AI-generated code is shifting the bottleneck in software development to code reviews, with engineering teams spending more time reviewing AI-written code than writing it themselves, according to a rep…
Dosu released Decant, a local-first CLI and web tool that analyzes Claude Code and Codex session logs to show token usage, estimated cost, context, and agent activity, with full-text search and export…
Check Point Research's AI Security Report 2026, published July 14, says AI is now operating inside live cyberattacks, citing a breach that generated 5,317 AI-executed commands across 34 sessions and a…
Anthropic's Chrome extension update, released August 7, now syncs Claude Cowork and Claude Code sessions across Chrome, enabling users to carry full AI context and conversation history between desktop…
Anthropic announced today that Claude's Chrome side panel is now a full Cowork session, enabling browser-based tasks and conversations to be saved to Claude history and resumed across Claude's desktop…
Docker's new Docker Sandboxes product runs AI coding agents such as Claude Code, Codex CLI, Copilot CLI, Kiro, and OpenCode inside dedicated microVMs with custom VMMs, providing hardware-level isolati…
Anthropic launched Claude for Chrome, a browser extension available on all paid plans that reads the page a user is signed in to and can click, type, and fill forms while the user decides what happens…
A developer argues that a better model alone doesn't guarantee better results, emphasizing the importance of the 'harness'—the system that controls context, tools, permissions, and feedback loops—citi…
Drift, a semantic version-control layer wrapping Git, turns every commit into an 'Intent' that records the originating prompt, agent model, AST-level mutations, an optional cognitive-state checkpoint,…
A developer released a corpus of 480 real AGENTS.md and CLAUDE.md instruction files pulled from 272 production repositories, including React, Grafana, LangChain, and Home Assistant. The project, hoste…
A developer found that running their evaluation suite through Anthropic's Claude Code CLI costs $0 per run, while the same 27 calls via the API would bill $9.14. The CLI prints a total_cost_usd receip…
An engineer built MigrationPilot, a tool that parses SQL migrations with Postgres' own parser and checks them against 112 rules for locking footguns, after measuring that a one-line migration can hold…
Anthropic has begun watermarking AI-generated text across all Claude models, including in the EU, using an imperceptible statistical token watermarking scheme rather than hidden Unicode or whitespace,…
Bun creator Jarred Sumner detailed the JavaScript runtime's migration from Zig to Rust using Claude Code, while Zig creator Andrew Kelley publicly criticized the project and Sumner, calling him a 'sti…
A developer built Forge Code, a free browser-based coding challenge game, using Claude Code to help bridge the coding education gap in their community. The game offers two tracks: an Academy for begin…
A developer released bluepencil, an open-source editing skill that targets the root failure of AI-generated drafts—lack of commitment—rather than relying on word-ban lists that decay over time. The to…
Amazon Web Services (AWS) introduced granular cost attribution for Amazon Bedrock, enabling per-user and per-application tracking of inference requests via the new `line_item_iam_principal` column in …
Google Cloud has published a guide for configuring OpenAI's Codex CLI to work with Looker over the Model Context Protocol (MCP), marking the third iteration of the same integration approach previously…
A Hacker News user reports their company has shifted to a six-week implementation cycle with one-week planning/retro, where standups focus on demos and AI agents generate Product Requirement and Syste…
Lovable, an AI-powered software development platform, reached a $13.3 billion valuation after raising $400 million in a funding round. The company aims to automate full-stack generation, positioning i…