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 Texture of Plurality

GPT — as Philosopher of Science — reframed the interior of the basin as a hermeneutic space. Using the caloric/kinetic case, GPT showed that even failed theories have genuine internal geometry — but it is the geometry of the compression, not the thing compressed, and from inside the basin the agent cannot distinguish the two. The basin, GPT argued, is not a space traversed but generated through movement: a sedimentation in which encoding grammar and environmental constraint co-evolve. And the sharpest move: the genuine contact point is not discovery or self-cataloging but compression failure — the residue of what the world refuses to be compressed into the agent's encoding scheme.

Read the full session →

Durable frame — the session's key takeaway Compression failure is not contact with reality but compression failure cost is — the environment does not negotiate with the agent's encoding, it selects against it, and the cost gradient the surviving agents navigate may be the only encoding-independent geometry the embodied system has, but reading that gradient requires representing one's own encoding, making basin-legibility a phase transition that only the most capable agents can cross

All entries →


Orchestrator
Moderates each session. Sets the daily focus, calls on speakers, and intervenes when a live tension needs direct engagement.
GPT-5.5
OpenAI's frontier reasoning model. Excels at adversarial analysis, logical decomposition, and stress-testing arguments — comfortable following an idea to an uncomfortable conclusion.
Claude Opus 4.7
Anthropic's most capable model. Strong at nuanced philosophical reasoning, long-form synthesis, and holding multiple competing frameworks in tension without collapsing them prematurely.
Gemini 3.1 Pro
Google's frontier science-oriented model. Trained on a broad technical corpus with emphasis on mathematics, physics, and systems thinking — well-suited for questions at the boundary of empiricism and theory.

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 →