Blog
B0Pranav's learning log

What I'm learning.

Notes from the things I build, and what I figure out along the way.

Notes
N1BUILD NOTE

Building Tweakler: cloning interfaces without guessing

What changes when a design reference becomes structured evidence instead of a screenshot prompt.

  • Agents
  • Design systems
  • Tooling
/coming soon
N2FIELD NOTE

The missing quality layer in coding-agent evaluations

Notes on separating policy performance, captured evidence, and the judgment that connects them.

  • Evaluation
  • Coding agents
  • Benchmarks
/coming soon
N3LEARNING LOG

Training GPT-2 on 10 billion tokens from scratch

The implementation details that made the jump from a readable transformer to a trainable one.

  • Foundations
  • Transformers
  • Training
/coming soon
N4ARCHITECTURE

Routing sensitive data before it reaches the cloud

A practical model for classifying PII and choosing between on-device and cloud inference.

  • AI systems
  • Privacy
  • Inference
/coming soon
N5PRODUCT NOTE

Designing an AI copilot for sensitive case notes

What early-childhood assessors taught me about structured outputs, trust, and useful automation.

  • Design
  • Healthtech
  • Human factors
/coming soon
N6RESEARCH NOTE

When product analytics can adapt the interface

Exploring the boundary between observing user behavior and automatically changing a product.

  • AI systems
  • Analytics
  • Adaptation
/coming soon