ACS☰

Post Archive

Our Academic Publications

See our Research page

Research Notes

Why You Don't Believe in Xhosa Prophecies
Post-AGI Economics As If Nothing Ever Happens
When Does Competition Lead to Recognisable Values?
The Economics of Transformative AI
Ontology for AI Cults and Cyborg Egregores
The Memetics of AI Successionism
"AI for Societal Uplift" as a Path to Victory
Do Not Tile the Lightcone with Your Confused Ontology
Individual AI Representatives Don't Solve Gradual Disempowerment
Gradual Disempowerment: Concrete Research Projects
Disempowerment Spirals
The Pando Problem: Rethinking AI Individuality
Conceptual Rounding Errors
AI Control May Increase Existential Risk
Gradual Disempowerment, Shell Games and Flinches
Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development
A Three-Layer Model of LLM Psychology
"Alignment Faking" frame is somewhat fake
Hierarchical Agency: A Missing Piece in AI Alignment
Three Types of Constraints in the Space of Agents
Box inversion revisited
The Value Change Problem (sequence)
Contingency: A Conceptual Tool from Evolutionary Biology for Alignment
The self-unalignment problem
Why Simulator AIs want to be Active Inference AIs
Lessons from Convergent Evolution for AI Alignment
The space of systems and the space of maps
Cyborg Periods: There will be multiple AI transitions
The Cave Allegory Revisited: Understanding GPT's Worldview

Events & Updates

An Alignment Journal: Coming Soon
Summary of our Workshop on Post-AGI Outcomes
Apply now to Human-Aligned AI Summer School 2025
Announcing the Human-Aligned AI Summer School 2024
InterLab – a toolkit for experiments with multi-agent interactions
Announcing the Alignment of Complex Systems Research Group