Hello, I'm Jacques. I work on AI alignment.

The transition to advanced AI, and how to make it go well.

Recent

Everything, by year, in the archive

Start here

  • Automating AI Safety: What we can do today

    A concrete list of things to build now so a coding agent can actually run an interpretability experiment, and why the METR slowdown result does not say what people think.

      11 min read  ◆◆◇  Listen, 20 min

  • Foresight for AGI Safety Strategy

    Governance people should be writing the policy document and building the demo for each plausible scenario now, rather than starting the day a minister gives them three months.

      10 min read  ◆◆◇  Listen, 24 min

  • But is it really in Rome? Limitations of the ROME model editing technique

    The ROME edit does not generalise the way you would expect. It runs in one direction only, and cheese and fromage have to be edited separately.

      2 min read  ◆◆◇  Listen, 3 min

Get new posts by email

You get the post itself, not a summary. I send nothing else.

Buttondown opens in a new tab to finish signup. Your place here stays saved.