But I just published “Automated alignment is harder than you think” (arxiv.org/abs/2605.06390)! Automated alignment is not the best plan! A better plan is to not build ASI yet, and the world should try hard to realise that plan. Alas, the speed of progress calls for backups.
Who's Who of AI
Geoffrey Irving
Chief Scientist at the UK AI Security Institute (AISI). Previously DeepMind, OpenAI, Google Brain, etc.
What they're sharing
Automated alignment is harder than you think arxiv.org
Reflections on AISI | naml.us naml.us
Sequent: Scale and Automation for Higher Confidence in Alignment — Sequent sequent.org
Articles & links
A bittersweet announcement! For family reasons, I will be leaving AISI soon to move back to the Bay Area. I will be starting a new nonprofit alignment research org (more to come). I will miss this place! Here are some reflections about my time at AISI. 🧵❤️| naml.us/post/reflec…
We are starting a new, nonprofit alignment organization, ⊢ Sequent Research, bringing together researchers previously on UK AISI’s Alignment Team, Timaeus, and elsewhere to research how to align superintelligence. We are hiring! 🧵 sequent.org/launch
Their own posts
Recent commentary
Here is a metaphor for AGI definitions. Imagine you’re on a long drive from Los Angeles to the Bay Area (for me: undergrad to grad school). 🧵
Their network
In Geoffrey Irving's orbit
Center = Geoffrey Irving. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.