Code

A new AI code generation tool, Test-Gated AI Code Generation, claims to prove its work by generating tests alongside code, but the server hosting the announcement returned a temporary error, preventing access to details.…

Developer Vlad The Dev argues that Anthropic's Claude Code, an AI coding tool, is contributing to a decline in software craftsmanship by generating 'AI slop'—generic, low-quality code—that prioritizes speed over artistry…

Capuchin, an AI code assistant from the company Capuchin, offers a self-hosted deployment option that keeps source code private by running entirely on a company's own infrastructure, addressing concerns about code leakag…

M5Stack has introduced an Approval Console for AI coding agents, a hardware device designed to provide a physical approval interface for AI-driven coding tasks. The console aims to enhance security and control by requiri…

A developer reports that AI-generated code accelerates development but introduces scaling challenges earlier in the product lifecycle, as the speed of code creation outpaces traditional infrastructure and testing readine…

CoreAuto, a developer of autonomous vehicle software, reports that AI models are now generating systems-level code for its self-driving platform, a shift that could accelerate development but raises new safety and verifi…

A video titled 'AI Coding is Exhausting' discusses the challenges developers face when using AI tools for coding, highlighting the mental fatigue and inefficiencies that can arise from relying on AI-generated code.

A developer proposes using semantic contracts to rebuild trust in AI-generated code, addressing the reliability issues of current large language model outputs. The approach aims to provide formal guarantees about code be…

Anthropic released Claude Code, a new AI-powered coding tool. The product aims to assist developers with code generation and debugging. This launch marks Anthropic's entry into the developer tools market.

A PDF argues that teaching kids to code remains essential in the age of AI, emphasizing that coding fosters problem-solving, creativity, and understanding of technology. The document suggests that AI tools complement rat…

A developer argues that a coding agent is essentially six functions in a trenchcoat, breaking down the complexity of AI-powered coding assistants into core functional components. The post explores how these functions com…

A new approach enables developers to transform AI coding agents into deterministic Java Spring experts, offering precise and reliable code generation for enterprise applications. The method focuses on eliminating variabi…

The rapid acceleration of AI-generated code is outpacing the security infrastructure designed to protect it, creating a significant vulnerability gap for software development teams. As developers increasingly rely on AI …

ClickHouse engineers spent a year integrating AI agents into their coding workflow, learning that the tools excel at generating boilerplate code and writing tests but struggle with complex logic and debugging. The team f…

AI-generated code is creating a "pain waiting to happen" for developers, according to a new analysis warning that reliance on large language models for software development introduces hidden vulnerabilities and technical…

The article presents the source code for a music track titled "siberspace," which appears to be created using a live coding or algorithmic music environment. The code sets a tempo, loads French speech samples from a "sha…

OpenAI's Codex coding agent now runs across three surfaces — an open source CLI, the ChatGPT desktop app and IDE extension, and Codex Cloud — with cloud tasks startable and followable from any device since OpenAI's DevDa…

Earendil released Pi 1.0 on 1 Oct 2026, an MIT-licensed open source coding agent harness that runs in the terminal, reads repositories, edits files and executes shell commands with more than 15 supported model providers.…

Flux CTO Aaron Beals reported that an anonymized customer's AI coding assistant rollout improved deployment frequency and pull-request lead time over a three-month comparison, but time to first review rose from 6.4 hours…

Cline can run as a fully autonomous coding agent on local hardware by connecting to Ollama instead of cloud providers like Claude or GPT-4, keeping all inference on the user's own machine. The setup requires raising Olla…