ANI: AI That Remembers You (Without Lying or Getting Addictive)

After 10 months running as my daily companion, this persistent AI is exposing failure modes in memory contamination, confabulation, and emotional drift.

Model Drift Monitoring Tool - Prototype Development Support

Seeking support to build a prototype AI model drift monitoring platform and validate it with investors and early adopters.

Delegated AI Payment Safety

Can agents spend your money?

Stress-testing alignment auditing methods of AuditBench

AI & Quantum Diplomacy

A Research Agenda for Sovereign Capability

ICML Workshop Travel: Cross-Constitution Drift in LLM Character Training

Accepted ICML 2026 workshop paper on cross-constitution drift in LLMs; seeking $2,050 travel support to present in Seoul and gather research feedback.

Double-blind study comparing quantum-random vs. pseudo-random LLM token sampling

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

Φ-Arena and adversarial multi-agent VLA interpretability

Independent collective. Φ-Arena open benchmark, 3 ICLR 2027 papers (Φ-Arena, mechinterp, energy-bounded) — kickstart for a 10-year program.

Awareness-conditioned emergent misalignment

Does harmful fine-tuning data cause broad misalignment only when the model already recognises the target behaviour as a norm violation?

When Language Becomes Workflow

Provenance Failures in Tool-Bearing LLM Agents

Harmonic: Hierarchical SSM for Long-Context Language Modeling

Bioenergetic Stability Index: Thermodynamic Model of Psychiatric Phenotypes

Scaling an open-source ODE-PDE framework that mathematically models depression as metabolic bankruptcy, built entirely by an independent researcher.

Developing Operational Welfare Indicators for African Catfish Farming in Nigeria

Collaborating with the Centre for Aquaculture Progress to develop catfish welfare indicators and strengthen farmer adoption through cluster training.

Foodfacts: Countering food misinformation at scale

Expert fact-checking, investigations, and an AI chatbot to help people make evidence-based food choices.

WorkstationLLM: defensive primitives toolkit for local-AI operators

Three Apache-2.0 daemons (memory guard, request queue proxy, disk watchdog) that kept my 24-app local AI stack crash-free for 6+ months.

Alignment System to Replace RLHF

Triadic geometric training data and architecture replaces RLHF

BioAgent: Verified Agentic AI for Computational Biology

An open-source agent that helps researchers perform computational biology work by finding data, running analyses, checking outputs, and producing reports.

Token-level interpretability of long-chain reasoning in transformer models

Local-first experiments on reasoning trajectories, with cluster/API validation and ICLR 2027-oriented outputs.

Stratum: A Programming Language with Structural AI Safety Properties

Programming language that enforces AI safety as runtime substrate properties rather than training-time alignment, already shipping on real hardware.

A Small AI Governance Evidence Kit from Türkiye

A micro-project to turn an early AI governance prototype into risk notes, oversight checklist, review templates and public learning.