Full-text search across 56867 articles. Combine with topic and date filters; results sorted by relevance.
Creation of Coda AI, a VS Code extension designed to eliminate the workflow friction of constantly switching between a code editor and a browser to use AI tools. Unlike basic AI assistants, Coda understands the entire pr…
Concept of "accountability debt" in AI-assisted software development, defined as the gap between who benefits from the efficiency of AI-generated code and who bears the responsibility when that code fails. It argues that…
Anthropic engineer Thariq Shihipar is using HTML artifacts to plan projects and build interactive specs with Claude Code, arguing that HTML has replaced Markdown as the superior format for communicating with AI agents. E…
An analysis of AI-generated code argues that AI coding tools can produce PHP, JavaScript, HTML, CSS, and database queries quickly but often introduce security, architecture, and maintainability problems that require prof…
A developer reports that Anthropic's Claude Code CLI tool cut feature development time from 4-6 hours to 1-2 hours by reading entire codebases and making coordinated multi-file changes. The engineer says the tool, which …
David Heinemeier Hansson, creator of Ruby on Rails and co-owner of 37signals, discussed the release of Basecamp 5, his evolving stance on AI-assisted development, and the future of Rails in a podcast interview. Hansson r…
Anthropic's Claude Code v2.1.239, released on August 21, 2026, fixed a bug where proxies stripping the response Content-Type header caused Bedrock streaming to silently re-run every turn non-streaming, doubling billed AP…
SigNoz has released a guide for monitoring Anthropic's Claude Code AI assistant using OpenTelemetry, enabling engineering teams to export logs and metrics on token usage, costs, session activity, and tool decisions to Si…
Engineering teams that adopted AI coding tools like Cursor or Claude six months ago are hitting a productivity plateau, with initial gains leveling off and failing to deliver the step-change improvement promised to leade…
Claude Code and OpenAI Codex, agentic coding tools available for about 18 months, are more similar than different, and choosing between them depends on workflow and ecosystem rather than benchmarks, according to ZDNET. T…
Developers can now run Zhipu AI's GLM 5.2 model inside Anthropic's Claude Code coding environment by routing API calls through OpenRouter, using the ANTHROPIC_BASE_URL environment variable to point to OpenRouter's endpoi…
A product manager used AI as a tutor to learn coding from a Kaggle dataset, building a working model while catching a classic machine learning mistake. The approach reveals that AI amplifies existing expertise and gaps, …
Claude Code 2.1.277, released 09/18/2026, added AGENTS.md support via a built-in plugin with four modes, but the default loads AGENTS.md only when a project has no CLAUDE.md in the working folder or any folder above it, …
XAI released Grok 4.5, a large language model offering near-frontier coding performance at $2 per million input tokens and $6 per million output tokens, roughly half the cost of comparable models. The model is optimized …
A 2026 analysis reveals that 92% of developers use AI coding assistants monthly, yet only 7% of organizations have deployed autonomous agents in production, creating a 13x gap. The report warns that organizations failing…
A study of 212,000+ AI coding benchmarks across Python, Go, JavaScript, and C# found that no prompt configuration consistently beat an empty prompt, with a nearly perfect negative correlation (r = -0.95) between instruct…
A developer's teardown of the command-code@1.58.0 npm package found that its marketed "taste-1" feature is not a "meta neuro-symbolic AI model with continuous reinforcement learning" but a prompt sent to whichever ordina…
A developer optimized AI-powered code review for speed and accuracy by providing sufficient context, such as API documentation and system architecture summaries, to reduce false positives and hallucinations. The develope…
A developer published a deep-dive on applying discrete diffusion models to code generation as an alternative to autoregressive LLMs like GPT-4 and Claude. The writeup argues that diffusion's iterative denoising approach …
A blog post argues that the question "Do You Still Read the Code?" smuggles in a premature theory of progress, dividing AI-assisted developers into two camps: "accelerators," who read generated code to retain understandi…