-
Chatbot security: prompt injection, jailbreaks, and data exfiltration
A chatbot that can answer questions is useful. A chatbot that can search internal documents, read repositories, browse websites, execute tools, and interact with enterprise applications is considerabl
-
Evaluating generative vision: FID, CLIPScore, and human preference
Imagine two generative image models responding to the same prompt:
-
Agent memory: short-term, long-term, and avoiding context rot
An AI agent can process thousands of messages, call dozens of tools, and work across multiple sessions. Yet it can still forget a crucial decision from twenty minutes ago, resurrect an outdated requir
-
Evaluating LLMs beyond vibes: building an eval harness that catches regressions
A language model can produce a beautifully written answer that is completely wrong.
-
This is not an ML problem: constraint solvers with OR-Tools CP-SAT
Imagine you’re building a scheduling system for a fulfillment center.
-
Hyperparameter search done right: GridSearchCV, RandomizedSearchCV, and Optuna with CV built in
Hyperparameter tuning is easy to get started with and surprisingly easy to get wrong.
-
Streaming data: Kafka, exactly-once, and why it’s harder than it sounds
Imagine an e-commerce platform processing thousands of orders every second. A customer places an order, an event enters a Kafka topic, and a consumer processes that event to create a purchase record.
-
Ensembling at inference time: voting, stacking, and when it’s worth the latency
A model that achieves 92% accuracy in 2 milliseconds may be more valuable in production than an ensemble that achieves 93% accuracy in 40 milliseconds. But what if the ensemble reaches 95%? And what i
-
Cross-validation done right: k-fold, stratification, and time-series traps
A machine learning model can achieve 97% cross-validation accuracy and still fail spectacularly when deployed. The culprit is often not the algorithm, hyperparameters, or training data. It’s the way t
-
Hypothesis testing for engineers: p-values, effect sizes, and A/B pitfalls
Imagine you’re responsible for the checkout experience of an e-commerce platform.