Limits to Control
Can we keep enough control over AI? If systems are developed to be more and more autonomous, this is no longer a given. It's a hypothesis, calling for serious investigation.
Even alignment relies on control. Researchers build mechanisms to control AI's impacts in line with human values.
So how must a control mechanism operate? What limits its capacity to track and correct all the AI signals/effects? Does it provide enough stability, or give way eventually to runaway impacts?
We explore these questions in a new field: Limits to Control.
About the workshop
This in-person workshop brought together researchers to map the territory of AI control limitations – to understand the dynamics, patterns, and impossibilities of control. Through presentations, whiteboard discussions, and collaborative problem-solving, participants worked to build common knowledge, clarify viable research directions, and formalize this critical research topic.
Dates & location
- Date: Wednesday, June 11 - Friday, June 13, 2025
- Location: University of Louisville, Kentucky, USA (Belknap Academic Building, rooms 427 & 428)
Proceedings
See workshop statement.
Paper publications are pending. See for now:
- Richard Everheart's pre-print "On the Boundaries of Formal Intelligence"
- Remmelt Ellen's essay "Deconfusing AI and Evolution"
Participants
The workshop brought together researchers actively working on the theoretical and practical limits of AI control:
- Prof. Roman Yampolskiy
- Dr. Anders Sandberg
- Thibaud Veron
- Aybars Kocoglu
- Forrest Landry
- Richard Everheart
- Remmelt Ellen
- Will Petillo
Related reading
Writings by workshop participants:
Papers:
- On the Controllability of Artificial Intelligence: An Analysis of Limitations, by Roman Yampolskiy
- AI: Unexplainable, Unpredictable, Uncontrollable, by Roman Yampolskiy
- Impossibility Results in AI, by Roman Yampolskiy
- Richard Everheart's pre-print: "On the Boundaries of Formal Intelligence"
- Remmelt Ellen's essay: "Deconfusing AI and Evolution"
- [Forthcoming paper on control limits] by Anders Sandberg, Aybars Kocoglu, Thibaud Veron
Essays:
- Lenses of Control, by Will Petillo
- The Control Problem: Unsolved or Unsolvable?, by Remmelt Ellen
- Control as a Causative Feedback Process, by Forrest Landry
- An Exploration of AGI Uncontainability, by Forrest Landry
- On Error Detection, by Forrest Landry
Organizing team
This event was hosted by HΩ, and organized by:
- Orpheus Lummis (HΩ)
- Remmelt Ellen
- Thibaud Veron
Contact
For inquiries, please contact Orpheus at o@horizonomega.org.