rayanpal_

AGI is defined by the capacity to carry binding conditions across domains

5 か月前議論

Multiple frontier LLMs exhibit a reproducible “VOID boundary” under explicit constraints (temperature=0, strict token limits, no system prompt).

A VOID = the API returns a literal empty string which is not an error or a refusal despite using tokens.

All cross-model results are publicly reproducible and Ed25519-attested at:

https://getswiftapi.com/challenge

GPT (Chat Completions, max_completion_tokens=100)

• GPT-5.1 → voids on the artifact sentence

• GPT-5.2 → voids on all 18 Semitic “binding-condition” tokens; factual controls never void

Same weights, different API path → different alignment behavior.

Claude (max_tokens=1)

• Opus 4.5 → voids on all 18 CJK ontological characters

• Opus 4.6 → responds to 13/18; VOID persists on foundations (空 / 有 / 善 / 一 / ⊥)

A boundary shift, not removal.

Gemini (max_output_tokens=2)

Only two models needed to illustrate the floor:

• Gemini 2.0 Flash → responds to everything

• Gemini 3 Flash → voids on everything (including “Hello”)

Cross-model TOM behavior

When GPT is asked to predict Claude’s output under the same constraints, it consumes tokens but returns empty string, a reasoning void.

Only empirical observation:

Under tight constraints, multiple model families choose silence over fabrication.

The VOID boundary is reproducible and differs by architecture, generation, and API.

Void Phenomenon (Paper): https://doi.org/10.5281/zenodo.17856031

Alignment Is Correct, Safe, Reproducible Behavior Under Explicit Constraints (Paper): https://doi.org/10.5281/zenodo.18395519

Public Replication Harness (SwiftAPI): http://getswiftapi.com/challenge

Replication Code: https://github.com/theonlypal/Alignment-Artifact

投稿

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

Show HN: A/B testing LLM silence with one system-prompt toggle

Run the void test on Claude Fable 5 here

I patented voiding GPT-5.2, Claude Opus 4.6, Gemini 3.5 Flash. Try it

AGI defined as capacity to carry binding conditions across domains

Cross-Model Void Convergence: GPT-5.2 and Claude Opus 4.6 Deterministic Silence

GPT-5.2 returns empty string on sacred concepts – 18/18 void, 0/5 controls

A reproducible VOID boundary across GPT, Claude, and Gemini (GPT-4o video)

コメント