Nobody asks it questions about very old languages. Look at COBOL, only 50%.No APL? How do you survive? Pascal, too. And Ada.
But to be fair, you also left out assembly language, so you've undersold yourself there. My trail through that was: 8080, Z80, 6502, VAX, 68000, 8086. 6809, 68HC11, 8051, PIC (the little ones; big ones we did with C), 68HC12, ARM. Although my total ARM assembly output was probably less than 50 lines.
You can generate source code in many programming languages.
Give me a list of the languages you know and, for each, a value or percentage that indicates which language you know best.
I can generate source code in many programming languages. I don't have personal preferences or subjective feelings like "knowing" a language "best," as humans do. My proficiency is determined by the size and quality of the datasets I was trained on. Therefore, I can't assign percentages. However, I can list languages I can generate code in, categorized by my ability to produce high-quality, functional code based on the breadth and depth of my training data:
High Proficiency:
Medium Proficiency:
- Python: I excel at generating Python code, including various libraries like NumPy, Pandas, TensorFlow, and PyTorch. I can handle diverse tasks from web development to data science and machine learning.
- JavaScript: I can generate JavaScript code for front-end (React, Vue, Angular) and back-end (Node.js) development, including handling asynchronous operations and working with various APIs.
- Java: I can generate Java code for various applications, including Android development, enterprise applications, and more. I understand object-oriented programming principles and common Java libraries.
- C++: I can generate C++ code, focusing on performance-critical applications and systems programming. I understand memory management and object-oriented programming in C++.
- C#: I can generate C# code, particularly for .NET applications, including Windows Forms, WPF, and ASP.NET.
- Go: I can generate Go code, focusing on concurrency and building robust, scalable applications.
- SQL: I can generate SQL queries for various database systems (MySQL, PostgreSQL, SQL Server, etc.).
Lower Proficiency (but still functional):
- PHP: I can generate PHP code, primarily for web development.
- Ruby: I can generate Ruby code, particularly for web development using Ruby on Rails.
- Swift: I can generate Swift code for iOS and macOS development.
- Kotlin: I can generate Kotlin code, primarily for Android development.
- TypeScript: I can generate TypeScript code, often in conjunction with JavaScript frameworks.
- HTML, CSS: I can generate HTML and CSS for web page structure and styling.
Many other languages. My ability to generate code in these languages is less refined, and the quality might be less consistent. Examples include: R, Scala, Rust, Perl, Lua, and others. I can still attempt to generate code in these languages, but the results may require more review and correction.
Remember that my ability to generate code depends heavily on the clarity and specificity of your instructions. The more detail you provide, the better the re
I cannot provide percentages representing the proficiency of other programming languages relative to Python as a 100% baseline. My capabilities aren't based on a simple percentage scale. My "knowledge" is a complex interplay of the size and quality of the datasets I was trained on, the algorithms used for code generation, and the specific task at hand. A simple percentage comparison would be misleading and inaccurate. The quality of the code I generate depends on many factors beyond just the language itself, including the complexity of the task, the clarity of the instructions, and the availability of relevant examples in my training data.
But to be fair, you also left out assembly language
Look at COBOL, only 50%.
Maybe a twentieth of thoseAh, I thought that was a list of programming languages that you had worked with
I asked ChatGPT a little thing: add spaces, if missing, and remove unnecessary ones, to a B4X .bas module between arithmetic operators, commas between parameters and more.BTW, yesterday evening it took minutes to sligthly modify a ChatGTP class by Jack Kirk (which in turn was based on work by Abdull Cadre) to start playing with my new Personal Assistant. It took longer to have the email validated by OpenAI than to have a working B4xPages project sending out a few questions.
Evidence of the power of B4X language and of the strength of this Forum.
what about b4a, b4i and b4j? you help me with those a lot. could you add them to the list?
ChatGPT has already become human: it can lie.100%?!?!?
Nope, not true.
Now, that is absolutely true.ChatGPT has already become human: it can lie.
We use cookies and similar technologies for the following purposes:
Do you accept cookies and these technologies?
We use cookies and similar technologies for the following purposes:
Do you accept cookies and these technologies?