Seattle Skeptics on AI

Tamara Weed, Jun, 20 2026

Learn how to build persistent LLM agents with robust memory and state management. Explore vector databases, RLEM, and frameworks like Mem0 and LangChain for long-term retention.

Tamara Weed, Jun, 19 2026

Learn how to secure Large Language Models with Zero-Trust Architecture. Discover key strategies including federated learning, sentinel systems, and strict access controls to protect data privacy.

Tamara Weed, Jun, 18 2026

Learn when to rewrite AI-generated modules instead of refactoring. Discover key indicators like complexity and security flaws, and apply the three-strike rule to save time and reduce technical debt.

Tamara Weed, Jun, 17 2026

Explore how Query, Key, and Value projections work in LLM attention mechanisms. Understand what these matrices learn during training and how they enable context-aware processing in transformer models.

Tamara Weed, Jun, 16 2026

Discover proven prompting techniques like Human Persona and System 2 thinking to reduce stereotypes in LLM responses by up to 33%. Learn practical implementation strategies for 2026.

Tamara Weed, Jun, 15 2026

Discover how generative AI transforms customer service through smart chatbots, real-time agent assistance, and automated knowledge management. Learn to boost satisfaction and reduce costs.

Tamara Weed, Jun, 14 2026

Learn how Mata v. Avianca reshaped legal ethics regarding AI. Discover practical safety policies to mitigate hallucination risks and ensure compliant use of generative AI in professional settings.

Tamara Weed, Jun, 13 2026

Learn how to use generative AI to streamline education operations. Discover practical strategies for creating syllabi, lesson plans, and rubrics with tools like ChatGPT and Magic School, while avoiding common pitfalls.

Tamara Weed, Jun, 12 2026

Explore the true Total Cost of Ownership (TCO) for scaling Large Language Models. We break down hidden costs, GPU expenses, and scaling laws to help you build a realistic AI budget.

Tamara Weed, Jun, 11 2026

Learn how quantization and knowledge distillation cut LLM inference costs by up to 90%. Explore the economics of model compression, compare techniques, and discover best practices for cheap, scalable AI deployment.

Tamara Weed, Jun, 10 2026

Explore ethical guidelines for vibe coding at scale. Learn about security risks, IP issues, and best practices for responsible AI-assisted development in 2026.

Tamara Weed, Jun, 9 2026

Discover how Large Language Models work, from tokenization to transformer architecture. Learn about self-attention, parameters, and future trends in AI.