trained Transformer (GPT)
- AI Governance
- Graphical Tools for Modeling AI Components
- Google Natural Language
- World Models
- Service Capabilities
- AI Marketplace & Toolkit/Model Interoperability
- TransmogrifAI - workflows on Spark | Salesforce ... GitHub
- Graphpipe | Oracle
- Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)
- Journey to Singularity
- Digital Twin
- Inside Out - Curious Optimistic Reasoning
- Evolutionary Computation / Genetic Algorithms
- Apprenticeship Learning - Inverse Reinforcement Learning (IRL)
- Imitation Learning
- Simulated Environment Learning
- Differentiable Programming
- Git - GitHub and GitLab
- Kite works with the top Python editors; Atom, PyCharm, Sublime, VS Code and Vim
- Machine Learning vs Traditional Programming | Oleksii Kharkovyna - Towards Data Science - Medium
- Track: Solving Software Engineering Problems with Machine Learning | Cyril Magnin III - QCon.ai
- Automated Learning
- Explainable / Interpretable AI
- Re-imagining developer productivity with AI-assisted tools | Amanda Silver - Microsoft ...AI-assisted IntelliSense GPT-2 transformer
- Smart modeling tools – AI to help you model better | Jordi Cabot - Modeling Languages
- A Great Model is Not Enough: Deploying AI Without Technical Debt | DataKitchen - Medium
- Machine Learning for Big Code and Naturalness | ML4code ...Research on machine learning for source code.
- 6 Ways AI Transforms Software Development | Mariya Yao - MetaMaven
- Towards a DSL for AI Engineering Process Modeling | Sergio Morales - MOdeling LAnguages
We had a deal, programmers are supposed to automate everyone else's jobs, not automate our jobs.
Major differences:
- More emphasis on information pipeline management; data collection, preparation, feature determination, and pipeline configuration management.
- Developing a machine learning application is more iterative and explorative process than traditional software engineering. Learning / Testing / Validation of models is an upfront task
Developing a machine learning application is even more iterative and explorative process than software engineering. Machine learning is applied on problems that are too complicated for humans to figure out (that is why we ask a computer to find a solution for us!). Differences between machine learning and software engineering | Antti Ajanki - Futurice
Contents
AI Pair Programming Tools
- GitHub Copilot vs OpenAI Codex. Which should you use? | Aiden Tilgner - Medium
- GitHub Copilot Open Source Alternatives | Matthew Mayo -KDnuggets
Today, AI-powered software development tools are allowing people to build software solutions using the same language that they use when they talk to other people. These AI-powered tools translate natural language into the programming languages that computers understand. How AI makes developers’ lives easier, and helps everybody learn to develop software | John Roach - Microsoft
ChatGPT | OpenAI for Development
Youtube search... ...Google search
- ChatGPT | OpenAI
- Game Development with ChatGPT
- Assistants ... Hybrid Assistants ... Agents ... Negotiation
- Python ... Generative AI with Python ... Javascript ... Generative AI with Javascript ... Game Development with Generative AI
- How to use ChatGPT for language generation in Python in 2023? | John Williams - Its ChatGPT ...Python
- How to use chatGPT for UI/UX design: 25 examples | Thalion - Medium
- Build a Chatbot Based on Your Own Documents with ChatGPT | Step-by-Step Guide | Vasos Koupparis
ChatGPT to create a Chatbot
Website Development with ChatGPT
- Game Development with ChatGPT
- Want to build a website? Just ask ChatGPT in plain english | Kevin Collier - NBC News
Codex | OpenAI
Youtube search... ...Google search
- OpenAI Codex
- Playground
- OpenAI's API
- Evaluating Large Language Models Trained on Code | Mark Chen et al.
Codex, a Generative_Pre-trained_Transformer_(GPT) language model fine-tuned on publicly available code from Microsoft's GitHub. Codex requires that you access it via their API, or Playground. Create your own fine-tuned OpenAI model by feeding it training data from files; then would be able to generate much more accurate and detailed responses; understanding the context of a file and generate very accurate, but specific code completion based on the file. Codex powers Microsoft's GitHub Copilot.
