Seattle Skeptics on AI

Tamara Weed, May, 19 2026

Explore why tokenization remains critical for LLM efficiency, cost, and accuracy. Learn how subword methods like BPE impact performance and how to optimize for your domain.

Tamara Weed, May, 18 2026

Explore cost-aware scheduling for LLM workloads. Learn how frameworks like DeepServe++ and CATP-LLM optimize SLOs and reduce costs in serverless and multi-cloud environments.

Tamara Weed, May, 17 2026

Explore how Mixture-of-Experts (MoE) architectures balance cost and quality in large language models. Learn about compute savings, memory tradeoffs, and recent advances like DeepSeek-v3 and EAC-MoE.

Tamara Weed, May, 16 2026

Learn how Chain-of-Thought prompting improves LLM accuracy on complex tasks. Discover step-by-step implementation guides, cost trade-offs, and best practices for zero-shot and few-shot reasoning.

Tamara Weed, May, 15 2026

Explore how transformer architecture evolved since 2017. From RoPE embeddings to SwiGLU activation, discover the key innovations driving modern LLM efficiency and accuracy.

Tamara Weed, May, 14 2026

Explore the critical copyright risks of multimodal generative AI in 2026. Learn why AI images, music, and videos lack protection in the US, how training data lawsuits threaten creators, and strategies to mitigate legal exposure.

Tamara Weed, May, 13 2026

A practical guide to implementing vibe coding in your organization. Learn how to train developers, select the right AI tools, and restructure incentives to drive successful adoption.

Tamara Weed, May, 12 2026

Explore how Generative AI transforms life sciences research through de novo protein design and automated literature reviews. Learn about tools like BoltzGen and RFdiffusion3.

Tamara Weed, May, 11 2026

Learn how to force LLMs to output valid JSON using schema-constrained prompts. Explore finite state machines, implementation tools, and trade-offs between reliability and semantic accuracy.

Tamara Weed, May, 10 2026

Explore structured vs unstructured pruning for LLMs. Learn how Wanda and FASP optimize model efficiency, reduce memory usage, and speed up inference on standard and specialized hardware.

Tamara Weed, May, 9 2026

Learn how to measure generative AI adoption using telemetry, experience sampling, and surveys. Discover strategies to calculate ROI, track usage, and improve organizational AI effectiveness.

Tamara Weed, May, 8 2026

Navigate the complex regulatory landscape for AI-generated code in 2026. This guide covers EU AI Act deadlines, US state laws, and practical compliance steps for developers.