Skip to content
Samuel McDonnell
  • Projects
  • Writing
  • About

Writing

Notes on evaluation harnesses, reliability, and the measurements that show whether a change to an AI system actually helped.

  • 2026-07-28

    My Thoughts on Graph Engineering

    Four frameworks converged on graph execution years before "graph engineering" existed as a term — and their own engineers argued against the diagram.

  • 2026-07-21

    The American Economy Is Leveraged to a Leaderboard

    Kimi K3 didn't erase America's AI lead. It priced how much of current US growth rests on seven stocks and one story holding.

  • 2026-06-22

    Google Built a Faster AI by Making It Worse. When Is That a Good Trade?

    DiffusionGemma, dFlash and TurboQuant get sold as one 6x speedup. They're three different tradeoffs, and collapsing them hides the one that matters.

  • 2026-06-15

    My Thoughts on Loop Engineering

    Loop engineering is a new label for an old bottleneck. The generator was never the hard part to build — the verifier always was.

  • 2026-06-09

    DeepSeek Killed the Commodity Tier, Not the Frontier

    Cheap open-weight models killed single-shot chat pricing. Multi-step agentic reliability is a different market, priced on different logic.

  • 2026-06-08

    Claude Code Dynamic Workflows: What's Actually Changed

    What Dynamic Workflows actually changes under the hood, what it costs in tokens, and the tasks it's the wrong tool for.

Samuel McDonnell — 2026

  • GitHub
  • X
  • Email