Seattle Skeptics on AI

Tamara Weed, Oct, 23 2026

Explore how Large Language Models process multiple languages, from mBERT to GPT-4. Learn about semantic alignment, data imbalances, and the future of equitable global AI.

Tamara Weed, Oct, 22 2026

Cut LLM costs by up to 80% with prompt compression. Learn how to reduce tokens using hard and soft methods while preserving model quality.

Tamara Weed, Oct, 21 2026

Discover how grounded QA evaluation detects LLM hallucinations in RAG systems. Compare RAGAS, deepset, and ContextNLI for source-aware scoring.

Tamara Weed, Oct, 20 2026

Discover how v0, Firebase Studio, and AI Studio enable vibe coding. Compare features, workflows, and best use cases for each cloud platform.

Tamara Weed, Oct, 19 2026

Discover how vibe coding uses AI to turn plain English into functional apps. Learn who can build now, compare tools, and avoid security pitfalls.

Tamara Weed, Oct, 18 2026

Learn how to define security SLAs for vibe-coded products. Discover optimal patch windows, clarify code ownership, and implement runtime security to protect AI-generated applications.

Tamara Weed, Oct, 17 2026

Learn how to navigate COPPA compliance while using AI-driven 'vibe coding' methods. We break down the FTC's 2026 policy on age verification, explaining how to legally collect data for age checks without violating children's privacy rights.

Tamara Weed, Oct, 16 2026

Discover how v0 by Vercel accelerates React and Next.js development. Learn its strengths in generating shadcn/ui components, its limitations with other frameworks, and practical tips for integrating AI-generated code into your workflow.

Tamara Weed, Oct, 15 2026

Discover how Large Language Models transform email and CRM automation. Learn about RAG, fine-tuning, and real-world ROI metrics to scale personalization effectively.

Tamara Weed, Oct, 14 2026

Discover how domain adaptation bridges the gap between generic LLMs and specialized needs in medicine, law, and finance. Learn why simple fine-tuning fails and explore techniques like RAG, adversarial training, and PEFT to build accurate, industry-ready AI.

Tamara Weed, Oct, 13 2026

Discover how to scale open-source LLMs in 2026. Learn about hardware needs, serving stacks like vLLM, and strategic playbooks for cost-effective AI deployment.

Tamara Weed, Oct, 12 2026

Learn how to rigorously evaluate LLM prompts using A/B testing. Discover statistical methods, key metrics, and top tools like Braintrust and PromptLayer to optimize performance.