5 areas
1 open question
Questions I might spend years trying to answer.
This is not a finished research profile yet. It is where I keep the questions.
My work is currently moving towards artificial intelligence, machine learning, deep learning, trustworthy AI, traceability, explainability, and human-AI decision support.
I am especially interested in the gap between a model producing an answer and a human being able to trust, verify, and act on it. That gap is not a UX problem. It is a fundamentally hard problem in epistemics, system design, and the relationship between algorithmic reasoning and human judgement.
Keywords:trustworthy ai; traceability; human-ai collaboration; knowledge graphs and memory; deep learning foundations.
Research focus areas
- Trustworthy AI
- How do we design AI systems that can be checked, challenged, and trusted? Not just through performance metrics, but through transparency of process, auditability of decisions, and the ability to fail gracefully.
- Traceability
- How do we preserve the trail between data, reasoning, output, and decision? I am interested in the chain of provenance: from source to inference, from evidence to conclusion.
- Human-AI Collaboration
- How do we design systems where AI helps humans think better, rather than replacing judgement with automation? The interface between human cognition and machine output is one of the most underexplored problems in applied AI.
- Knowledge Graphs and Memory
- How do we structure information so that ideas can be found, connected, and reused over time? This links to Curio Synapse: building systems that preserve the trail of learning.
- Deep Learning Foundations
- What makes modern neural networks powerful, fragile, interpretable, or opaque? Understanding the mechanisms under the performance numbers matters if we want to build systems we can trust.
active
Active question
Question 1 (traceability). How do we build AI systems that can explain where their answers came from?
Remarks.Not just with a citation pasted underneath, but with a real trail of reasoning, evidence, uncertainty, and context. The answer sits somewhere between knowledge graphs, natural language reasoning, information retrieval, and the philosophy of evidence.
& essays
Research seeds
These are early-stage notes connected to research questions. Some will grow into proper essays or paper notes.
- N° 21
The Off-Switch and the Objective: What the Fable 5 Shutdown Reveals About Capability Control
On 12 June 2026, the US government ordered Anthropic to disable its most capable public model. The action was not a response to a misaligned system. It was the off-switch being pulled, and it exposes the precise limit that Bostrom and Russell warned about: capability control is a supplement to alignment, never a substitute for it.
essayai, ai safety, value alignment
- N° 19
He Asked for Water. His Son Threw Him in the Sea. This is an AI Problem.
What a Arabic proverb and a drowning man can teach us about how we state problems in AI. The right question is half the answer. The wrong goal is all the danger.
essayai, problem framing, requirements
- N° 17
AI Traceability: The Gap Between Answer and Trust
AI systems can produce confident answers with no trail of reasoning behind them. This is not just a UX problem. It is a fundamental problem in epistemics and system design.
research seedai, machine learning, traceability
- N° 9
What Start With Why Actually Changed in How I Think
Sinek's book is easy to dismiss as business self-help. But asking why before what changed how I approach problems in ways I did not expect.
essaybusiness, leadership, start with why
See how research seeds, reading notes, and essays connect in the Neural Map.