Hi, I'm Ian.
Senior AI Engineer @ Salesforce. I build AI systems and agentic AI systems that make AI feel simple, fast and trustworthy.
BlogMy 350M parameter deepfake detector scored 100% on tests and failed in the real world
A 2M parameter model with no pretrained backbone beat my 350M parameter WavLM pipeline by 24 percentage points on out-of-distribution data. I ran 50 experiments across four architectures, multiple datasets, and different audio codecs. The results inverted every assumption I had.
ProjectAI-SPY Text Detection: AI Writing Detection That Shows Its Work
A multi-level AI text detection system built on DeBERTa and a custom dual-path architecture — sentence, paragraph, and document analysis with attention-based attribution so you can see exactly which parts triggered the verdict.
BlogBuilding AI text detection that explains itself
Most AI detectors give you a percentage and call it a day. We built one that shows you which sentences triggered the verdict, how much each one mattered, and why—using attention-based attribution on a sliding window transformer.
BlogAre words the best building blocks for AI?
Language tokens are a poor substrate for grounded intelligence. This post argues for structured, world-centric tokens—geometry, dynamics, agency, causality—and outlines bridging mechanisms like cross-attention and V-JEPA to connect language with learned perceptual models.
BlogAgents that learn in production
Most LLM agents don’t learn from deployment-time experience. This post outlines how to add true online learning via preferences, memory‑augmented policies, streaming adapters, and continual learning—plus the hard gaps to close.
BlogAgents are risky - How much access should we give them?
A practical framework for agent permissions through CRUD—why read-only agents are safest, how compositional risk explodes with actuators, and what guardrails enable safe autonomy.