Double-blind study of quantum-random LLM token sampling

Raising $20,000active

Seeking funds to formalize our newly-founded open research collective and run first studies investigating the effects of quantum entropy in LLM token sampling.

Donate:Manifund

Seeking funds to formalize our newly-founded open research collective and run first studies investigating the effects of quantum entropy in LLM token sampling.

Donate:Manifund

Project Details

Project summary

We've just established Entropic Science – an open research community studying the role of quantum entropy in the behavior of complex intelligent systems. Our first study target is the source of randomness inside large language models. An LLM chooses each token by sampling from a probability distribution, and that choice is normally settled by a pseudo-random number generator (a deterministic algorithm fixed by its seed). We replace it with a hardware quantum random number generator (QRNG), drawing entropy from physical measurement events, and detect whether true quantum-level randomness changes how the model behaves and how people experience interacting with it.

Why are we doing this?

In each quantum decoherence event, the evolution of a system branches into two distinct futures. Regardless of metaphysical interpretation, a conscious observer can only ever experience a single specific branch. Exactly how the experienced branch is selected remains a mystery (we only know these selections must conform to the Born rule).

One hypothesis, formulated within the context of free will, is that there may exist some mechanism by which observers (in any definition), or living organisms, have some say in how they move through the (perceived or constitutive) branchial space delineated by different possible outcomes of each instance of quantum decoherence.

Current LLMs do not allow for any such branching points. Our quantum-random LLM (QR-LLM) however, provides a token-probability-weighted branching point for each new token sampled (quantum entropy is generated "fresh", just-in-time). This makes them categorically closer to conscious observers or living systems.

Whether this distinction is purely metaphysical or constitutes an observable difference in the behavior of these systems is the open empirical question we're trying to answer with our study.

Experiment design

Our first experiment will put participants in conversation with a modified LLM chatbot, comparing quantum-random token sampling vs. classical deterministic pseudo-random sampling. In a double-blinded and pre-registered study design, we will collect objective measures from the transcripts (if users choose to share them) and subjective ones through a questionnaire curated by expert advisors.

We don't want to pre-suppose the emergence of any specific effects, but since it can be argued that life emerged from the chaotic entropy of constant quantum decoherence events in aqueous environments, and LLMs have also provided a platform for various emergent behaviors in the digital world, it is plausible that their combination might lead to behavioral differences informing the fields of artificial life, AI safety and alignment, and even machine consciousness.

In this exploratory study we are intentionally not presupposing any concrete hypothesis, but we have already put a lot of conceptual and theoretical work into the design of the pipeline from the actual hardware quantum noise to user visible token output, so as to maximally increase the sensitivity of detecting even small biases or correlations that might result in outputs being objectively differentiated from the uniform pseudo-random baseline.

More in-depth information about our community's thesis and mission is available in our Charter.

We have been pre-admitted to the SparkWell program by the Anti Entropy non-profit organization that, subject to us successfully securing funding, would act as our fiscal sponsor and provide us with operations and administrative services and mentorship for up to two years.

What are this project's goals? How will you achieve them?

Strengthen the community's infrastructure and operations
Entropic Science already runs in the open: a public charter, governance, and code of conduct on GitHub, a working quantum-random LLM (QR-LLM) prototype, and a community of more than sixty members on our Discord server. The funding formalizes operations and adds the coordination that keeps the work moving without leaning on volunteer time.
Build the serving stack and the experimental harness
Serving a QR-LLM at the throughput a study needs, without a latency penalty on every token, is a real engineering problem. We will continue development and maintenance of our software layer that injects quantum entropy through per-request control of the sampling stream in the vLLM inference engine, and with enough funds we will also upgrade the necessary high-bandwidth QRNG over low-latency streaming (gRPC server). The research study harness will then randomize the sampling, log transcripts if approved by the user, run the questionnaire, and compile data for the preregistered an

Theory of Impact

If you're building any kind of system, you have a design choice to make: how much error, noise, or randomness you want. And this is a spectrum. If you're aiming for a system with no error and no randomness, you get a kind of mathematical precision tool that's supremely accurate and does exactly what it's meant to do.

In some way, we've come to equate that with the quality of the system itself. We're trying to optimize for efficiency and precision. We always want the perfect, sharp cutting tool that does exactly what we want – determinism.

But I'd argue that if the universe and nature worked that way – if life itself were a system with no errors – there would be no evolution, no progress, not even any fun. Everything would be sterile, stagnant, unchanging. And if some self-replicating system did happen to arise inside that paradigm, it would stay exactly as it was. No mutation, no adaptation, no real progression.

The introduction of randomness, of this entropy, is an essential and crucial aspect of all living systems. Without it, they wouldn't be what they are.

Now, the way we're building AI right now, we're building it in the digital realm. And the digital realm is something we constructed to be the epitome of determinism: no noise, no error. The lengths we go to in order to create that are extraordinary, and the possibilities it opens up are extraordinary too – copying files, a free and open space for computation, simulation, data sharing, preservation.

People

Jáchym Fibír

Team Member

Grants Received– no grants recorded

Add grant

Funding Asks

grantmaking.ai Launch Round

Applied

Minimum

$20,000

Ideal

$100,000

What this ask is

Project summary

Why are we doing this?

Whether this distinction is purely metaphysical or constitutes an observable difference in the behavior of these systems is the open empirical question we're trying to answer with our study.

Experiment design

More in-depth information about our community's thesis and mission is available in our Charter.

What are this project's goals? How will you achieve them?

Strengthen the community's infrastructure and operations
Entropic Science already runs in the open: a public charter, governance, and code of conduct on GitHub, a working quantum-random LLM (QR-LLM) prototype, and a community of more than sixty members on our Discord server. The funding formalizes operations and adds the coordination that keeps the work moving without leaning on volunteer time.
Build the serving stack and the experimental harness
Serving a QR-LLM at the throughput a study needs, without a latency penalty on every token, is a real engineering problem. We will continue development and maintenance of our software layer that injects quantum entropy through per-request control of the sampling stream in the vLLM inference engine, and with enough funds we will also upgrade the necessary high-bandwidth QRNG over low-latency streaming (gRPC server). The research study harness will then randomize the sampling, log transcripts if approved by the user, run the questionnaire, and compile data for the preregistered an

How the money will be spent

Because we failed to raise any money on Manifund, last week I bought a gamer-hybrid server (notably connecting 4x 5060Ti 16GB + 2x Crypta Labs Dragonfly QRNGs) allowing me to serve the 30B-class dense models with quantum-random sampling 50+ tok/s, for $5.5k. I'm just saying that because I'm proud of it. I don't want money for that. I want money for social media recruiting people for the study, paying contributors in our community, maybe some expert to help with the study design. Probably I'll do a raffle to win some cash prize for anyone that goes through the study and fills out all the questionnaires. I will find a way to push through, making some money along the way to fund this, but it will be slow. The opportunity here is to accelerate this 10x, with relatively small amount of money.

Discussion

No comments yet. Be the first to share your thoughts.