Seattle Skeptics on AI

Tamara Weed, Aug, 2 2026

Explore the key differences between BERT and GPT architectures. Learn why encoder-only models excel at understanding while decoder-only models dominate text generation, and how to choose the right one for your NLP project.

Tamara Weed, Aug, 2 2026

Explore the key differences between BERT and GPT architectures. Learn how encoder-only and decoder-only models impact NLP tasks, performance, and implementation costs.

Tamara Weed, Aug, 1 2026

Learn comparative prompting: a proven technique to ask AI for structured options, trade-offs, and recommendations. Improve decision quality by 73% with specific criteria.

Tamara Weed, Jul, 31 2026

A practical guide to detecting, containing, and remediating harmful LLM outputs, focusing on bias, fairness, and prompt injection attacks.

Tamara Weed, Jul, 30 2026

Discover how generative AI is transforming construction bids, schedules, and safety plans. Learn about tools like ALICE and nPlan that optimize timelines, reduce risks, and enhance safety through predictive analytics.

Tamara Weed, Jul, 29 2026

Learn how to build a winning Enterprise LLM Strategy Roadmap in 2026. Discover the 5-phase implementation process, governance best practices, and cost-control tactics to scale AI successfully.

Tamara Weed, Jul, 28 2026

Explore architectural standards for vibe-coded systems. Learn how reference implementations and strict governance prevent technical debt and security risks in AI-generated software.

Tamara Weed, Jul, 27 2026

Navigate the legal complexities of generative AI in 2026. Learn how fair use, licensing deals, and data provenance impact your business strategy and copyright compliance.

Tamara Weed, Jul, 26 2026

Explore the critical risks of prompt injection in LLMs. Learn how attackers exploit semantic ambiguity, common attack vectors like jailbreaks and stored injections, and practical defense strategies including context partitioning and input filtering.

Tamara Weed, Jul, 25 2026

Discover how generative AI is revolutionizing automotive design, diagnostics, and in-car experiences. Learn about real-world applications, challenges, and future trends shaping the industry.

Tamara Weed, Jul, 24 2026

Compare NVIDIA A100, H100, and CPU offloading for LLM inference. Learn about performance differences, cost-efficiency, and when to choose each option for your AI infrastructure.

Tamara Weed, Jul, 23 2026

Learn how to build custom benchmarks for enterprise LLMs. Move beyond generic metrics to evaluate tone, compliance, and task success with practical steps and LLM-as-a-Judge techniques.