SCC Comets

Tess Rempel Mar, 23 2026 Artificial Intelligence

On-Device Generative AI: How Edge AI Delivers Privacy and Speed Without the Cloud

On-device generative AI processes data locally on your phone or smart device, eliminating cloud delays and keeping your data private. It's faster, more secure, and already in your hands.

Tess Rempel Mar, 22 2026 Software Architecture

Monolith or Microservices for Vibe Coding: How to Choose the Right Architecture

Choosing between monolith and microservices in Vibe Coding isn't about trends-it's about flow. Learn when to stick with one codebase and when to break things apart for faster, smarter shipping.

Tess Rempel Mar, 21 2026 Artificial Intelligence

Role Assignment in Vibe Coding Prompts: Senior Architect vs Junior Developer

Role assignment in vibe coding lets you tell AI whether to act like a senior architect or junior developer - and it dramatically changes code quality, security, and review time. Learn how to use it effectively.

Tess Rempel Mar, 20 2026 Artificial Intelligence

How AI High Performers Capture Value from Generative AI: Workflow Redesign and Scaling

High-performing organizations don’t just use generative AI - they redesign workflows around it. Learn how companies like Klarna, Colgate, and Five Sigma cut costs, boosted productivity, and re-engaged employees by focusing on one high-impact use case at a time.

Tess Rempel Mar, 19 2026 Artificial Intelligence

Scientific Workflows with Large Language Models: How Researchers Are Using Sci-LLMs to Accelerate Discovery

Scientific Large Language Models (Sci-LLMs) are accelerating research by automating literature reviews, generating hypotheses, and designing experiments. Learn how they work, where they excel, and where they still fail.

Tess Rempel Mar, 18 2026 Artificial Intelligence

Token Probability Calibration in LLMs: How to Fix Overconfidence in AI Predictions

Token probability calibration fixes AI overconfidence by aligning predicted probabilities with real accuracy. Learn how GPT-4, Llama-2, and other models misjudge confidence-and what to do about it.

Tess Rempel Mar, 17 2026 Artificial Intelligence

Natural Language to Schema: How to Prompt Databases and ER Diagrams Effectively

Natural Language to Schema lets non-technical users query databases using plain English. Learn how ER diagrams, schema awareness, and LLMs work together to turn spoken questions into accurate SQL-plus real-world accuracy stats, tool comparisons, and implementation tips.

$Domain-Specialized Large Language Models: Code, Math, and Medicine$

Tess Rempel Mar, 15 2026 Artificial Intelligence

Domain-Specialized Large Language Models: Code, Math, and Medicine

Domain-specialized LLMs like CodeLlama, Med-PaLM 2, and MathGLM are outperforming general AI models in code, math, and medicine - with higher accuracy, lower costs, and real-world impact.

Tess Rempel Mar, 13 2026 Artificial Intelligence

Autoscaling Large Language Model Services: Policies, Signals, and Costs

Autoscaling LLM services requires specialized metrics like prefill queue size and slots_used-not CPU or GPU usage. Learn how to balance cost and latency with real-world policies for chatbots, batch jobs, and real-time apps.

Tess Rempel Mar, 11 2026 Artificial Intelligence

Multilingual RAG for Large Language Models: Overcoming Cross-Language Retrieval Challenges

Multilingual RAG lets LLMs answer questions across languages using external data-but hidden biases favor English. Learn how cross-language retrieval fails, why translation alone isn’t enough, and what new frameworks like DKM-RAG are doing to fix it.

Tess Rempel Mar, 7 2026 Artificial Intelligence

Vision-Language Applications with Multimodal Large Language Models

Vision-language models now combine image and text understanding in real-time, transforming document processing, healthcare, and robotics. Open-source models like GLM-4.6V are outperforming proprietary systems in key areas, despite high compute costs and hallucination risks.

Tess Rempel Mar, 6 2026 Artificial Intelligence

Token Budgets and Quotas: How to Stop LLM Cost Overruns Before They Happen

Token budgets and quotas are the only way to prevent runaway LLM costs. Learn how to set limits on token usage, apply graduated throttling, and avoid expensive mistakes before they happen.