We are pleased to invite you to the PIBBSS Summer Symposium where the fellows from the ‘23  fellowship program present their work. 

The symposium is taking place online, over several days in the week of September 18th

  • Check out the full program, including brief descriptions for each talk. (You can toggle between the different days.)
  • Register via this link. You will receive an email with the event link which you can use for the entire symposium. You will be able to drop into as few or as many presentations and breakout sessions as you like. 
  • Click here to add the schedule to your google calendar.


PIBBSS is a research initiative aiming  to explore parallels between intelligent behavior in natural and artificial systems, and to leverage these insights towards the goal of building safe and aligned AI. 

During June-August ‘23, we ran the second iteration of our 3-month research fellowship program. The symposium acts as a venue to share research conducted as part of this program. 

About the symposium 

The PIBBSS Summer Symposium is a multi-day event where PIBBSS fellows present their work.  

The event is taking place on the days of Tuesday - Friday, Sept 19th - 22nd, between 18:00-~21:00 CET / 9:00 - 12:00 PT / 12:00 - 15:00 ET.

The event is set it up such that you can easily join whichever talks and breakout sessions you are most interesting in.

The program 

Find a program overview here

Find the full program here, including brief descriptions of each talk. 

On top of the talks, there will also be opportunities to continue the discussion with fellows at the end of each block in speaker-specific breakout rooms.

Talks span a wide range of topics in line with PIBBSS’s research mission. Some representative examples of topics include: 

  • novel avenues for interpretability 
  • naturalistic approaches to understanding the nature and emergence of agency and goal-directed behavior
  • attempts to develop a principled understanding of the dynamics emerging from multi-agent interactions in and across AI/LLM systems
  • analyses of the space of AI risks — from single to multiple agents, from misuse to structural risks, etc.
  • exploration of the potential and limits of existing legal tools for reducing catastrophic risks from AI 
  • ..and more!

The format

The symposium is taking place over the course of four days, in blocks of ~4 fellows. 

Each fellow presents for a total of 30 minutes, including some time for questions. 

At the end of each block, there will be speaker-specific break-out rooms to allow for further questions and discussions.

Example day: 

Day 1Starting time
Speaker 1  18:00 CEST          
Speaker 2  18:30 CEST
Speaker 3  19:00 CEST
Speaker 4  19:30 CEST
Breakout/Discussion Rooms 
with Speakers 1-4 (parallel)     

  20:00 CEST

  - 21:00 CEST

How to engage

Register here to receive a link to the webinar. 

The same link works for the entire symposium. This allows you to tune in for exactly those talks and breakout sessions you’re most interested in!

Find the full program here, including brief descriptions of each talk. (You can toggle between the days to discover the full program.)

If you cannot make it to a talk, worry not! Most talks will be recorded and can later be viewed at the PIBBSS YouTube Page.

Talks (overview)

For a full version of the agenda, including talk descriptions, see here. Times below are in CEST. 

Tuesday, Sep 19th

18:00  —  Auto-Intentional Agency and AI Risk  —  Giles Howdle

18:30  —  Allostasis emergence of auto-intentional agency  —  George Deane

19:00  —  (Basal) Memory and the Cognitive Light Cone of Artificial Systems  —  Urte Laukaityte

19:30  —  Searching For a Science of Abstraction  —  Aysja Johnson

20:00  —  Breakout sessions with each presenter

Wednesday, Sep 20th

18:00  —  Agent, behave! Learning and sustaining social norms as normative equilibria  —  Ninell Oldenburg 

18:30  —  Detecting emergent capabilities in multi-agent AI systems  —  Matthew Lutz

19:00  —  An overview of AI misuse risks (and what to do about them)  —  Sammy Martin

19:30  —  Tort Law as a tool for mitigating catastrophic Risk from Artificial Intelligence  —  Gabriel Weil 

20:00  —  Breakout sessions with each presenter

Thursday, Sep 21st

18:00  —  The role of model degeneracy in the dynamics of SGD  —  Guillaume Corlour

18:30  —  A Geometry Viewpoint for Interpretability  —  Nischal Mainali

19:00  —  Studying Language Model Cognition through Prompt-Engineering Experiments  —  Eleni Angelou

19:30  —  Breakout sessions with each presenter

Friday, Sep 22nd

18:00  —  Beyond vNM: Self-modification and Reflective Stability  —  Cecilia Wood

18:30  —  Constructing Logically Updateless Decision Theory  —  Martín Soto

19:00  —  A Mathematical Model of Deceptive Policy Optimization  —  Tom Ringstrom

19:30  —  Causal approaches to agency and directedness  —  Brady Pelkey

20:00  —  Breakout sessions with each presenter

We are looking forward to seeing you there!

Personal Blog


New Comment
1 comment, sorted by Click to highlight new comments since:

Some talks are visible on YouTube here