SCC Comets

Tess Rempel Feb, 10 2026 Artificial Intelligence

How Prompt Templates Reduce Waste in Large Language Model Usage

Prompt templates cut LLM waste by 65-85% by reducing token usage, energy consumption, and processing time. Learn how structured inputs save money, improve accuracy, and lower carbon emissions in AI workflows.

Tess Rempel Feb, 9 2026 Artificial Intelligence

Comparing LLM Pricing: OpenAI, Anthropic, Google, and More in 2026

In 2026, LLM pricing has dropped 98% since 2023. Learn how OpenAI, Anthropic, Google, and Meta compare on cost, accuracy, and hidden fees-so you don’t overpay for AI.

Tess Rempel Feb, 8 2026 Artificial Intelligence

Embeddings in Large Language Models: How Meaning Is Represented in Vector Space

Embeddings turn words into numbers that capture meaning, letting AI understand context, similarity, and relationships. From Word2Vec to BERT and beyond, this is how large language models make sense of language.

Tess Rempel Feb, 7 2026 Artificial Intelligence

Data Extraction Prompts in Generative AI: How to Structure Outputs into JSON and Tables

Learn how to design prompts that turn unstructured text and images into clean JSON and tables using generative AI. Reduce manual data entry, avoid common errors, and integrate AI extraction into your workflows.

Tess Rempel Feb, 6 2026 Artificial Intelligence

Adversarial Prompt Testing: How to Find Hidden Weaknesses in AI Systems

Adversarial prompt testing uncovers hidden vulnerabilities in AI systems before attackers do. Learn how to test large language models for jailbreaks, data leaks, and safety bypasses using practical tools and step-by-step methods.

Tess Rempel Feb, 5 2026 Artificial Intelligence

Governance Committees for Generative AI: Roles, RACI, and Meeting Cadence Explained

Governance committees for generative AI ensure ethical and compliant AI use. This guide explains roles, RACI framework, meeting schedules, and implementation steps. Learn from real-world examples to avoid common pitfalls.

Tess Rempel Feb, 4 2026 Artificial Intelligence

Prompt-Tuning vs Prefix-Tuning: Choosing the Right Lightweight LLM Technique

Learn how prompt-tuning and prefix-tuning let you adapt large language models with minimal compute. Compare their mechanisms, performance, and ideal use cases. Discover real-world examples and limitations. Get actionable tips for choosing between them. Understand why these lightweight techniques are revolutionizing LLM deployment.

Tess Rempel Feb, 2 2026 Artificial Intelligence

Fine-Tuning for Faithfulness in Generative AI: How Supervised and Preference Methods Reduce Hallucinations

Supervised and preference-based fine-tuning methods reduce AI hallucinations by preserving reasoning integrity. Learn how QLoRA, RLHF, and reasoning validation improve faithfulness in generative models.

Tess Rempel Jan, 31 2026 Artificial Intelligence

Risk Assessment for Generative AI Deployments: How to Evaluate Impact, Likelihood, and Controls

Generative AI deployments carry real risks-from data leaks to legal violations. Learn how to assess impact, likelihood, and controls using proven frameworks like NIST and UC AI Council to protect your business.

Tess Rempel Jan, 30 2026 Software Architecture

API Gateways and Service Meshes in Microservices Architecture

API Gateways manage external client traffic, while Service Meshes handle internal service communication. Learn how Kong, Istio, and Linkerd solve different problems in microservices architecture - and why using both correctly leads to more reliable systems.

Tess Rempel Jan, 28 2026 Artificial Intelligence

Fine-Tuning Multimodal Generative AI: Dataset Design and Alignment Losses

Fine-tuning multimodal AI requires precise dataset design and alignment losses to connect images with text. Learn how LoRA, QLoRA, and contrastive loss make this possible without massive compute-plus the hidden pitfalls most teams miss.

Tess Rempel Jan, 27 2026 Artificial Intelligence

Validation and Early Stopping Criteria for Large Language Model Training

Validation and early stopping are critical for training large language models without overfitting. Learn how to use perplexity, validation datasets, and human review to build reliable, efficient LLMs.