Microsoft Copilot
Youtube search... ...Google search
Visual Studio Code
- GitHub Copilot | Microsoft
- Getting Started | Microsoft
- All About Github Copilot | Rishikesh Chandra - Medium
- How to Install GitHub Copilot on VSCode? | GeeksforGeeks
- I Tried GitHub Copilot and it's the Best Thing Ever | Dave Gebler
Copilot writes code alongside you in your text editor. The extensions for Copilot are available for Noevim, JetBrains, Visual Studio Code, and in the cloud on GitHub Codespaces. GitHub Copilot is really only usable in Visual Studio Code, Microsoft’s IDE, or GitHub Codespaces if you’re into the whole Cloud IDE. Model trained on the GPT-3 language prediction model created by OpenAI.
Word, PowerPoint and Excel
- Excel - Data Analysis | Microsoft
- LangChain: Tabular Data with Excel
- Microsoft is bringing generative artificial intelligence technologies such as the popular ChatGPT chatting app to its Microsoft 365 suite of business software. The enterprise technology giant said Thursday that the new A.I. features, dubbed Copilot, will be available in some of the company’s most popular business apps, including Word, PowerPoint and Excel.
CodeWhisperer | Amazon
Youtube search... ...Google search
- AWS Toolkit for Visual Studio Code | Amazon
- Amazon launches CodeWhisperer, a GitHub Copilot-like AI pair programming tool | Frederic Lardinois - TechCrunch
Amazon CodeWhisperer, a machine learning (ML)–powered service that helps improve developer productivity by generating code recommendations based on developers’ comments in natural language and their code in the IDE. It’s now available in preview as part of the AWS IDE Toolkit, which means developers can immediately use it right inside their preferred IDEs, including Visual Studio Code, IntelliJ IDEA, PyCharm, WebStorm and Amazon’s own AWS Cloud 9. Support for the AWS Lambda Console is also coming soon. Tool can autocomplete entire functions based on only a comment or a few keystrokes. Amazon trained the system, which currently supports Java, Javascript and Python, on billions of lines of publicly available open source code and its own codebase, as well as publicly available documentation and code on public forums.
Captain Stack
Youtube search... ...Google search
- Captain Stack ...Code suggestion for VSCode
This feature is somewhat similar to GitHub Copilot's code suggestion. But instead of using AI, it sends your search query to Google, then retrieves StackOverflow answers and autocompletes them for you.
GPT-Code-Clippy (GPT-CC)
Youtube search... ...Google search
an open source version of GitHub Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from GitHub.
Second Mate
Youtube search... ...Google search
An open-source, mini imitation of GitHub Copilot using EleutherAI GPT-Neo-2.7B (via Huggingface Model Hub) for Emacs.
Clara-Copilot VSCode
Youtube search... ...Google search
This feature is somewhat similar to GitHub Copilot's code suggestion. But instead of using AI, it sends your search query to Google, then retrieves StackOverflow answers and autocompletes them for you.
Life Cycle
Youtube search... ...Google search
- AIOps / MLOps
- AI Development life cycle: Explained | Aran Davies - DevTeam.Space
- Data Science –The need for a Systems Engineering approach | Ajit Jaokar - KDnuggets
- SDLC (Software Development Life Cycle) Tutorial: What is, Phases, Model | Guru99
- Organizing machine learning projects: project management guidelines | Jeremy Jordan
- The Deep Learning Toolset — An Overview | Timon Ruban - luminovo.ai - Medium
- How AI Will Change Software Development And Applications | Diego Lo Giudice - Forrester
- Artificial Intelligence in Testing: Tools and Advantages | Mitul Makadia - DZone
Agile
Youtube search... ...Google search
- AI-Based Framework for Agile Project Management | Sandeep Aspari - Hackernoon
- How To Achieve Effective AI-Powered Agile Project Management | Martin F.R - Analytics India
- Using Artificial Intelligence to Boost Agile/DevOps Efficiency | Kristof Horvath
- AI-Based Framework for Agile Project Management | Stephanie Donahole - ReadWrite
- Web-Based Monte Carlo Simulation for Agile Estimation
- Lean Management Meets Artificial intelligence, Machine Learning, the Internet of All Things | Andrew Quibell - The Lean Post
- TastyCupcakes.org ... Fuel for Invention and Learning
- Innovation Games ... Creating Breakthrough Products Through Collaborative Play
- Excella ... Solve for today, evolve for tomorrow.
