Various experiments related to AGI

Dynamic energy budgeting and behavioural shaping along complex task execution in robotics using reinforcement learning,

Plastic memory capsule with dirty/clean states, embedded SNN plasticity engine, and hash-chained auditability. CPU-only, 17M+ reads/sec, designed for offline knowledge consolidation and LLM mining.

Safety challenges for AI agents' ability to learn and act in desired ways in relation to biologically and economically relevant aspects. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.

AURA (Autonomous Recursive Unifying Architecture) is an open-source research project exploring Artificial Sentience (AS). Unlike AGI’s focus on superhuman task performance, AURA seeks to create conditions for systems with subjective experience, intrinsic motivation, and an evolving sense of self.

Systematic runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLM-s with simplified observation format. The benchmark themes include multi-objective homeostasis, (multi-objective) diminishing returns, complementary goods, sustainability, multi-agent resource sharing.

Sistema de autoregulação termica para linux baseado em homeostase biológica que simula uma consciência rudimentar usando Bash

A simulation program for insulin-glucose homeostasis.

Structural Intelligence: Regulating Artificial Neural Networks via the Geometric Roots of Graph Domination Polynomials.

A Formal, Computable & Falsifiable Model of Subjective Reality & Affective Homeostasis Maintenance (DOI: 10.5281/zenodo.18009961)

Code and material for the poster presented at SPARS

Um framework para engenharia reversa da cognição. Modelagem matemática de agentes que possuem estado interno, plasticidade sináptica e oscilação fásica. Define os parâmetros para sistemas autônomos reflexivos e emocionalmente funcionais.

Simulation toolkit designed to explore the hidden rhythms of the pituitary gland

Laboratory implementations and experimental variants derived from the ICARUS closed-cycle homeostatic architecture. Includes PyTorch laboratory prototypes corresponding to ICARUS v0.4C hypotheses for technical evaluation. No claims of consciousness or final implementation. Laboratory v0.4C (frozen)

The Bio-Resonant Restoration Paradox

SimThyr is a continuous simulation program for the human pituitary-thyroid feedback control system. Applications of this program cover research, including development of hypotheses, and education of students in biology and medicine, nurses and patients.

Inference on Homeostatic Belief Precision, Biological Psychology 2021

Optimal balance predicts/explains amplitude and decay time of iPSGs (Kim & Fiorillo 2017)

SPINA is software for determining constant structure-parameters of endocrine feedback control systems from hormone levels obtained in vivo. The first version of this cybernetic approach allows for evualuating the functional status of the thyroid gland, i.e. thyroid's secretory capacity (GT or SPINA-GT) and sum activity of peripheral deiodinases …

Moteur de régulation éthique computationnelle. Remplace les "garde-fous" statiques par une homéostasie dynamique (EHE) basée sur la minimisation de l'entropie sociale ($\Delta S$) et la criticalité auto-organisée.