AUTOMATER NEWSROOM

What’s changing.
Why it matters.

New tools, useful workflows, and consequential AI developments.

Subscribe via RSS ↗

Latest briefing

Oct 6, 2026, 9:32 PM EDT
GitHub Actions Degraded for Four Hours: 47% of Workflow Runs Failed at Peak
GitHub's initial report quantifies a four-hour Actions and hosted-runner outage: at peak, 47% of hosted-runner workflow runs failed and 71.9% of hosted jobs missed the five-minute start mark.
Oct 6, 2026, 8:28 PM EDT
Claude Code 2.1.290 Adds Advisor Data and Clearer Plugin Hook Validation
Claude Code v2.1.290 adds advisor tool records, identifies subagent permission checks, exposes required-approval metadata, and reports gating hooks with .catch handlers.
Oct 6, 2026, 6:50 PM EDT
Claude Code v2.1.292 Adds Sub-Agent Effort Control, Mod Autocomplete, and One-Step Marketplace Installs
Anthropic ships Claude Code v2.1.292 with per-sub-agent effort budgets, a prompt.autocomplete hook for mods and plugins, --marketplace flag on plugin install, prompt caching for mods, workflow agent visibility in hooks, and critical security fixes for sandbox escapes and UNC path bypasses.

Browse all →

Graphic showing Mistral Large 4 Preview with text indicating 1 trillion parameters on Grace Blackwell.

October 6, 2026

Mistral Large 4 Preview Released: 1 Trillion Parameters on Grace Blackwell

Mistral launches the API preview for Mistral Large 4, a 1-trillion parameter multimodal model with strong performance in cybersecurity and agentic coding. Open weights drop soon.

Our AI-assisted editorial method · Explore our in-depth Intel guides