SCC Comets

Tess Rempel Jul, 3 2026 Artificial Intelligence

How to Build Human-in-the-Loop Evaluation Pipelines for LLMs

Learn how to build Human-in-the-Loop evaluation pipelines for LLMs. Discover tiered architectures, uncertainty sampling, and best practices for combining AI speed with human nuance to ensure model quality and safety.

Tess Rempel Jul, 2 2026 Software Architecture

Architecture-Aware Prompting: How to Guide AI for Better Software Designs

Learn how architecture-aware prompting uses deep context to guide AI in creating robust, constraint-compliant software designs, avoiding common pitfalls of generic AI advice.

Tess Rempel Jul, 1 2026 Artificial Intelligence

Vibe Coding for IoT Demos: Simulating Devices and Building Cloud Dashboards Fast

Learn how vibe coding transforms IoT demos by enabling rapid device simulation and cloud dashboard creation using AI. Discover best practices, security risks, and tools for 2026.

Tess Rempel Jun, 30 2026 Artificial Intelligence

Incident Management for LLM Failures: A Practical Guide to Handling AI Incidents

Learn how to build robust incident management strategies for LLM failures, including handling hallucinations, prompt injections, and safety violations with practical frameworks.

Tess Rempel Jun, 29 2026 Software Architecture

Automated Architecture Lints: Enforcing Boundaries in Vibe-Coded Apps

Learn how automated architecture lints enforce boundaries in vibe-coded apps, preventing technical debt and maintaining structural integrity in AI-generated software.

Tess Rempel Jun, 28 2026 Artificial Intelligence

Efficient Sharding and Data Loading for Petabyte-Scale LLM Datasets

Master efficient sharding and data loading for petabyte-scale LLM datasets. Learn tiered storage, SDP, and optimization techniques to eliminate GPU idling.

Tess Rempel Jun, 27 2026 Artificial Intelligence

Visualizing LLM Evaluation Results: Techniques, Tools, and Best Practices

Master LLM evaluation visualization with proven techniques like scatter plots, heatmaps, and parallel coordinates. Learn to use tools like EvaLLM and LIDA to uncover model weaknesses and compare benchmarks effectively.

Tess Rempel Jun, 26 2026 Artificial Intelligence

Task Decontamination for LLM Benchmarks: How to Stop Training Data Leakage

Learn how to prevent training data leakage in LLM benchmarks using task decontamination techniques like ConTAM and lm-evaluation-harness to ensure accurate model evaluation.

Tess Rempel Jun, 25 2026 Artificial Intelligence

State-Level Generative AI Laws in the US: California, Colorado, Illinois, and Utah (2026 Guide)

Navigate the complex landscape of US state-level generative AI laws. This guide covers key regulations in California, Colorado, Illinois, and Utah, helping you understand compliance requirements for transparency, training data, and biometrics.

Tess Rempel Jun, 24 2026 Artificial Intelligence

Edge Cases That Trigger Hallucinations in Generative AI: Patterns and Prevention

Explore the edge cases that trigger hallucinations in generative AI, including prompt ambiguity and domain specificity. Learn proven prevention strategies like RAG and automated fact-checking to mitigate risks in enterprise deployments.

Tess Rempel Jun, 23 2026 Artificial Intelligence

On-Prem and Private Cloud LLMs for Regulated Data Handling: A Complete Guide

Explore how on-premise and private cloud LLMs solve data privacy challenges in regulated industries. Learn about deployment options, cost benefits, and compliance strategies for HIPAA and GDPR.

Tess Rempel Jun, 22 2026 Artificial Intelligence

Calibrating Confidence in Large Language Models: Techniques and Metrics

Explore techniques to calibrate confidence in LLMs, including verbalized confidence, the Thermometer method, and key metrics like ECE. Learn how to fix AI overconfidence for safer deployments.