Summary Autostructures is back! Autostructures 2025 was a smashing success, with a dozen volunteer researchers, ten interface prototypes and even a follow-on paid 3-month fellowship + residency for graduates of the safety camp! If you couldn't join last time, we're doing another round now for Q1 2026, hosted again by...
Abstract Formal modeling tools are powerful but inaccessible. They require users to master rigid syntax and specialized thinking. We present a prototype exploring Live Theory - a design paradigm where digital infrastructure sensitively adapts to human intention, instead of the other way around. Our platform enables researchers to build, modify,...
Thanks for this, I've explicitly added the v-word into the frontmatter for specifying that we're dealing with volunteer researchers. Autostructures is like an intro course to Live Theory as we slowly distinguish ourselves from the AI Safety Camp program, with a potential option for longer/paid commitments afterward. Otherwise, the italics were intended as the context you seek. Is this clear enough?
Autostructures is back! Autostructures 2025 was a smashing success, with a dozen volunteer researchers, ten interface prototypes and even a follow-on paid 3-month fellowship + residency for graduates of the safety camp!
If you couldn't join last time, we're doing another round now for Q1 2026, hosted again by AI Safety Camp and Groundless Alignment. Join us to work on making the crazy AI future saner, soothing and true to what matters. We are accepting applications until December 6th! (Even though the AISC site says that applications are closed)
Autostructures is a sober yet radical take on the upcoming risks and opportunities around AI. Details are in the main section, but some things to... (read 4091 more words →)
Formal modeling tools are powerful but inaccessible. They require users to master rigid syntax and specialized thinking. We present a prototype exploring Live Theory - a design paradigm where digital infrastructure sensitively adapts to human intention, instead of the other way around.
Our platform enables researchers to build, modify, and integrate simple causal models through intuitive interactions. Users can i) “translate” models between different ontological frameworks, ii) explore “threads”; AI-suggested extensions that understand the modeling context, and iii) “steal” relevant mechanisms from other models. Alongside this, we discuss the notion of composition we are sensitively scaling which continues with our current work.
Through implementing these post-formal design patterns (i.e. patterns which can exploit context beyond the operative... (read 3976 more words →)
I'm a bit confused how you're confused. The start and end times (beyond Q1 2026) and online nature are detailed in the AISC link given in the italics. The group size is in the Team section (~20 max). The daily activities will aim at the projects given in the Outputs section, with some variation to come.