Writing
Notes from building
Longer-form write-ups of things I've actually built — what the problem was, what I tried, and where it broke.
- 6 min
Your agent isn't repeating itself. It's just not learning anything.
Repetition detection is the standard guard against stuck agent loops, and it fails in both directions. Building Plateau meant measuring stagnation in embedding space instead — and calibrating the threshold per run.
- Agents
- Embeddings
- Reliability
- 7 min
Reciprocal Rank Fusion in practice: what k actually controls
Why hybrid retrieval fuses ranks instead of scores, what the k constant in RRF really does, and where the method quietly fails on legal and compliance corpora.
- Retrieval
- RAG
- Evaluation
- 6 min
Reinforcement learning over cgroup v2: why PSI beats free bytes
Building a predictive memory orchestrator meant choosing an observation space for the policy. Free-memory counters looked obvious and were wrong. Here's what PSI telemetry gives you instead.
- Systems
- Reinforcement Learning
- Linux