Anthropic released Claude Opus 4.8 on Thursday, a large language model the company says is roughly four times less likely than its predecessor to allow flaws in code to pass unremarked. The new model …
Anthropic launched dynamic workflows for Claude Code on May 28, 2026, enabling the AI assistant to write orchestration scripts that run tens to hundreds of parallel subagents in a single session to ta…
Anthropic released Claude Opus 4.8, an upgraded version of its flagship AI model, featuring improvements across coding, reasoning, and agentic benchmarks. The new model launches with user-controlled e…
Cord has launched a free, open-source platform that enables developers to run parallel AI coding sessions with Claude Code or OpenCode directly within Slack. The tool allows users to spin up full deve…
Microsoft plans to release a new AI coding model at its Build developer conference next week, according to The Information, as the company seeks to reclaim its position in the competitive AI coding to…
Microsoft told its engineering teams to reduce usage of Claude Code after the AI coding agent's monthly bill exceeded what budget owners were willing to approve. The company, which owns a stake in Ope…
A survey of 1,260 quantitative social scientists fielded in early 2026 found that 81% have used AI chatbots in research, but only 20% have adopted coding agents that autonomously write and execute ana…
Claude Code desktop app user and newsletter author Daniel used the AI tool to create a sponsorship landing page, replacing a Notion page that previously housed the information. The project demonstrate…
Researchers at HKUDS Lab released CLI-Anything, a system that generates command-line interfaces for any software, enabling AI agents to control GUI-only applications like Blender, GIMP, and LibreOffic…
Coding agents achieved product-market fit in April 2026, as evidenced by Anthropic approaching its first profitable quarter and OpenAI locking all enterprise customers into full API pricing. The shift…
A developer spent $47.30 total in API costs over six weeks using Aider, an open-source AI pair programming tool that works with any LLM and treats git as its core operating system. The tool, which pre…
A developer has created a Markdown file called "agents.md" that teaches AI coding agents how to work on a specific project, solving the problem of AI-generated code not matching a developer's style or…
A developer has released Claude Code Workflow (CCW), a generator that creates linear Spec-Driven Development workflow plugins for Claude Code from a single YAML configuration file. The tool automatica…
A developer discovered that their MCP server for Safari browser control could silently disappear from an AI agent's tool catalog mid-conversation due to a 30-second initialization timeout. The `safari…
A developer released a set of AI agents as markdown files that implement UK Government Digital and Data Profession Capability Framework roles and skills. The agents, designed for multi-agent software …
NVIDIA Vice President Bryan Catanzaro stated in April 2026 that AI compute costs now exceed employee payroll costs, a warning most enterprises ignored while focusing on "tokenmaxxing." Microsoft cance…
Uber's engineering teams reported that 25% of all code commits in Q1 2026 came through Claude Code, marking a shift from pilot programs to regular production use at one of the largest multi-service or…
Blogger Ian Welsh reported switching from Claude to DeepSeek V4 after finding that his monthly AI costs dropped from $3,000-$5,000 to roughly $5 per week. Welsh cited DeepSeek's pricing of $0.28 input…
XAI released version 0.2.3 of its Grok Build coding agent on May 27, 2026, adding a /remember command that allows developers to save notes and project context that persist across coding sessions. The …
A new open-source coding agent, mini-SWE-agent, achieves up to 74% on the SWE-bench verified benchmark using just 100 lines of Python code. Developed by the Princeton and Stanford team behind SWE-benc…