Full-text search across 62491 articles. Combine with topic and date filters; results sorted by relevance.
Developer Rhubarb launched Rhubarb, a platform that uses an AI assistant to write JavaScript and D3 code for custom data visualizations and publish them live, with a limited public demo available at rhubarbviz.com/try. T…
Hermes Labs has released Hermeneutic, an open-source tool that mines user corrections from coding-agent conversations and surfaces relevant guidance when similar tasks arise. Hermeneutic reads Claude Code, Codex, and Ope…
Autonomous published a three-layer defense for unattended AI coding agents that combines Secure MCP Cloud, Runtime Protection, and session-state egress restrictions to break the "lethal trifecta" of private data access, …
A developer post argues that starting Rust development for AI agents now requires only an IDE, a coding agent such as Claude Code, Codex or Cursor, and a single prompt, citing DHH's Rails World 2026 keynote where he said…
An engineering manager who oversees teams using Claude Code and Codex argues that AI coding assistants create "comprehension debt" — working code that no one on the team can explain. The piece cites an Anthropic randomiz…
Thinking Machines Lab is hiring a Software Engineer, Developer Productivity, AI Tools in San Francisco at an annual salary of $300,000–$350,000, a range the job board reports sits 48% above the $220,000 median for MLOps/…
A developer built a phase-split latency harness that separates a remote generate call into named clocks — connect, time-to-first-byte, body, patch apply, and pytest — to show that P99 stalls often come from the wire (TLS…
Google launched early access to Home MCP on September 16, a Model Context Protocol server that lets MCP-capable AI agents monitor, query, and control devices in a user's Google Home ecosystem, with access gated behind th…
Former Google researcher Jeff Dean said Gemini's origins trace to a one-page memo he wrote urging separate teams at Google Brain, Legacy DeepMind, and Google Research to combine their people, ideas, and compute into a si…
Long-horizon AI agents can now produce logically sound outputs, such as the Lean-verified proof in the OpenAI Navier–Stokes incident, that no human holds a theory for — what Peter Naur in 1985 called a "dead program." Th…
Agentic coding TUIs including Claude Code, Codex, Aider, Crush, opencode, and Goose each ship their own slash commands, keybindings, pane layouts, and status lines with no shared conventions or documented standards, acco…
Software developer Andrew Oliver warns that TODO code comments have become dangerous in the age of AI coding agents, which can treat a hastily written note as fact and turn it into real code, causing bugs or outages. Oli…
Sumama Jameel, a 14-year-old developer in Karachi, Pakistan, has shipped nine products that he designed and built by directing AI to write, test, and debug the code. His primary project, Megabit, is a data generation eng…
Microsoft published first-party throughput data for its internal PRAssistant AI code review tool, which ran across 5,000 internal repos, covered over 90% of pull requests and 600,000 PRs a month, and measured a 10–20% me…
A new Model Context Protocol (MCP) server, davinci-resolve-mcp, enables AI assistants to control DaVinci Resolve Studio through the official Scripting API, offering full API coverage and workflow helpers for editing, med…
Software engineers remain in high demand because AI coding agents generate code cheaply but lack discernment, producing buggy or overly complex software that requires human judgment to manage, according to an essay in th…
Redowan Delwar, writing on his blog 'Redowan's Reflections', argues that the Pi coding harness, created by Mario Zechner, is more effective than Claude Code and Codex because its system prompt and tool definitions total …
A developer's hands-on comparison of three AI coding agents found Anthropic's Claude Code excels at complex refactors, open-source Opencode offers deeper terminal integration, and Kiro delivers faster execution for small…
A developer's field test of running local AI models on consumer GPUs in 2026 finds that memory capacity is the key constraint, with 8GB handling 3B-4B models and 32GB enabling 14B-30B models via quantization. Code autoco…
CodeRabbit, an AI-powered code review tool, has reached a $1.5 billion valuation, signaling a shift in AI workflows toward safety and review rather than code generation. The company's specialized LLM agent scans pull req…