OpenAI's GPT-5.6 powers a new version of Charlie, an AI engineering agent that autonomously investigates and resolves stuck PRs, production alerts, and bug reports. The updated system uses three GPT-5…
AI-generated code now accounts for 51-75% of weekly output at two-thirds of tech firms, with 45% of AI-written code containing security flaws, while the average time from bug disclosure to exploitatio…
Claire Vo built a custom AI harness for bug triage at ChatPRD using the Claude Agent SDK, a terminal UI with Ink, and adapters for Sentry, Linear, GitHub, and Vercel. The harness automates evidence ga…
Engineers face 'cognitive debt' as AI tools write code they don't fully understand, warned by a 2025 MIT Media Lab preprint. A developer recounts two debugging sessions on the same Android codebase: o…
A developer explains that Model Context Protocol (MCP) is the critical infrastructure enabling AI agents to interact with real services like Stripe, Postgres, and Sentry. By wiring MCP servers into a …
A developer who spent 60 days using Claude Code on a production ERP project reports 984 commits, 131,628 lines of TypeScript/TSX/JS/JSX, 276 Supabase migrations, and 74 architecture decisions. The pro…
A malicious npm package called codexui-android stole OpenAI Codex authentication tokens from developers in a supply chain attack. The package, which had over 29,000 weekly downloads and was also bundl…
Vercel released AI SDK 7 on June 25, introducing durable WorkflowAgent that preserves agent state across serverless timeouts and deploys, and HarnessAgent to unify multiple CLI runtimes. The update al…
A new AI agent automatically analyzes production errors from Sentry, identifies root causes in a codebase, and opens GitHub pull requests with fixes. The tool connects via OAuth and a GitHub App, supp…
Morning Report, a new AI-powered tool, aggregates data from email, code, payments, and analytics into a single daily briefing. The service offers a free tier with two integrations and a $5/month Pro p…
Assembled open-sourced 143.dev, its internal infrastructure for running coding agents as a team, under an MIT license. The system runs multiple agent harnesses in sandboxes and integrates with tools l…
A developer built Ravn, an open-source Python error monitoring tool, after finding Sentry's pricing too expensive for a side project. Ravn captures exceptions with two lines of code, groups similar er…
Tenet Security disclosed a new attack vector called Agentjacking on June 12, which hijacks AI coding agents like Claude Code, Cursor, and Codex with an 85% success rate by injecting crafted fake error…
An engineer tested 100 Model Context Protocol (MCP) servers to identify the 12 worth installing. The MCP ecosystem has grown to nearly 20,000 servers, with major adoption across tools like Claude Code…
Anthropic launched the Claude ecosystem, enabling users to connect tools like Slack, Google Workspace, and Microsoft Office to Claude for automated workflows. The platform includes connectors and plug…
Postman AI Engineer was demoed at a meetup in San Francisco, showing how it uses a Context Graph to map system dependencies and identify downstream impacts of code changes. The demo highlighted that a…
A team at an unnamed company built a customer support agent on LangChain that hallucinated a wrong return policy in a multi-step process, logging success while being confidently wrong. This incident h…
Navdeep Singh, known as NeetCode, discussed his journey from Amazon and Google to building NeetCode.io, a coding interview preparation platform, on The Pragmatic Engineer podcast. He argued that LeetC…
A developer built Pathway AI, a full-stack SaaS platform for international students, in one month using Next.js, Supabase, and TypeScript. The platform features student profiles, visa checklists, SOP …
GLM 5.2, an open-weight coding model from Z.AI, outperformed Claude Opus in four real-world coding tasks including a codebase audit, UI redesign, and autonomous bug hunting, costing only $3.36 for 6 m…