InfoQ Homepage Code Generation Content on InfoQ
-
QConSF 2025 - Developing Claude Code at Anthropic at AI Speed
At QCon San Francisco 2025, Adam Wolff showcased Claude Code at Anthropic, where AI powers 90% of production code. With a focus on speed over planning, Claude Code's design evolved through experimentation, addressing challenges like Unicode issues and shell command bottlenecks. Discover successful iterations and lessons learned in real-time software development.
-
AI-Generated Code Creates New Wave of Technical Debt, Report Finds
AI-generated code is “highly functional but systematically lacking in architectural judgment”, a new report from Ox Security has found. In a report released in late October called Army of Juniors: The AI Code Security Crisis, AI application security (AppSec) company Ox Security outlined 10 architecture and security anti-patterns that are commonly found in AI-generated code.
-
Kimi's K2 Opensource Language Model Supports Dynamic Resource Availability and New Optimizer
Kimi released K2, a Mixture-of-Experts large language model with 32 billion activated parameters and 1.04 trillion total parameters, trained on 15.5 trillion tokens. The release introduces MuonClip, a new optimizer that builds on the Muon optimizer by adding a QK-clip technique designed to address training instability, which the team reports resulted in "zero loss spike" during pre-training.
-
Anthropic Adds Sandboxing and Web Access to Claude Code for Safer AI-Powered Coding
Anthropic released sandboxing capabilities for Claude Code and launched a web-based version of the tool that runs in isolated cloud environments. The company introduced these features to address security risks that arise when Claude Code writes, tests, and debugs code with broad access to developer codebases and files.
-
Cursor 2.0 Expands Composer Capabilities for Context-Aware Development
Cursor has launched version 2.0 of its AI-driven code editor, featuring Composer, a new model that enables developers to write and modify code through natural language interaction.
-
Apple Open Sources Diffusion-Based Coding Model DiffuCoder
Apple open sourced DiffuCoder, a diffusion large language model (dLLM) fine-tuned for coding tasks. DiffuCoder is based on Qwen-2.5-Coder and outperforms other code-specific LLMs on several coding benchmarks.
-
Anthropic Upgrades App-Building Capabilities to Claude Artifacts
Anthropic has upgraded Claude with new app-building capabilities, allowing users to create, host, and share AI applications directly from text prompts. This functionality, known as Artifacts, enables users to build functional tools like data analyzers, flashcard generators, or study aids by simply describing their ideas.
-
Mistral Releases Its Own Coding Assistant Mistral Code
Mistral has introduced Mistral Code, a new AI-powered development tool aimed at improving the efficiency and accuracy of coding workflows. Mistral Code utilizes advanced AI models to offer developers intelligent code completion, real-time suggestions, and the capability to interact with the codebase using natural language.
-
Windsurf Launches SWE-1 Family of Models for Software Engineering
Windsurf has introduced its first set of SWE-1 models, aimed at supporting the full range of software engineering tasks, not limited to code generation. The lineup consists of three models SWE-1, SWE-1-lite, and SWE-1-mini, each designed for specific scenarios.
-
GPT-4o Code Completion Model Now Available in Public Preview for VS Code Copilot
Recently, GPT-4o Copilot is introduced for Visual Studio Code (VS Code) users. This AI model is built upon the GPT-4o mini foundation and includes extensive training from over 275,000 high-quality public repositories across more than 30 widely used programming languages. The enhanced training is expected to provide more accurate and contextually relevant code suggestions.
-
Gemini Code Assist Now Grants Generous Free-Usage Limits to Everyone
Born as an enterprise-focused AI-based code generation tool, Gemini Code Assist now provides a free tier to individual developers with a limit of 6,000 code completions and 240 chat requests daily.
-
OpenAI Introduces Software Engineering Benchmark
OpenAI has introduced the SWE-Lancer benchmark, to evaluate the capabilities of advanced AI language models in real-world freelance software engineering tasks.
-
Mistral Introduces AI Code Generation Model Codestral
Mistral AI has unveiled Codestral, its first code-focused AI model. Codestral helps the developers with coding tasks offering efficiency and accuracy in code generation.
-
Gemini Code Assist to Create APIs, Integrations, and Automation Flows in Public Preview
At the Cloud Next Conference, Google unveiled its enterprise-focused AI Code completion and assistance tool, Gemini Code Assist, which is available in public preview for Apigee API Management and Application Integration.
-
Large Language Models for Code by Loubna Ben Allal at QCon London
At QCon London, Loubna Ben Allal discussed Large Language Models (LLMs) for code. She discussed the lifecycle of code completion models, which consists of pre-training on vast codebases and finetuning and continuous adaptation. She specifically discussed open-source models, which are powered by platforms like Hugging Face.