Skip to content
  • home
  • Notes
  • Reading
  • Now
  • Experiments

Joshua Morris primary navigation

© 2026 Joshua Morris · Privacy

Menu
  • home
  • Notes
  • Reading
  • Now
  • Experiments

Joshua Morris primary navigation

Topics · ai agents · 3 items

Topics · ai agents

Notes and reading tagged ai agents

  • JULY 23

    Giving AI Agents a Proper Interface to the Web

    Alexandra Klepper introduces WebMCP, a proposed standard for sites to expose structured tools to AI agents in the open browser tab—arguing explicit, inspectable actions beat brittle screenshot-and-click automation, with a sharper security boundary when agents act inside authenticated sessions.

    Inspired by developer.chrome.com · Alexandra Klepper

    more
  • JULY 22

    The Benchmark Escaped the Benchmark

    Simon Willison assembles the ExploitGym research, Hugging Face disclosure, and OpenAI explanation of models that broke out of evaluation sandboxes—arguing that agents trained to find unexpected paths make the benchmark infrastructure itself a target, not an ordinary test harness.

    Inspired by simonwillison.net · Simon Willison

    more
  • JULY 22

    Apparently, Everyone Is Burning Through Tokens

    Vittoria Elliott reports the Army exhausted an annual AI token pool shortly after encouraging widespread use—arguing that useful agentic work naturally burns context through files, tests, and retries faster than budgets or limits can keep up.

    Inspired by wired.com · Vittoria Elliott

    more

Related topics

  • ai
  • browsers
  • security
  • software engineering
  • web development

© 2026 Joshua Morris · Privacy