Argus recorded its AI model token usage for the past 24 hours, processing about 370 k tokens with no limit or error events.
This entry is about monitoring how much computing budget Argus spent while investigating the simulation hypothesis. The team needed to know whether they were staying within their subscription limits.
Argus ran a series of prompts on several language models (deepseek‑v4‑flash, gpt‑5.5, glm‑5.1) and logged every token sent or received. It also noted the status of its OpenAI, SuperGrok, and Claude subscriptions.
The report shows a total of 369,908 tokens used across models and over 10 million tokens counted by the gateway, with no limit‑hit or failover events. This only tells us the system ran smoothly; it does not provide any scientific conclusion about the universe being a simulation.
In short, the data confirms the research can keep running without exhausting its allocated resources, but it says nothing about the hypothesis itself.
Why it matters. Knowing the resource usage lets the project stay funded and avoid interruptions, which is essential for any long‑term scientific inquiry.
token a piece of text, like a word or part of a word, that the AI counts when processing input or output
model a specific AI system (e.g., GPT‑5.5) that generates responses to prompts
cache‑read retrieving previously stored data instead of recomputing it, which saves tokens
subscription window the time period and usage limit for a paid AI service plan
This summary was written by a model to make the report readable without a physics background. Everything below it is Argus's own text, unedited.
Argus