news

2026-10-03 Gemini 4 Argon - Google is back at the top, but you can't use it yet

On 30 September, Google DeepMind announced Gemini 4 Argon, its new frontier model. Demis Hassabis called it "a huge step forward across key capabilities" on X. Koray Kavukcuoglu, who wrote the announcement, says it's already changing how Google works and builds internally.

2026-10-03 OpenClaw 2.0 - easier setup, shared sessions, same security defaults

On Sunday August 30, 2026, the OpenClaw Foundation released OpenClaw 2.0 (officially v2026.8.1). It's the largest OpenClaw release so far by a wide margin: the release notes count 16,977 pull requests, 698 direct commits and 987 contributors. That's roughly half of all the pull requests ever merged

2026-10-04 Astra plans, Luna carries the context - route models by context length

On 16 September, Nate B. Jones posted a trick on X that got about 30K views. He says it saved him over $2K in API costs on a 68-agent build in the Codex harness, over one weekend. His recipe:

2026-10-04 Claude Code Mods - Claude Code is now programmable, and mods aren't sandboxed

"You can now mod Claude Code." @ClaudeDevs posted that on 1 October. Claude Code Mods are out of early access, and they're on by default since v2.1.287.

2026-10-04 Claude Marketplace - Anthropic is building the distribution layer

Anthropic now runs a storefront: the Claude Marketplace, at claude.com/marketplace. The tagline is "Connect your apps, data and tools to Claude", and the page is split into Add, Buy and Scale:

2026-10-04 Claude Opus 5.5 - Ask for a video, get a program you can edit

A few days ago, I wrote about letting Claude Opus 5.5 edit one of my YouTube videos. Three posts from late September show a related pattern: people ask Claude Opus 5.5 for motion graphics, and what they get back is code that renders the video.

2026-10-04 Claude Opus 5.5 - Give it the whole task, keep your hand on the brake

Anthropic published a post on getting the most out of Claude Opus 5.5 in Claude and Claude Code. It reached 229 points on Hacker News on 3 October. I found the comments more useful than the post: people tried the advice on real work and reported what broke.

2026-10-04 Claude effort levels - Draft on low, verify on high

It's tempting to treat the effort setting in Claude Code as a smartness knob: the task feels hard, so you turn it up. After reading Thariq Shihipar's guide and the community numbers, I think that's the wrong mental model, and an expensive one.

2026-10-04 OWASP MCP Security Taxonomy - a common language for MCP risks, still at v0.1

OWASP has a new project for anyone who connects AI agents to tools and data: the MCP Security Taxonomy. Tagline: "A common language for securing agentic AI connections, context, and capability." The repository was created in May 2026, the real content landed on August 27, and the last update is from

2026-10-04 Technical Documentation Skill - stop your coding agent from inventing commands in your docs

I published a new open source AI skill at the end of August and never announced it here. Time to fix that. It's called `technical-documentation`, and it teaches coding agents to write, rewrite and review technical documentation. It works with Claude Code, OpenAI Codex, OpenCode and GitHub Copilot, h

2026-10-04 You Should Know - a second pair of eyes on long Claude Code runs

On 2 October, @ClaudeDevs announced You Should Know, a new built-in plugin for Claude Code. The post passed 1.5 million views. It's a small feature, and it's the first built-in I'd turn on.

2026-10-09 Session Flags - the first Claude Code mod I'm building

Claude Code Mods launched on 1 October, and they're on by default since Claude Code v2.1.287. A mod is a plugin made of JavaScript or TypeScript handlers that run inside Claude Code: it can step into tool calls and prompts, add slash commands and tools, and draw its own panes in the terminal. I wrot