8 min read
Turning Production Queries into an LLM Eval Set You Can Trust
How I sample real user queries by stratum, redact PII before anyone reads them, split off a holdout and keep the eval set current as the product changes.
Privacy
8 articles
1 min read
On-Device Models: Deploying AI Without the Cloud
On-device AI enables new categories of privacy-preserving, low-latency applications. Choose the right format and optimization strategy for your target platform.
2 min read
Windows AI Recall: Photographic Memory for Your PC
Recall continuously captures screenshots of your activity and makes them searchable through AI. Think of it as a time machine for your digital life.
1 min read
Local AI Models: Running Intelligence On-Device
Not every AI workload needs to call the cloud. Today I'm exploring when and how to run AI models locally on your device.
1 min read
GDPR and AI: Practical Compliance for ML Systems
GDPR's implications for AI are practical, not theoretical: logging decisions, maintaining provenance, and ensuring human review where necessary are the…
1 min read
PII Detection and Protection in AI Applications
Implementing comprehensive PII detection and protection strategies for AI applications.
1 min read
Differential Privacy in Machine Learning: Protecting Individual Data
Differential privacy ensures that the output of a computation doesn't reveal whether any individual's data was included. The key insight: add calibrated…
1 min read
Federated Learning: Privacy-Preserving Machine Learning
Federated learning in 2021 moved from research to practical deployment. Healthcare, finance, and mobile applications led adoption where data privacy is…