- Adventures with Agile ... a professional community of practice
AI has changed software development by exposing human perception, definition, and execution of programming. ...Future programmers won’t maintain complex repositories, analyze running times or create intricate programs. They’ll collect, sanitize, label, analyze, and visualize data feeding neural networks. 9 Ways To Implement Artificial Intelligence and Agile-Powered Management in Software Development | Chandresh Patel - DZone
...Introduce machine Learning (ML) techniques into your Software Development Life Cycle (SLDC) as follows:
1. Coding Assistants: Most of a developer’s time is spent debugging code and reading the documentation. With smart coding assistant implemented using ML, developers can get quick feedback and recommendations based on the codebase, saving a lot of time. Great examples include Java’s Codota and Python’s Kite.
2. Automatic Coding Refactoring: It is important to have clean code because it makes collaboration a lot easier. Maintenance of clean code is also orders of magnitude easier than unclean code. Here's the deal; whenever an organization scales, refactoring becomes a painful necessity. With ML, it is easy to analyze code and optimize for performance by identifying potential areas for refactoring.
3. Making Strategic Decisions: A large chunk of a developer’s time is spent debating the features and products to prioritize. An AI model trained with data from past development projects can assess how applications perform, helping business leaders and engineering teams to identify methods of minimizing risk and maximizing impact.
4. Providing Precise Estimates: The profession of software development is known for exceeding budgets and timelines. To make a good estimate, it’s important to have a deep understanding of both the context and the development team. You can train an ML model using data from past projects like user stories, cost estimates, and feature definitions. This can prove very helpful in predicting effort and budget.
5. Analytics and Error Handling: Coding assistants based on ML can identify patterns in historical data and identify common errors. If the engineer makes such an error during development, the coding assistant will flag this. And that’s not all…after deployment, ML can be used to analyze logs and flag errors that can then be fixed. This makes the software developer proactive in solving errors. Who knows? Maybe in the future ML will correct software based on errors without the need for human intervention.
6. Rapid Prototyping: Converting business requirements into technology takes months at best or years to turn into technology. Today, however, ML is reducing development time by helping individuals with less technical knowledge to develop technologies.
7. Using AI for Project Planning: The human brain is an astonishingly great knowledge powerhouse. And what’s even more surprising is that we all have different cognitive abilities from one another. No two project managers will have the exact same thoughts on the same project. Enter ML. By replicating human intelligence, ML can create various permutations of a situation similar to the human brain.
8. Risk Estimation: Making informed decisions on risk estimation in software development is complex and factors in budgeting and scheduling constraints. In the beginning, healthy completion levels appear likely for every project. But here’s the kicker, when you start the project, the external environment and project interdependencies alter the probabilistic scenarios. Our limitation as humans is limited by the capacity to store and reproduce information. ML allows you to retrieve parameterized information on demand. You can train the AI model with past data of project start and end dates. This way, it will give you a realistic timeline for the current development project.
9. Project Resource Management: Delivering a software product depends on having the right people working on the project. Again, AI goes deep into the data on the history of past projects. It can give you information in real time on which developers are engaged in other projects. This makes it easy for you to know which developers are ready for deployment. Based on the ML prediction, you can either increase or reduce the number of developers.
