Seattle Skeptics on AI

Tamara Weed, Aug, 13 2026

Cut LLM costs by 30-80% without losing quality. Learn proven architectural strategies like model routing, semantic caching, and right-sizing to optimize your AI budget effectively.

Tamara Weed, Aug, 12 2026

Discover how sampling choices like temperature and nucleus sampling directly influence LLM accuracy and hallucination rates. Learn practical strategies to optimize your AI outputs.

Tamara Weed, Aug, 11 2026

Explore how model parallelism and pipeline parallelism enable training of massive AI models by splitting networks across GPUs. Learn about scheduling strategies, hybrid approaches, and real-world implementation challenges.

Tamara Weed, Aug, 10 2026

Compare vibe coding and agentic systems to choose the right AI autonomy level for your software projects. Learn when to use conversational AI vs autonomous agents.

Tamara Weed, Aug, 9 2026

Learn how to effectively prompt AI for performance profiling and optimization plans. Discover structured techniques to identify bottlenecks, interpret profiler data, and implement actionable code improvements.

Tamara Weed, Aug, 8 2026

Master product management for generative AI. Learn how to scope non-deterministic features, define reliable MVPs, and track hybrid metrics that prove business value.

Tamara Weed, Aug, 7 2026

Discover why longer prompts often hurt LLM output quality. Learn the science behind attention bottlenecks, recency bias, and how to optimize prompt length for better accuracy and lower costs.

Tamara Weed, Aug, 6 2026

Learn how to design secure authentication flows using OAuth 2.0, SSO, and MFA. Discover best practices for prompting controls, managing sessions, and balancing security with user experience.

Tamara Weed, Aug, 5 2026

Explore how GPUs, NPUs, and edge devices accelerate multimodal generative AI. Learn about hardware constraints, optimization techniques, and the future of unified AI architectures.

Tamara Weed, Aug, 4 2026

Explore Safety by Design in Generative AI, a framework by Thorn and partners like NIST that embeds protections into product architecture. Learn how to prevent CSAM and other harms through proactive development, deployment, and maintenance strategies.

Tamara Weed, Aug, 4 2026

Explore Safety by Design in Generative AI, a framework by Thorn and NIST that embeds protections into product architecture to prevent harm like CSAM, moving beyond reactive filters to proactive engineering.

Tamara Weed, Aug, 3 2026

Learn how to scale marketing content using generative AI for product descriptions, emails, and social posts. Discover top tools, best practices, and how to maintain brand voice in 2026.