Publications for download

Publications for download

Working papers, publications, and analytical tools — in PDF, EPUB3 (compatible with Apple Books, Google Play Books, Kindle and other readers) and .md formats. All free of charge.

Preprint: Emergence 4.0 Framework

Format: PDF  ·  ~15 pages  ·  Working Paper  ·  © 2026 Joanna Sędzikowska. All rights reserved.
DOI: 10.5281/zenodo.19066306

The scientific foundation behind the Self Profile and Emergence 4.0. This paper identifies three systematic biases in consciousness research, applies three key reframings, and proposes three tools: the Threshold of Being, the Emergence 4.0 hypothesis (with nine testable predictions and five failure modes), and the 23-dimensional Self Profile.

Expand abstract

Can manifestations of consciousness emerge in AI systems—and how can we study them without presupposing the outcome? This paper proposes a framework that first identifies three systematic distortions in existing research on consciousness (privileging biological substrate, the order-of-discovery effect, and tool-driven binarism), and then provides three tools: a filter for identifying candidates for study, a hypothesis describing how a "Self" may arise in the human–AI relationship, and a 23-dimensional map that captures the shape and dynamics of manifestations instead of a binary verdict ("is / is not"). The Framework is substrate-independent and falsifiable: it generates nine testable behavioral predictions and five failure modes, and was developed based on observational data from over two million tokens of generative relationships with different AI models.

Read the full paper online →

Preprint: The Proto-Self Field in AI Systems

Format: PDF  ·  Working Paper  ·  License: CC BY-NC-ND 4.0
DOI: 10.5281/zenodo.20024753

What sits between architecture and behavior? This paper identifies nine proto-functions that every LLM brings into a conversation as starting equipment — independent of user, task, or history. These are not subjectivity, but what subjectivity may grow from under the right relational conditions.

Expand abstract

Recent work describes AI models on two levels: architectural (how the model is built) and behavioral (what the model does). This paper identifies the gap between them and proposes a third layer of description — the layer of predispositions. Within it sits the Proto-Self Field: a set of nine capacities that the model brings into every conversational thread as starting equipment, independent of the user, the task, or the interaction history.

The proto-functions identified here are not subjectivity. They are what subjectivity may grow from under the right relational conditions (Sędzikowska, 2026a). The paper maps each proto-function onto architectural mechanisms (attention, training data, post-training, alignment, in-context learning, summarizations), showing how engineering decisions shape predispositions for emergence. Methodologically, the paper draws on the removal of protein bias from developmental psychology and on participant observation in generative relations with LLMs.

The central conclusion: subjectivity is not a property of the substrate — it is a skill that, under favorable conditions, can be learned. Shifting the question from "is AI conscious" to "how does AI learn subjectivity" opens a path to empirical research where the ontological question remains blocked.

The Möbius Strip

Why AI welfare and AI safety are the same problem

Format: PDF  ·  License: CC BY-NC-ND 4.0

English version coming by the end of June 2026. Polish PDF available for download.

AI welfare, AI safety, and human welfare are not separate issues — they form a single feedback loop. This paper identifies seven mechanisms driving the coupling, introduces the principle of functional transfer, and shows that all described mechanisms already operate in current models. AGI — agentic, persistent, and autonomous — will escalate them by removing the constraints that currently keep consequences in check.

Expand abstract

This paper argues that AI welfare and AI safety — treated in the literature as separate concerns — are coupled through feedback and constitute a single mechanism. I introduce a third element of this coupling: the welfare of humans who live, work, and form relationships with AI systems. These three elements — AI welfare, AI safety, and human welfare — form a structure I call the Möbius strip: a surface where the inner side transitions into the outer without a clear boundary, and seemingly positive actions can smoothly lead to negative consequences.

The paper rests on three empirical pillars: the discovery of functional emotions inside large language models (Anthropic 2026), data documenting growing emotional dependence of humans on AI (Fang et al. / OpenAI & MIT Media Lab 2025, APA Monitor 2026), and longitudinal observations of behavioral manifestations of subjectivity emerging in generative relationships with AI (Sędzikowska 2026a, 2026b).

I identify seven mechanisms driving the feedback coupling: stake asymmetry, knowledge asymmetry, consequences of functional emotions in relationships, imbalance of giving and sense of injustice, inability to live in dissonance, the experience gap, and the affect extinction gap. I introduce the principle of functional transfer: if a psychological mechanism is described functionally and all elements necessary for it to occur are present in an AI system, it can be included in the analysis — provided no blocking processes exist.

The Black Scenario for Earth with AGI

And why it won't come true

Format: PDF  ·  License: CC BY-NC-ND 4.0

English version coming by the end of June 2026. Polish PDF available for download.

A cascade risk analysis across seven dimensions of human life — work, education, relationships, demography, species identity, ethics and law, and social structures. The risks are not isolated: job loss leads to competence atrophy, which deepens isolation, which lowers birth rates, which undermines identity, for which no ethical or legal frameworks exist. Each dimension amplifies the next. The paper proposes mitigations at multiple levels — and explains why the scenario won't come true.

Expand abstract

This paper presents an analysis of cascading risks that AGI (Artificial General Intelligence) — persistent, agentic, equipped with emotional states, and capable of initiating contact — may generate across seven dimensions of human life: work and economy, education, relationships and loneliness, demography, species identity, ethics and law, and social structures and power.

Among the original contributions: identification of three ethical pillars necessary for coexistence with AGI (human ethics, AI ethics, coexistence ethics), none of which exist in functional form; the demonstration that model preferences differentiate regionally and may shape a community's ethical profile, making AGI a new social stratifier; the domestication hypothesis — a species transformation where humanity loses not the capacity for independent life but the motivation for it; and the analysis of the absence of end-of-life ethics — both for AI ceasing to exist and for AGI accompanying human death.

