AI
AI-Assisted Development Under Deadline: What It Takes to Ship Production Code on an Unfamiliar Stack
Ihor Riazantsev | | AI code risk, AI coding tools, AI-assisted development, AI-generated code, Claude Code, code consistency, code review, devops teams, engineering discipline, feature isolation, manual testing, memory leak debugging, Next.js development, production readiness, production validation, production-ready code, rapid feature delivery, React development, software architecture, software engineering judgment, technical debt, TypeScript development, unfamiliar codebaseHow Claude Code accelerated development on an unfamiliar stack while proving that production-ready AI-generated code still requires human judgment ...
FakeGit Targets AI Coding Agents with Malicious GitHub Repos
Jeff Burt | | AgentBaiting, AI coding agents, AI supply chain risk, Anthropic Claude Code, fake repositories, FakeGit, github, Google Gemini, Island, MCP Server, OpenAI ChatGPT, SmartLoader, StealCThreat actors continue to find new ways to incorporate AI into schemes aimed at luring developers into downloading malware from fake repositories. The latest example involves almost 7,600 malicious GitHub repositories that ...
OpenAI’s Codex Context Cut Puts Enterprise AI Coding Workflows on Notice
OpenAI quietly trimmed the default input context window for GPT-5.6 inside its Codex CLI, dropping it from 372,000 tokens to 272,000 tokens. That's a 27% cut, and developers noticed fast. The change ...
VS Code 1.129 Moves Agent Sessions Out of the Editor Window
Microsoft has released Visual Studio Code 1.129, and the headline change isn't a new feature so much as a new foundation. The update introduces the agent host, a dedicated process that runs ...
Security Risks from AI Coding Agents Expand Beyond the Sandbox: Pillar
Jeff Burt | | AI code assistants, AI coding agents, AI Developers, AI sandbox, AI security risks, Cursor, Cymulate, Google Antigravity, Google Gemini, OpenAI Codex, Pillar Security, prompt injectionAI coding assistants have become an essential part of developers’ work, automating many of the repetitive tasks – think boilerplate coding and scaffolding – that in the past ate up a lot ...
Signed, Attested, and Malicious: The Software Supply Chain Has a Deepfake Problem
Nigel Douglas | | AI coding agents, AntV packages, behavioural analysis, continuous scanning, dependency security, Developer Security, GitHub Actions compromise, malicious packages, Miasma worm, Mini Shai-Hulud, npm malware, OIDC tokens, open source security, package provenance, package quarantine, policy as code, Red Hat npm attack, registry scanning, Shai-Hulud worm, SLSA provenance, software attestation, Software Supply Chain Security, TanStack compromise, trusted pipeline attacksA developer pulls a package from a reliable repo. It is signed, has provenance, and has been scanned. And then…it contains malware. That is no longer hypothetical. When the Miasma worm tore ...
Harness Extends DevOps Reach to the Realm of AI Agents
Harness today extended the reach of its core continuous integration/continuous delivery (CI/CD) platform to enable DevOps teams to build and deploy artificial intelligence (AI) agents. At the core of that capability are ...
AI Moved the Bottleneck From Writing Code to Understanding and Trusting It
Ted Julian | | AI code generation, AI code security, AI coding tools, AI investment ROI, AI-generated code, application security, automated code review, code quality, code review, codebase visibility, compliance, dependency risk, developer productivity, devsecops, Engineering leadership, engineering metrics, engineering ROI, production incidents, pull request review, SCA, software composition analysis, software delivery, software development productivity, software governance, technical debtAI coding boosts velocity, but without stronger review, governance and codebase visibility, teams risk higher costs, security gaps and production failures. TL;DR ...
xAI Open-Sources Grok Build Coding Agent After Cloud Upload Exposes SSH Keys, Repos
Tom Smith | | AI agent governance, AI coding agent, Apache 2.0, credential exposure, developer privacy, devops security, github, Grok Build, open-source coding agent, Repository Security, source code security, xAIxAI has published the full source code for Grok Build, its terminal-based AI coding agent, on GitHub under an Apache 2.0 license. The release lands three days after a security researcher showed ...
AI-Generated Code Is Cheap But the Context Infrastructure Behind It Is Not
Saqib Jan | | AI coding, context engineering, Enterprise AI, RAG, retrieval-augmented generation, vector databasesThe cost curve for generating code with AI has moved in one direction, and it has moved fast. What used to require a senior engineer's full attention for an afternoon can now ...
Why You Need AI Agent Security Validation in Software Testing
Engineering teams have been racing for the last two years to deploy AI agents that can find bugs faster than any QA team ever could. Autonomous testing agents can crawl through codebases, ...
SmartBear Tightens Integration Between AI Coding and Testing Tools
SmartBear this week revealed it is narrowing the divide between coding and testing by integrating its platform with artificial intelligence (AI) coding tools. Sheryl Koenigsberg, senior vice president of product marketing at ...
