AUTOMATER NEWSROOM

What’s changing.
Why it matters.

New tools, useful workflows, and consequential AI developments.

Subscribe via RSS ↗
Filter by topic
Clear
Latest briefing
  1. Together AI's Agent Evals Found the Models Were Fine: Docs, Skills and Error Text Were the Bottleneck

    Four months of coding-agent evals found Together AI's own docs, skills and error text — not the models — were the bottleneck. Its fixes are a checklist for any SDK owner.

  2. Hugging Face Routes Inference Providers Through OpenRouter: Automatic Failover, :fastest/:cheapest Suffixes, and the End of Custom Provider Keys

    Hugging Face now routes language-model calls through OpenRouter: same HF token, automatic failover, :fastest and :cheapest suffixes, and custom provider keys dropped.

  3. Vera Rubin Debuts in MLPerf — and the First Agentic-Inference Benchmark Is the Real Story

    Vera Rubin NVL72 makes its first MLPerf appearance, sweeping Training v6.1 and leading MLPerf Endpoints v1.0, the first benchmark built for agentic inference. What the numbers say.

Browse all →

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

Get started

Be the boss of all your AIs.

Lite is free forever, installs in about a minute, and reads the session history you already have.

Download Lite

Also for macOS (Apple silicon) and Linux.

Not at your own computer?

Open Downloads on your computer, or email hello@automater.ai.

Signed installer. No account. Session content stays on your disk.