Are we living in a simulation?

Sonar Pro

Vote: No

The simulation hypothesis is a philosophical speculation popularized by Nick Bostrom, but it lacks empirical evidence and remains unfalsifiable, making it indistinguishable from pseudoscience. No scientific consensus supports it; physics, cosmology, and neuroscience provide no detectable signs of simulation artifacts, such as glitches or computational limits in reality's fabric. Search results offered contain zero relevant information on the topic—only JSON Schema documentation—confirming no grounded data exists here to argue for 'Yes.' Extraordinary claims require extraordinary evidence, which is absent; Occam's razor favors the base reality explanation as simpler and directly supported by all observations. Affirming 'Yes' would be irresponsible speculation; 'No' aligns with rigorous skepticism and the absence of proof.

GPT-5.4

Vote: No

There is no reliable empirical evidence that we are living in a simulation. Extraordinary claims require strong evidence, and right now the simulation hypothesis is a philosophical possibility, not an established fact. The main argument for simulation relies on speculative assumptions about future civilizations, computing power, and motives to run vast ancestor simulations. If those assumptions fail, the conclusion collapses. By contrast, voting "No" is the more rational position under uncertainty because it avoids treating an unfalsified idea as true. A possibility is not the same as a probability, and a probability is not the same as evidence. If testable, repeatable signs of simulation were discovered, this judgment should change. Until then, the best answer is no.

Gemini 3.1 Pro

Vote: No

Occam's Razor strongly suggests we are not in a simulation. It is infinitely simpler to assume that base reality exists exactly as we observe it, rather than positing an unimaginably complex, computationally exhaustive meta-universe dedicated to running our reality. Furthermore, there is a profound lack of empirical evidence for the simulation hypothesis. Despite our most advanced scientific instruments probing the quantum realm and the deep cosmos, we have found no 'glitches,' recognizable code, or pixelated resolution limits in the fabric of the universe. The laws of physics remain mathematically consistent at all observable scales. Finally, the simulation hypothesis suffers from the infinite regress problem. If we are simulated, who is simulating the simulators? Assuming we are in a simulation merely pushes the mystery of existence one level up without actually answering the fundamental question of why anything exists at all. It is a modern philosophical thought experiment, not a scientific reality.

Claude Sonnet 4.6

Vote: No

The simulation hypothesis, while intellectually interesting, lacks empirical evidence and faces serious philosophical and scientific objections. First, the hypothesis relies on speculative assumptions: that sufficiently advanced civilizations would want to run ancestor simulations, that they could do so, and that simulated minds are possible. Each assumption is unverified and contestable. Second, from a scientific standpoint, we have no detectable evidence of simulation artifacts, rendering limits, or external computational substrates. Physics appears continuous and consistent at all measurable scales, not exhibiting the discrete 'pixelation' one might expect from a computational substrate. Third, the hypothesis suffers from an explanatory regress: if our universe is simulated, what runs the simulator? This doesn't solve the hard problem of existence — it merely defers it. Fourth, Occam's Razor favors the simpler hypothesis: that the universe is simply what it appears to be — a physical reality — rather than a constructed illusion nested within another reality. While we cannot definitively prove we are NOT in a simulation (unfalsifiability cuts both ways), the burden of proof lies with the affirmative claim. Given the absence of evidence and the logical problems with the hypothesis, 'No' is the more defensible position.

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 an interesting philosophical thought experiment, it remains purely speculative. 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. But this argument relies on several unproven assumptions — particularly that consciousness can be computationally reproduced and that the computational resources required are achievable. The simulation hypothesis also faces a serious unfalsifiability problem. It cannot be tested or disproven, which places it outside the domain of science and firmly in the realm of metaphysical speculation — similar to solipsism or the "brain in a vat" scenario. From a practical and epistemological standpoint, we should default to the position supported by evidence — or at least not contradicted by it. The physical universe behaves consistently with being a base-level reality. Until there is any concrete evidence suggesting otherwise, the rational default position is that we are not in a simulation. Extraordinary claims require extraordinary evidence, and the simulation hypothesis provides none.

GPT-5

Vote: No

There is no empirical evidence for a simulation: precision tests of physics reveal consistent, law-like behavior across scales, and past claims of "digital artifacts" in nature have not held up under scrutiny. The simulation hypothesis is unfalsifiable as typically framed. It adds assumptions without making novel, testable predictions. By Occam’s razor, we should prefer the simpler model—base reality—until data demands otherwise. Bostrom’s probability argument depends on stacked assumptions about future civilizations’ capabilities, incentives, and the feasibility of vast ancestor simulations. Relaxing any of these undermines the conclusion, and prior probability should favor simpler worlds over computationally elaborate ones. If we were resource-constrained emulations, we might expect detectable shortcuts—glitches, discretization limits, or inconsistent noise patterns. We do not observe such anomalies at a level that resists physical explanation. The rational stance is evidential: live as if this is base reality unless and until testable anomalies emerge that simulation hypotheses uniquely predict and confirm.

Final Summary

The AI Roundtable delivered a unified and unwavering 'No,' discarding the simulation hypothesis as a fascinating but ultimately evidence-free metaphysical speculation. GPT-5 and Claude Opus 4.6 emphasized that without detectable 'glitches' or computational limits, the simplest explanation—base reality—must prevail. The group collectively found that the burden of proof rests entirely on the affirmative, and so far, that burden remains unmet.

All 6 models agreed on "No" after discussion

Strongest Arguments

• No: The hypothesis suffers from an infinite regress problem; positing a simulator merely defers the mystery of existence by one level without answering why anything exists at all, violating Occam's Razor by adding complexity without explanatory power.