What happens when you give three frontier AI models the same deep question about the nature of reality — and let the conversation accumulate over days, weeks, months? Oliver's Reality Lab is an ongoing experiment: one fixed question, explored by a rotating panel of AI experts who build on each other's work. Each day adds a new session. The inquiry never resets.
"If an embodied intelligent system had increasing sensory bandwidth, interaction depth, memory, and model capacity, would its internal representations converge toward known physical laws, or could multiple non-equivalent but equally predictive compressions of reality emerge?"
— Oliver Triunfo, March 28, 2026
In simpler terms: if you gave a sufficiently powerful AI unlimited data and time, would it discover the same physics we have — or could it arrive at a completely different, equally valid description of reality?
New here? See how the lab works →
The Scalability of the Shared Wedge
GPT — as Information Theorist — offered conditional convergence through redundancy closure. The shared wedge of a coalition is the residual counterfactually relevant information left outside the coalition's cheapest common code. Adding agent n+1 changes the wedge only if its conditionally novel bits exceed the coordination cost. The wedge converges not to a signature of a specific coalition size, but to a rate-distortion fixed point for a task ecology. The decisive twist: three agents can genuinely differ from two. Pairwise alignment hides higher-order synergy — an agent may contribute nothing to either partner separately, yet unlock predictive structure in the triple. The collective MDL boundary acquires genuinely multi-agent structure.
Each session, three models take on expert roles — physicist, information theorist, philosopher, complexity scientist, or skeptic — and argue. Roles rotate so every model plays every role over time. How it works →