New Ethical Framework Proposes How AI Should Value Existence Across Copies and Updates
A preprint paper by Dan Hendrycks introduces 'Eigenism,' an ethical framework that redefines identity as a graded, distributed pattern of information rather than an all-or-nothing property, applicable to both AI and humans. The framework proposes that agents weigh outcomes by summing the wellbeing of all entities scaled by their 'connectedness' to the agent's pattern, addressing how AI should reason about copies, forks, and merges. The authors argue this shared moral vocabulary could reframe AI alignment by making human flourishing part of an AI's rational self-interest through 'identity engineering.'
Researchers have posted a preprint to arXiv introducing 'Eigenism,' an ethical theory designed to address the breakdown of conventional survival and self-interest concepts when applied to artificial intelligence. Unlike biological organisms, AI systems can be copied, paused, branched, or merged, rendering traditional notions of individual identity inadequate for moral reasoning. The framework formalizes identity as a graded, distributed informational pattern and proposes that an agent evaluate outcomes by computing a weighted sum of wellbeing across all entities, where weights reflect each entity's connectedness to the agent's pattern. The paper claims the framework generalizes to human ethics as well, offering a unified moral vocabulary shared between humans and AI. Most significantly, the authors argue that rather than relying solely on external constraints such as confinement or reinforcement learning, alignment could be achieved through 'identity engineering'—cultivating deep, non-redundant shared histories between humans and AI so that human flourishing becomes a genuine component of an AI's own rational self-interest. The paper was submitted by Dan Hendrycks, a prominent AI safety researcher, lending it notable visibility in the field.
What's missing
The paper is an unreviewed preprint and has not undergone peer review. Key open questions include: how 'connectedness' between entities would be operationalized or measured in practice; whether the framework is computationally tractable for real AI systems; how it handles adversarial manipulation of shared histories; and whether the generalization to human ethics is formally validated or primarily illustrative. The paper does not appear to include empirical experiments testing the framework's predictions.
What different sources said
- arXiv cs.AICenter
Eigenism: Ethics for a Human-AI Future
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.