InfoQ Homepage Code Generation Content on InfoQ
-
GitHub's Learnings from Building Copilot - An Enterprise LLM Application
GitHub has published an article containing the lessons they learned in building and scaling GitHub Copilot -- an enterprise application using an LLM (Large Language Model). In a post on GitHub's blog, AI product leader Shuyin Zhao describes how -- over three years -- they broke the project down into three stages - "find it", "nail it" and "scale it", and successfully launched GitHub Copilot.
-
JetBrains Unveils AI Assistant for IntelliJ-Based IDEs and .NET Tools
JetBrains, the software development company known for creating the IntelliJ IDEA, has announced the introduction of a new AI Assistant in its Early Access Program (EAP) builds for all IntelliJ-based IDEs and .NET tools. This significant addition is aimed at transforming the landscape of software development tools by integrating generative AI and large language models into JetBrains' products.
-
Google Previews Studio Bot, a Coding Bot for Android Development
At Google I/O 2023, Google has previewed Studio Bot, an AI-powered coding bot integrated in Android Studio latest version, codenamed Hedgehog. Studio Bot aims to help developers generate code, unit tests, and fix errors.
-
AI-Based Code-Completion Tool Tabnine Now Offers Automatic Unit Test Generation
One of the pioneers in the field, Tabnine is a code completion assistant that uses generative AI to predict and suggest the next lines of code based on its surrounding context. Tabnine is now opening beta access to new capabilities aimed at generating unit tests.
-
Stanford Researchers Present AI Framework to Implement and Validate Complex Algorithms
Parsel, an AI framework created by a group of researchers at Stanford, uses large language model (LLM) reasoning to transform hierarchical functions descriptions in natural language into an implementation in code. Additionally, the researchers maintain, Parsel can be used for robot planning and theorem proving.
-
Google Launches Relay to Transform and Accelerate Android UI Creation
Recently launched in alpha, Relay is a design-to-code solution aiming to radically transform the way UI designers and UI developers collaborate to create Android UI components by removing the need for UI specs.
-
Google Published Results on How ML-Enhanced Code Compilation Could Improve Developers’ Productivity
The rapid advances in natural language processing (NLP) opened a new direction to use deep learning models in providing smarter suggestions for developers while writing software codes. Google AI has recently published results on ML-enhanced code compilation and how it improved developers’ productivity considering different metrics.
-
GitHub Copilot Adopts Paid Model, Still Free for Some Open-Source Maintainers and Students
After almost one year in technical preview, GitHub Copilot is now prime time-ready for students and individual developers, says GitHub, while companies and larger organizations could get access to it before the end of the year.
-
GitHub's Copilot Still a Long Way From Autopilot
Three months after GitHub launched Copilot, a group of academics affiliated with New York University's Tandon School of Engineering released their empirical cybersecurity evaluation of Copilot’s code contributions, concluding that 40% of the time, the code created is buggy and vulnerable.
-
Uber Reveals Its API Gateway's Architecture
Uber recently detailed the architecture of its internally built API gateway. It described how independent layered components handle each request in the gateway, with each layer being responsible for a different facet of the request lifecycle. A combination of YAML and Apache Thrift defines the gateway configuration, and a code-generated artifact in Go makes up the gateway implementation.
-
Building a Banking Infrastructure with Microservices: QCon London Q&A
In a few years, the number of microservices has grown from 100 to 1600 at Monzo, and it continues to grow. Microservices are split when responsibilities grow, or merged when services are tightly coupled. Engineers can generate, deploy, scale and monitor their own services using code generation.
-
C# 9: Partial Method Enhancements for Source Generators
Source Generators in C# 9 will allow compiler-extensions to inspect code and then inject additional source code at compile-time. This injected code is then incorporated into the very same assembly that was being compiled. In order to facilitate this capability, Microsoft is removing most of the restrictions on Partial Methods.
-
Source Generators Will Enable Compile-Time Metaprogramming in C# 9
Source generators are a new feature of the C# compiler that enables inspecting user code using compiler-generated metadata and generating additional source files to be compiled along with the rest of the program.
-
Designing Microservice Architectures the Right Way: Michael Bryzek's Lessons Learned at QCon NY
At QCon New York 2018, Michael Bryzek discussed how to design microservice architectures “the right way”. Key takeaways included: engineers should design schema first for all APIs and events, as this allows the automated code generation of boilerplate code; and investment should be made in automation, such as deployment and dependency management.
-
How No and Low Code Approaches Support Business Users and Professional Developers
No code approaches aim to support business users in developing and maintaining their own applications, where low code simplifies the developer’s work and makes them more productive. Both approaches enable faster development at lower costs. As the distinction between these approaches is becoming smaller, business users and developers can team up and use them together.