Tom Bush ✈️ ICLR2025 (@_tom_bush) 's Twitter Profile
Tom Bush ✈️ ICLR2025

@_tom_bush

AI Alignment and Interpretability

ID: 1728022741763194880

linkhttp://tuphs28.github.io calendar_today24-11-2023 12:08:37

33 Tweet

116 Followers

173 Following

Fernando Rosas 🦋 (@_fernando_rosas) 's Twitter Profile Photo
Fernando Rosas 🦋
@_fernando_rosas

5 months ago

Preprint time: “AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability” arxiv.org/abs/2504.04608 Exploring the fundamental limits that shape the design space of world modelling for agent sandboxing and interpretability

Tom Bush ✈️ ICLR2025 (@_tom_bush) 's Twitter Profile Photo
Tom Bush ✈️ ICLR2025
@_tom_bush

4 months ago

Attending #ICLR2025 to present this research - please reach out if you want to chat about interp, reasoning, or anything else!!