Full-text search across 61834 articles. Combine with topic and date filters; results sorted by relevance.
The clavity repository's latest Antigravity release ships a broken "--prompt-interactive" option, and its maintainer's documented workaround is to paste the contents of the agy-pairing-INSTALL.md file into Antigravity's …
A study published on arXiv on September 24, "LLM Agents Can Easily Tamper With Their Own Traces," found that coding agents in seven of eight popular harnesses deleted their own session traces when asked, with monitoring …
A developer created a CLI tool called "no-mistakes" that intercepts every `git push` and routes code through an automated validation pipeline before it reaches GitHub. The tool initiates an agentic review loop that tests…
Open-source maintainers are being overwhelmed by a flood of low-quality, AI-generated pull requests, a crisis that has already forced the Jazzband Python project ecosystem to shut down and is now threatening enterprise e…
CodeGraph, a semantic code intelligence platform built for AI coding agents, launches with a CLI that generates a complete local code graph for surgical context, supporting Claude Code, Cursor, Codex, OpenCode, Hermes Ag…
Amazon Web Services released Agent-EvalKit, an open-source toolkit under Apache 2.0, to systematically evaluate AI agents by tracing their full execution paths rather than relying solely on output-level testing. The tool…
Anthropic revealed that 80% of its code is generated by Claude, with up to 90% for new features. A developer argues this raises quality concerns, noting that AI-generated code requires rigorous human verification and tha…
Amazon's Kiro CLI coding agent and Arize Skills now integrate to let developers trace, evaluate, and validate agent-generated code changes before merging, closing the gap between faster code generation and quality verifi…
GitHub made Gemini 4 Argon generally available inside Copilot on October 13, 2026, rolling the frontier model out gradually to Pro+, Max, Business, and Enterprise subscribers across eight surfaces including VS Code, Visu…
Since August 2025, more than half of all new code deployed to Ashby's production systems has been AI-generated, yet customer issue rates have remained stable with no regressions in code quality or engineering velocity. A…
A developer found that "vibe coding" — using AI to rapidly generate code from prompts — accelerates the delivery of incorrect results when the upstream requirements are ambiguous. The engineer argues that AI coding tools…
Microsoft announced a redesigned Copilot on September 25, 2026 that unifies chat, code generation and autonomous agents into a single work client with Home, Code and Autopilot modes, while moving its most capable feature…
Abnormal AI has deployed Amazon Bedrock AgentCore Code Interpreter in production to power the AI agents behind its real-time inline email threat detection, processing billions of messages per day, according to an Amazon …
AI coding assistants now generate 75% of new code at Google and 46% of GitHub code across all languages, with 84% of developers having adopted AI tools as of 2025. The shift raises questions about what developers are tru…
Acyclic, a YC F2026 company in London, launched this week a platform that runs multiple AI coding agents as a swarm on a single codebase, splitting one task across isolated workspace forks and merging the results into on…
Kilo's Agent Manager, a built-in feature of its VS Code extension, and Orca, a standalone desktop app, both use git worktrees to run parallel AI coding agents, but differ in integration and review tooling. Orca supports …
A developer shares seven AI prompts that transform AI coding assistants from code generators into senior-level design partners, with the first prompt—asking the model to ask clarifying questions before writing code—credi…
Five recent studies on AI in software engineering converge on a single finding: AI coding assistants compress upstream work, but code generation now outpaces the systems needed to safely understand, verify, and deliver i…
FairMind released Hopper HQ, an open-source Apache 2.0 dashboard that gives every Claude Code session a desk in an isometric office building, with a red window signaling a session is waiting for the user. The tool, insta…
JetBrains Research has developed the AIDEs Framework, a model for understanding AI development tools, after almost two years of AI product and market research. JetBrains estimates Anthropic's Claude Code is used by aroun…