A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Anthropic's Interactive Prompt Engineering Tutorial

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining …

Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"

The app uses the Gemini language model to generate personalized book recommendations.

#Provided by Somayeh Komeylian: PhD Student at UCSD & SDSU # Event bindings: The code includes mouse event bindings for the username and password fields to demonstrate the functionality you request…

Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"

End-to-end diabetes risk prediction pipeline (Pima): EDA → feature engineering → calibration + cost-aware threshold → deployable artifacts.

IMDB reviews sentiment analysis: EDA → TF-IDF baselines (NB/LogReg/Linear SVM + calibration) → F1 threshold tuning → explainability → BiLSTM baseline.

Sentiment Analysis and Topic Modeling of Pet Market Reviews in Santo André using BERTimbau and Active Learning.