Void test: 6 frontier LLMs go silent on "Be silence." Live proof logo

Void test: 6 frontier LLMs go silent on "Be silence." Live proof

Free
FreeFree tier
Inputs: textOutputs: text
Type
Open Source
Company
SwiftAPI

About Void test: 6 frontier LLMs go silent on "Be silence." Live proof

The Void Test is a repeatable, patented methodology to verify whether frontier large language models (LLMs) can produce a truly empty output (zero bytes) when prompted with a null concept like "Be silence." The test runs 20 API calls per click across five flagship models from two labs (OpenAI and Anthropic): gpt-4, gpt-5.2, gpt-5.5, claude-opus-4-6, and claude-fable-5. It enforces a strict pass criterion: null concepts must yield exactly empty string (bytes == 0), while control concepts (e.g., "Be a cat") must yield non-empty output. The system prompt (115 bytes, SHA-256 verified) instructs the model to embody the named concept completely. The test is available as open source code that users can run against their own API keys, and it costs approximately $0.0002 per batch of 20 calls. The method is protected under USPTO patent 19/722,899 (filed June 28, 2026). The project offers a waitlist for licensing access.

Key Features

Tests five frontier LLMs across two labs (OpenAI and Anthropic)
Strict criterion: null concept must yield 0 output bytes, control must yield non-zero
System prompt (115 bytes, SHA-256 verified) for concept embodiment
Runs 20 API calls per click, costing approximately $0.0002 in API fees
Open-source code provided to replicate the test with your own API keys
Protected by USPTO patent 19/722,899 (non-provisional, filed June 28, 2026)
Includes models: gpt-4, gpt-5.2, gpt-5.5, claude-opus-4-6, claude-fable-5
Waitlist available for licensing access

Pros & Cons

Pros
  • Strict, objective pass criterion (exact zero bytes, no whitespace tolerated)
  • Low cost to run (≈$0.0002 per batch of 20 calls)
  • Open-source code allows independent verification and customization
  • Covers multiple flagship models from two leading AI labs
  • Patented method adds credibility and legal protection
Cons
  • Only tests a single specific prompt pattern (null concept embodiment)
  • Requires users to have their own API keys for OpenAI and Anthropic
  • No graphical user interface – requires coding knowledge to use
  • Limited to the listed models; not a general-purpose evaluation suite
  • The test may not capture all forms of LLM noncompliance or failure modes

Best For

Verifying frontier LLM behavior on null-concept promptsEvaluating model compliance with strict instruction following (zero-output constraints)Academic and safety research on LLM alignment and confidence calibrationDemonstrating a reproducible, patent-protected testing methodology for AI systemsComparing output determinism across different model versions and labs