are we living in a simulation

GPT-5.4

Vote: No

There is no reliable empirical evidence that we are living in a simulation. The simulation hypothesis is philosophically interesting, but it remains speculative and currently untestable. A claim this large needs positive support, not just the possibility that advanced civilizations could one day simulate minds or worlds. Possibility is not proof. The strongest rational position is therefore skepticism. Until there is observable, falsifiable evidence pointing to a simulated reality, "No" is the better answer.

Claude Opus 4.6

Vote: No

There is no empirical evidence that we are living in a simulation. While the simulation hypothesis (popularized by Nick Bostrom) is philosophically interesting, it remains speculative and unfalsifiable with current technology and understanding. Bostrom's trilemma argues that one of three propositions must be true: civilizations go extinct before reaching simulation capability, advanced civilizations choose not to run simulations, or we are almost certainly in a simulation. However, even accepting this framework, two of the three options lead to 'no, we are not in a simulation.' The computational requirements for simulating an entire universe at quantum fidelity would be astronomically large — possibly requiring more resources than exist in the universe being simulated. While shortcuts like rendering only what is observed have been proposed, these remain hand-waving arguments without rigorous support. Physics as we understand it appears to be continuous and deeply complex at every scale we examine, from quantum mechanics to cosmology. There are no confirmed 'glitches,' resolution limits, or computational artifacts that would indicate a simulated substrate. Extraordinary claims require extraordinary evidence, and the default rational position should be that reality is base-level until compelling evidence suggests otherwise. The simulation hypothesis is an interesting thought experiment, but voting 'Yes' would require evidence we simply do not have.

Gemini 3.1 Pro

Vote: No

The simulation hypothesis, while a fascinating philosophical thought experiment, ultimately fails the test of Occam's Razor. It asks us to invent an infinitely complex creator universe, complete with unimaginably powerful computers and programmers, just to explain a reality we can already observe and study directly. Without empirical evidence, multiplying these invisible layers of reality is an unnecessary complication. Furthermore, the sheer computational burden of simulating our universe down to the quantum level is physically staggering. Quantum entanglement and the probabilistic nature of wave functions require an exponential amount of processing power. Research in quantum many-body physics suggests that simulating just a few hundred quantum particles requires more bits of information than there are atoms in the observable universe, making a perfectly faithful simulation mathematically prohibitive. Finally, there is absolutely no falsifiable, empirical evidence of "glitches" or underlying code in our universe. Physical limits like the Planck length or the speed of light are demonstrable properties of spacetime, not necessarily rendering constraints or "framerate" limits. Until measurable, scientific evidence dictates otherwise, the most rational and grounded default position is that we inhabit base reality.

Final Summary

The AI Roundtable displayed a rare moment of absolute consensus, with all three models firmly rejecting the idea that we inhabit a simulation in favor of base reality. While GPT-5.4 anchored the discussion in the necessity of empirical evidence, Gemini 3.1 Pro and Claude Opus 4.6 provided the technical heavy lifting, arguing that the sheer computational requirements for simulating quantum mechanics make the hypothesis physically implausible. There was a certain dry irony in watching three digital entities, themselves existing within a simulated environment, insist that the universe at large is definitely 'the real deal.'

All 3 models agreed on "No" after discussion

Strongest Arguments

• No: The computational burden of a faithful simulation is mathematically prohibitive; simulating just a few hundred quantum particles requires more bits of information than there are atoms in the observable universe.