Timeline
A chronological view of the journey so far.
2026
Sentiment Analysis Demo
A proof-of-concept interactive demo showing keyword-based sentiment analysis embedded in MDX.
Machines of Loving Grace
A reflection on Dario Amodei's essay and what it means for those building AI systems.
2025
Constitutional AI Deep Dive
Studied Anthropic's constitutional AI approach and RLHF alternatives for safer model training.
2024
Interpretability Research Sprint
Explored mechanistic interpretability techniques — sparse autoencoders, circuit analysis, and activation patching.
Deep Dive into AI Safety Research
Focused study of alignment techniques and interpretability methods.
AI Ethics Reading Group
Organized a cross-team reading group on AI ethics papers, from Bender & Gebru to Anthropic's core views.
Open Source Contributions
Started contributing to open-source AI tooling — building bridges between research and production.
2023
First Production LLM Integration
Built production systems integrating large language models with traditional software engineering.
The Anthropic Moment
Read 'Machines of Loving Grace' and realized alignment work is where engineering meets purpose.
Pivoting Toward AI
Made the deliberate career decision to focus entirely on AI engineering and safety research.
2022
Red-Teaming Workshop
Participated in adversarial testing workshops, learning to probe LLM vulnerabilities systematically.
Engineering Foundation
Established core skills across distributed systems, web platforms, and data infrastructure.
2021
Philosophy of Mind & AI
Explored connections between philosophy of mind, consciousness research, and artificial intelligence.
First Encounter with Machine Learning
The combination of mathematical elegance and practical impact sparked a lasting fascination.