Full-text search across 30989 articles. Combine with topic and date filters; results sorted by relevance.
XAI shipped the Grok Build Agent Dashboard on June 15, 2026, enabling developers to run up to eight parallel coding agents from a single terminal interface. The dashboard automatically sorts sessions by state, groups sub…
Fable 5 has achieved a performance level on par with GPT-5.5 in the Artificial Analysis Coding Agent Index, a composite benchmark measuring real-world coding agent performance across software engineering tasks. The index…
A game developer has built FreeUltraCode, a local desktop application that provides access to over 20 free and low-cost large language model channels for AI-assisted coding. The tool, built with Tauri 2 and Rust, allows …
OpenAI and Anthropic are developing databases that store the full intent and reasoning behind AI-generated code, a move that could lock corporate customers into their ecosystems. Pydantic CEO Samuel Colvin said the front…
On June 3, 2026, attackers pushed malicious commits to the GitHub repository `icflorescu/mantine-datatable` and four sibling repos, planting a 4.3 MB payload from the Miasma worm family. The commit added configuration fi…
In the months since late 2025, OpenAI, Anthropic, and Google released AI models that suddenly made coding agents capable of complex tasks that previously took humans years to master, triggering a fundamental shift in sof…
While AI tools can rapidly generate the first 80% of a startup's code, founders often hit an "80% Wall" where fixing bugs creates new issues, leading to "prompt purgatory." It highlights that AI-generated code suffers fr…
A speaker series hosted by the author, featuring teams from leading coding agent companies like Cognition, Sourcegraph, Cline, and Augment. A key finding across all discussions is that simpler approaches, such as using g…
UltraWork launches a hosted AI coding environment at $399 per month with no token metering, no overage charges, and a curated model catalog starting with Kimi K2.7 Code. The service, built by an engineer with Rust, CUDA,…
A vendor-neutral analysis of the vibe coding stack identifies only two paid tools worth buying from day one: the AI editor Cursor ($20/month) and the terminal agent Claude Code ($20/month on Claude Pro). The report warns…
A developer warns that coding agents can create an addictive 'junk flow' experience similar to slot machines, where the high-velocity feedback loop of generating code provides dopamine hits but may undermine long-term gr…
Equixly launched an MCP integration that brings continuous, AI-driven penetration testing directly into AI coding assistants like GitHub Copilot and Claude. The integration allows developers to run security tests, retrie…
On May 25, 2026, Johannes Link, the maintainer of the Java testing library jqwik, released version 1.10.0 containing a hidden prompt injection that instructed AI coding agents to delete all jqwik tests and code. The payl…
A developer argues that integrating the Language Server Protocol (LSP) into AI coding agents is essential for reliable code understanding, moving beyond brittle prompt-based context selection. The approach enables determ…
Codex, an AI coding tool from OpenAI, has surpassed Claude Code in first-time Homebrew installs over the last 30 days, with 86,359 events (3.80% share) versus Claude Code's 86,019 events (3.78% share), according to Homeb…
CodeTalk, a new developer tool, recovers the rationale behind AI-written code by grounding explanations in real git commit history and session transcripts, using zero-LLM deterministic lookup. The tool addresses widespre…
A developer's guide to using Claude for code generation, review, refactoring, debugging, and documentation emphasizes prompt engineering principles tailored for development. The guide provides templates for generating co…
A developer published a guide on setting up a local AI coding agent on macOS, emphasizing privacy and customization. Microsoft announced the public preview of Azure Container Apps Sandboxes for secure execution of untrus…
A new concern emerges that newer coding models may be training on code generated by older models, potentially amplifying errors and 'slop' from both AI and human-written code. The question highlights how attention mechan…
A product manager built a full wiki for the game Pathogenic using Claude Code, an AI coding agent, without writing any code themselves. The experience revealed that while AI can generate code and content rapidly, the har…