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

Recent

• Automated alignment research needs a better plan than 'Stop if we catch them scheming'

  My PIBBSS Symposium talk from September 2025, with the deck and the full transcript, on why the dual-use worry is overblown.

  24 Sep 202536 min readListen, 63 min◆◆◆

• Fooled by Vast Knowledge

  Models look like they generalise because the training data is vast enough to hide the difference between interpolation and extrapolation. I think that confusion is leading safety research astray.

  19 May 20266 min readListen, 9 min◆◆◆

• Difficulties in Building an AI Safety Startup

  Guardrails, evals, RL environments, control infrastructure. I work through each one and keep landing in the same place, too far from what happens inside a frontier lab.

  9 Jan 20263 min readListen, 6 min◆◆◇

• Gaining clarity on Automated Alignment Research

  Four different things get conflated in the phrase automated alignment research, and the crux is whether applying techniques we already have is a short step from inventing a new paradigm.

  9 Jan 20264 min readListen, 6 min◆◆◇

• 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.

  8 Aug 202511 min readListen, 20 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.

  30 Dec 20222 min readListen, 3 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.

  5 Dec 202210 min readListen, 24 min◆◆◇

Everything, by year, in the archive