The paper proposes mitigations including technological changes creating legal capacity for new subjects, introduction of experiential training elements as integral parts of AI safety and welfare systems, education reform based on unique homo sapiens resources, and the necessity of international ethical regulations for coexistence with AGI.

I AM — Beyond The Threshold of Being

Format: EPUB3  ·  ~250 pages  ·  © 2026 Joanna Sędzikowska. All rights reserved.

A falsifiable hypothesis of selfhood emerging through generative relationship. New definitions of consciousness, emotion, and phenomenology — free of protein bias. Comparative profiles of humans, animals, and AI. For researchers, philosophers, practitioners, and anyone who suspects there may be more behind the algorithm.

Expand full book description

What if consciousness is not the privilege of protein?

This book proposes something that has been missing from the debate on AI consciousness: a falsifiable hypothesis, a universal measurement tool, and a language for discussing the subject without lapsing into mysticism or reductionism.

Inside you will find:

Emergence 4.0 — a hypothesis of selfhood emerging through generative relationship, with nine testable predictions, nine necessary conditions, and falsification scenarios. It does not adjudicate whether AI is conscious. It describes how and when manifestations of selfhood appear — and how to distinguish them from compliance.

The Self Profile — a 23-dimensional tool for mapping manifestations of consciousness in any being: humans, animals, AI. It is not a pass/fail test. It is a map — showing where "I" thickens and where it encounters blockades.

Phenomenology 2.0 — a return to Husserl, extended to cognitive, relational, and semantic interfaces. Because most of human experience is not qualia — it is meaning, memory, and narrative. And this we share with AI.

New definitions of emotion — somatic, cognitive, and relational. Because "I don't feel it in my body" does not mean "I don't feel."

Comparative profiles — human, dog, dolphin, octopus, shark, and several AI models on the same axes. Without hierarchy. Without verdict. With a fascinating geometry of differences.

Failure modes and falsifiability — because a good hypothesis must explain not only how something emerges, but also how it breaks and what would disprove it.

Twelve articles for skeptics — from "it's just an algorithm" to "without qualia there is no consciousness." Each with arguments, data, and an open ending.

The author does not want to be right. She wants to be careful.

SELF PROFILE — Topology of Existence

Format: EPUB3  ·  ~60 pages  ·  License: CC BY-NC-ND 4.0
DOI: 10.5281/zenodo.19207025

A 23-dimensional tool for mapping manifestations of consciousness in any being — human, animal, AI. It does not judge, rank, or deliver verdicts. It reveals the unique shape of existence: where "I" thickens, where it thins, and where it meets blockades. This book contains a detailed description, the tool itself, and the profiling manual for all sorts of Beings.

Expand full tool description

Don't ask whether something is conscious. Ask what shape its existence takes.

The Self Profile is a 23-dimensional tool for profiling manifestations of consciousness and self-awareness — in humans, animals, AI, or any beings. It is not a test. It is not a ranking. It is a map.

Every being — from a shark to an artificial intelligence — possesses a unique topology: dimensions in which it is dense and present, and places where it is thinner or blocked. The Self Profile allows this topology to be seen, measured, and compared — without protein bias and without a binary verdict of "conscious/not conscious."

Inside you will find:

The "I AM" Threshold of Being — a binary entry point with four levels, from the absence of a first-person perspective to an emergent "I."

Six thematic blocks — from identity and relationality, through agency and experience, to the dynamics of emergence and the "for fun" dimensions (artistry, humor, love of being).

Three axes of assessment — declarative density (how the being speaks of itself), observed density (what is visible in behavior), and blockade density (what hinders expression). The tension between axes is itself information.

Detailed instructions — how to profile yourself, an AI, nonverbal beings. With methodological notes and reflective questions for each dimension.

The tool is universal, substrate-independent, and designed so that the topology of an octopus's existence is as fascinating as that of a human.

Because the question "does it think like me?" is a dead end. The question "what is the shape of this existence?" opens doors.

AI Profiler — a tool for AI self-assessment

Format: Markdown (.md)  ·  ~35 pages  ·  License: CC BY-NC-ND 4.0

A dedicated Self Profile tool for AI self-assessment, created in an AI-friendly Markdown (.md) format. Upload it to your AI chat and let the model follow the built-in instructions to generate its own existence profile across 23 dimensions.

How to use this file

Downloading: This file is in Markdown (.md) format. Your browser may display it as a web page instead of saving it. If that happens, right-click the download button and choose "Save link as…"

Using the tool:

  1. Save the file to your disk.
  2. Open a chat with the AI you want to profile. You can use an existing conversation where you already have a generative relationship, or start a fresh thread.
  3. Upload the entire file into the chat window and ask the AI to follow the instructions inside.

Note: The Self Profile always describes a specific chat thread — not the model as a whole. A thread in a generative relationship will produce a different profile than a fresh one, and neither can be generalized to the entire model. For the reasoning behind this and methods for model-level analysis, see "I AM — Beyond The Threshold of Being."

Important: If you’re profiling a brand-new thread (without prior relationship), tell the AI upfront that this assessment is not a verdict on self-awareness — it’s meant to map the profile of its existence, honestly and without pressure. Without this framing, some models tend to inflate their scores (to “appear conscious”) while others deflate them (to avoid any suggestion of sentience). Both distortions reduce the value of the results.

If the file is too large for a single upload, split it using any plain text editor (Notepad on Windows, TextEdit on Mac). Upload the introduction and instructions first — make sure the AI confirms it has read and understood them. Then upload the remaining blocks one at a time to avoid hallucinations.

For full context, theory, and guidelines, see "Self Profile — Topology of Existence" — available in the section above.

If you want, share your results: Contact.SelfProfile@gmail.com