Millions of people are using ChatGPT and similar artificial intelligence tools for therapy, but with little government regulation, there's no guarantee these apps are helping—or that they won't cause ...

In this tutorial, we focus on building a transparent and measurable evaluation pipeline for large language model applications using TruLens. Rather than treating LLMs as black boxes, we instrument ...

In this tutorial, we build a robust, multi-layered safety filter designed to defend large language models against adaptive and paraphrased attacks. We combine semantic similarity analysis, rule-based ...

This beginner-friendly tutorial shows how to create clear, interactive graphs in GlowScript VPython. You’ll learn the basics of setting up plots, graphing data in real time, and customizing axes and ...

A new framework from researchers Alexander and Jacob Roman rejects the complexity of current AI tools, offering a synchronous, type-safe alternative designed for reproducibility and cost-conscious ...

blockrun-llm is a Python SDK for accessing 43+ large language models (GPT-5, Claude, Gemini, DeepSeek, NVIDIA, and more) with automatic pay-per-request USDC micropayments via the x402 protocol. No API ...

Next wave of AI capabilities in Canvas LMS demonstrates commitment to a privacy-first, interoperable future for education While the edtech market has been flooded with isolated AI point solutions that ...

Abstract: As generative AI tools become increasingly prevalent in higher education, this paper explores the use of an LLM-based workflow system developed in-house to provide AI-generated feedback on ...

The University Insider is The Daily’s first faculty and staff-oriented newsletter. This weekly newsletter will give U-M faculty and staff the ability to see the most important issues on campus and in ...

Problem: Teams waste weeks integrating multiple LLM providers, handling failures, and tracking costs across disparate APIs. Solution: Single interface with automatic failover, built-in cost tracking, ...