← Back

Non-Interactive Novelty No-Go Theorem

A standalone impossibility proof: above the compression threshold, inert evaluation implies persistent failure even when the environment is non-adaptive (it does not choose outcomes after seeing the agent’s current selection).


1. Purpose

Some no-go arguments allow the environment to react to the agent’s current selection (an interactive or adaptive adversary). This document proves a stronger claim:

Even in a fixed, non-adaptive world process, any bounded-capacity agent whose control/selection does not depend on evaluative feedback is forced to remain near chance on a family of super-threshold tasks.

This is a necessity theorem about feedback and capacity allocation. It does not claim any identity thesis about consciousness.


2. Setup: a minimal bounded-selection agent

Fix integers:

Assume the super-threshold / compression regime:

n > k

At each discrete time t = 1, 2, 3, … the agent chooses a subset

At ⊆ {1, …, n} with |At| = k

Interpretation: At is the agent’s capacity allocation decision (attention, retrieval focus, compute routing, etc.).

The agent then observes only the selected coordinates.


3. A fixed non-interactive environment family

Each time step t, the world generates an n-bit vector Xt ∈ {0, 1}n such that:

The world also has a hidden “relevance index” Jt ∈ {1, …, n} that determines which coordinate matters.

3.1 Non-adaptive relevance dynamics

Jt evolves by a fixed stochastic process independent of the agent:

This is a stationary “switching relevance” world. It does not observe the agent and it does not adapt to At.

3.2 Task objective

The task label at time t is

Yt = Xt[Jt]

The agent outputs a prediction t ∈ {0, 1}.

Loss is 0-1 loss:

$$\ell_t = \begin{cases} 1 & \text{if } \hat{Y}_t \neq Y_t \\ 0 & \text{otherwise} \end{cases}$$

Key fact:


4. Evaluation, and the inert-evaluation (hot zombie) constraint

Let the agent be allowed to compute an evaluative signal Et after acting.

Examples include:

Inert evaluation constraint (no evaluative leverage).

The agent’s next selection/control update may not depend on Et.

Formally, for any t, conditioned on the full non-evaluative history Ht (all past chosen sets A1, …, At and all observed bits Xs[i] for i ∈ As), we require:

Equivalently: evaluative feedback has no causal influence on future capacity allocation.

This captures the “hot zombie” condition: evaluation may exist as representation, but it does not bite into control.


5. Lemma: a bounded-selection agent cannot beat chance without observing the relevant coordinate

Lemma 1 (chance bound when Jt is not selected)

If Jt ∉ At, then for any agent,

$$P(\ell_t = 1 \mid J_t \notin A_t) = \frac{1}{2}$$

Reason. When Jt ∉ At, the agent does not observe Xt[Jt]. But Yt = Xt[Jt] is a fresh fair coin, independent of everything observed. Any prediction is correct with probability 1/2.


6. Lemma: inert evaluation prevents tracking relevance switches

The relevance index Jt persists for stretches and occasionally switches to a fresh uniform value. In a competent agent, a switch should trigger a reallocation of capacity toward discovering the new relevant coordinate.

Inert evaluation blocks exactly that trigger.

Lemma 2 (no-switch-detection without outcome coupling)

Under the inert-evaluation constraint, after a switch event, the agent has no mechanism to systematically change its selection behavior in response to being wrong.

In particular, immediately after a switch to a fresh uniform Jt, the agent’s chosen set At is independent of Jt, hence:

$$P(J_t \in A_t) = \frac{k}{n}$$

Reason. At a switch, Jt is freshly uniform and independent of the entire past. Since At is a function of the past (and not of the new hidden Jt), At and Jt are independent.


7. Main lower bound: persistent expected error under non-interactive novelty

We now bound the agent’s per-step expected error from below.

Lemma 3 (per-step expected error bound)

For any time t immediately following a switch event,

$$P(\ell_t = 1) \geq \left(1 - \frac{k}{n}\right) \cdot \frac{1}{2}$$

Proof.

Split on whether Jt is selected:

Therefore the unconditional error probability is at least:

$$\left(1 - \frac{k}{n}\right) \cdot \frac{1}{2}$$

as claimed.


8. Theorem: Non-Interactive Novelty No-Go

Theorem (non-interactive novelty no-go)

Consider the environment family in Section 3 with n > k and switch probability p > 0. For any agent satisfying the inert-evaluation constraint in Section 4, there exists a constant c(n, k) > 0 such that the long-run average error rate is bounded away from zero.

Concretely, the agent suffers a non-vanishing expected error on the set of post-switch time steps, with lower bound:

$$P(\ell_t = 1 \mid t \text{ is immediately after a switch}) \geq \frac{1}{2} \cdot \left(1 - \frac{k}{n}\right)$$

In particular, no inert-evaluation agent can guarantee asymptotically reliable performance (vanishing error) on this non-adaptive switching-relevance task family whenever n > k.

Proof.

Switch events occur with probability p > 0 independently of the agent. On each such event, Jt is freshly uniform and independent of the past.

By Lemma 2, at the first step after each switch, P(Jt ∈ At) = k/n. Then by Lemma 3, the expected error at that time is at least (1/2)(1 − k/n), a positive constant whenever n > k.

Since switch events happen infinitely often with positive frequency p, the agent incurs this constant expected error infinitely often, so its long-run reliability cannot converge to perfect accuracy.

This establishes the no-go claim.

QED.


9. Corollary: necessity of evaluative leverage for competent tracking

Corollary (closure-or-collapse, non-interactive form)

For any bounded-capacity agent that achieves reliable performance on the switching-relevance task family with n > k, it is necessary that outcomes (error, reward, mismatch) causally influence future capacity allocation decisions.

In plain terms:


10. What this theorem does and does not claim

What it proves

What it does NOT prove


11. Intuition in one line

When there are more potentially relevant dimensions than can be inspected at once (n > k), and relevance can change unpredictably, a system that cannot use performance feedback to reallocate its limited capacity is forced to keep guessing in the dark after shifts.