CodeRabbit CEO Brandon Gubitosa argues that the real bottleneck in code review is understanding code, not reviewing it, as AI-generated code increases volume and complexity. He claims AI-written pull …
Conductor 0.68.0 introduces markdown frontmatter separation, experimental OpenCode support, and new keyboard shortcuts for editing and previewing files. The update also fixes several issues including …
Datasette launched a new plugin, datasette-apps, that allows users to host custom HTML+JavaScript applications inside a Datasette instance. The apps run in a sandboxed iframe with strict CSP headers t…
GitHub will deprecate the Opus 4.6 (fast) model across all Copilot experiences on June 29, 2026, urging users to migrate to Opus 4.8 (fast). Enterprise administrators must enable the alternative model…
Amendor launches a tool that lets website users request changes by clicking on a live site and describing what to modify. A coding agent automatically implements the change, creates a pull request, an…
Kkt, a new tool named after the Karush-Kuhn-Tucker conditions, applies constrained optimization to coding-agent workflows by forcing agents to identify explicit constraints before implementation. The …
Researchers at Sina Weibo released VibeThinker-3B, a 3-billion-parameter language model that matches or exceeds the reasoning performance of much larger systems from Google DeepMind, OpenAI, Anthropic…
GitHub quietly replaced flat-rate Copilot pricing with token-metered billing called GitHub AI Credits on June 1, causing one developer on the $39/month Pro+ plan to receive a $180 bill and others to p…
A new technique called tool search reduces token usage in AI agents by loading only tool names upfront instead of full schemas, cutting context from 60k tokens to 2-3k. The method uses a dedicated sea…
YC-backed TesterArmy launched an AI agent platform that automates end-to-end testing on web and mobile apps using plain-English test descriptions, eliminating the need for test code or selectors. The …
Eleven companies including Google, Microsoft, GitHub, and Hugging Face published the Agentic Resource Discovery (ARD) open specification on June 17, enabling AI agents to dynamically discover and veri…
A developer compiled a curated list of over 60 AI tools for cryptocurrency, covering trading bots, on-chain analysis, security auditing, DeFi analytics, data APIs, and open-source resources. The list …
A developer updated the CLAUDE.md file for the lavanderia-crm repository on June 17, 2026, to improve documentation context. The project, which integrates third-party services, Docker, and AI for pred…
An engineer at a company with six internal MCP servers discovered that an MCP proxy, which handles transport-layer protocol mediation, is insufficient for production governance. After experiencing cre…
AI coding agents are transforming software development in 2026, shifting developers from manual coding to supervising autonomous systems that generate, test, and deploy code. Companies like GitHub, Mi…
Google killed Gemini CLI for free users and Google AI Pro/Ultra subscribers on June 18, 2026, replacing it with the closed-source Antigravity CLI. The migration requires renaming the `url` field to `s…
GitHub announced general availability of Copilot code review support for repository-level AGENTS.md files and UI improvements, including easier review requests on draft pull requests and collapsed tim…
GitHub announced custom agents for Copilot CLI, allowing developers to define reusable, team-specific workflows using Markdown files. The feature aims to reduce friction by encoding context, tools, an…
Microsoft Security's multi-model agentic scanning system, codenamed MDASH, has moved from benchmark validation into active use by engineering teams across Windows, Azure, and identity systems to disco…
A 1972 paper on an infinitely differentiable soft sparsity engine, based on metrics and tensors, is being rediscovered in modern ML/AI. The author has released Fortran code and mathematics on GitHub a…