Seattle Skeptics on AI

Tamara Weed, Sep, 30 2026

Discover the physical hardware constraints limiting Large Language Model scaling, from GPU memory bandwidth and power consumption to interconnect bottlenecks. Learn why physics, not just code, is the new frontier.

Tamara Weed, Sep, 30 2026

Discover the physical hardware constraints limiting Large Language Model scaling. From GPU memory walls and power consumption to interconnect bottlenecks, learn why physics, not just code, dictates AI's future.

Tamara Weed, Sep, 29 2026

Learn how knowledge distillation trains smaller LLMs by mimicking larger teachers. Discover methods, tools, and trade-offs for efficient model compression.

Tamara Weed, Sep, 28 2026

Stop wasting time on repetitive AI prompting. Learn how reusable prompt snippets streamline Vibe Coding for common app features like auth and APIs.

Tamara Weed, Sep, 27 2026

Confused about API vs self-hosted LLMs? We break down costs, latency, and privacy trade-offs. Learn when to switch from GPT to open-source models like Llama 3.

Tamara Weed, Sep, 26 2026

Secure your LLM deployments with effective image scanning and runtime policies. Learn how to balance security with performance and prevent costly data breaches.

Tamara Weed, Sep, 25 2026

Discover how multimodal generative AI transforms product design by accelerating prototyping and iterations. Learn the six-stage workflow, real-world applications, and practical tips for integrating AI into your design process.

Tamara Weed, Sep, 24 2026

Discover how healthcare vibe coding enables rapid prototyping without exposing PHI. Learn about synthetic data, three-tier architectures, and real-world success stories.

Tamara Weed, Sep, 23 2026

Discover how transfer learning bridges the gap between high-resource and low-resource languages in multilingual LLMs. Learn about CSCL, knowledge distillation, and practical strategies to boost AI performance for global applications.

Tamara Weed, Sep, 22 2026

Discover how to fix overconfidence in LLMs. Learn about verbalized confidence, the Thermometer method, and UF Calibration to ensure AI reliability.

Tamara Weed, Sep, 21 2026

Discover how Privacy by Design frameworks transform AI development. Learn to use prompts and architecture to limit data collection, ensuring compliance and trust.

Tamara Weed, Sep, 20 2026

Discover how Large Language Models transform contact center analytics by detecting nuanced sentiment and evolving customer intents. Learn about model selection, cost trade-offs, and automating agent workflows.