development
- The chain rule behind autoregressive models
Autoregressive models are just the probability chain rule plus a conditional model. Here’s the mental model, the math, and what training is really doing.
- Security Implications of Probabilistic Reasoning in Generative AI
A rigorous analysis of how probabilistic reasoning in generative models shapes security risk, failure modes, and robustness.
- Separation of Responsibilities in Spring-Based Systems: What Kotlin Makes Explicit
Examines how Kotlin’s type system and language semantics sharpen responsibility boundaries in Spring-style architectures without replacing architectural discipline.
- Amazon Bedrock: foundations, systems, and scaling
A highly technical article on Amazon Bedrock with mathematical foundations and numerical examples.
- Podcast episode
A post with a Spotify episode embedded at the top.
- Calculus, AI, and linear algebra: a compact field guide
A quick, code-backed refresher on gradients, Jacobians, and the linear algebra that drives modern ML.
- Graceful retries in Python with backoff
A small, production-ready retry helper using exponential backoff and logging.
- Streaming logs in Rust with Tokio
Build a small async log streamer that tails a file and ships JSON lines.
- Why Most Postmortems Miss the Real Failure Mode
Argues that postmortems often substitute proximate triggers for causal structure, obscuring system dynamics, incentives, and latent conditions that actually drive failure.
- Simple writing and publishing flow
A lightweight process to draft, edit, and publish consistently.
- Why this blog exists
A short purpose statement: clarity, record, and real learning.