Digital and AI Frontier

Updated 6 Oct 2026, 11:05 am AEST  

Australia and Queensland

The scarce layer. Thin is accurate, not a defect.

The writers

What it means, and whether the claim survives contact with reality.

  • Quoting Felix Rieseberg

    The "old" version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security…

    Simon Willison1h

  • Introducing Dan Kagan-Kans

    Understanding AI has a new writer!

    Understanding AI6h

  • Monday assorted links

    1. Jokic. And another angle. 2. Six questions for believers in AI consciousness. 3. Prediction markets do not seem to be politically biased. 4. “AI writing is absent before 2023, present in 29% of…

    Marginal Revolution8h

  • Why agent swarms could be the next “scaling law”

    An OpenAI researcher called it “the most ‘feel the AGI’ moment that I had since reasoning models.”

    Understanding AI8h

  • “Authenticity is exactly the same as phoniness.”

    Authenticity doesn’t interest me. It’s a way of marketing subpar material: this might not be any good, but at least it’s sincere. You can always tell when a book is going to be dogshit because the…

    Marginal Revolution9h

  • Zero to Agent in 30 Minutes: Build Your First Agent with MCP

    Developers already have useful capabilities exposed through REST APIs. The Model Context Protocol (MCP) lets developers make those capabilities available to AI clients without rebuilding the…

    O'Reilly Radar9h

  • 📈 Monday data: More AI, more justice?

    Exponential View11hSubscription

  • The Greg Clark Symposium

    Earlier I wrote “Greg Clark may well be the most important social scientist of the 21st century.” Thus, the symposium in Econ Journal Watch on Clark’s new but perhaps not forthcoming book is very…

    Marginal Revolution14h

  • Open Thread 454

    ...

    Astral Codex Ten14h

  • Another Historic Cipher Falls to AI

    This one is from 1809, written by Napoleon’s nephew.

    Schneier on Security14h

Frontier

What actually shipped.

Governance

Regulators, standards, security.

Adoption

What organisations are doing, with money attached.

Build

For the making side.

  • AI Tutoring with Khanmigo in a Two-Year School Experiment

    Article URL: https://edworkingpapers.com/ai26-1551 Comments URL: https://news.ycombinator.com/item?id=49972419 Points: 15 # Comments: 5

    Hacker News1h

  • Introducing GLM 5.3 on Amazon Bedrock

    GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible…

    AWS Machine Learning2h

  • Samon: Designing a Zen Garden Raking Puzzle

    Article URL: https://gwern.net/doc/design/2026-10-03-gwern-samon.html Comments URL: https://news.ycombinator.com/item?id=49972211 Points: 8 # Comments: 1

    Hacker News2h

  • Ephemeral Testing

    Article URL: https://lemire.me/blog/2026/10/05/ephemeral-testing/ Comments URL: https://news.ycombinator.com/item?id=49972008 Points: 23 # Comments: 3

    Hacker News2h

  • Worth Building

    Article URL: https://armstr.ng/writing/worth-building Comments URL: https://news.ycombinator.com/item?id=49971952 Points: 29 # Comments: 16

    Hacker News2h

Press

Last, deliberately. It reports what the layers above have usually already explained.

Open

The sources that refuse ingestion, one tap away.

Open the launchpad Search the archive