• Seattle Skeptics on AI
Seattle Skeptics on AI

Tag: LLM design

How Transformer Architecture Evolved: Key Innovations Since 2017
How Transformer Architecture Evolved: Key Innovations Since 2017

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.

Categories:

Enterprise Technology

Tags:

transformer architecture RoPE embeddings SwiGLU activation LLM design AI model efficiency

Recent post

  • Mixture-of-Experts (MoE) in LLMs: Balancing Cost and Quality
  • Mixture-of-Experts (MoE) in LLMs: Balancing Cost and Quality
  • Portfolio Management for Generative AI Use Cases: Prioritization and Resourcing
  • Portfolio Management for Generative AI Use Cases: Prioritization and Resourcing
  • Memory Planning to Avoid OOM in Large Language Model Inference
  • Memory Planning to Avoid OOM in Large Language Model Inference
  • Why Longer Context Doesn't Always Mean Better AI Output
  • Why Longer Context Doesn't Always Mean Better AI Output
  • Choosing the Right Embedding Model for Enterprise RAG Pipelines
  • Choosing the Right Embedding Model for Enterprise RAG Pipelines

Categories

  • Science & Research
  • Enterprise Technology

Archives

  • June 2026
  • May 2026
  • April 2026
  • March 2026
  • February 2026
  • January 2026
  • December 2025
  • November 2025
  • October 2025
  • September 2025
  • August 2025
  • July 2025

Tags

vibe coding prompt engineering large language models generative AI Large Language Models AI coding tools AI governance transformer architecture LLM security AI compliance data privacy AI development AI coding assistants responsible AI LLM optimization AI coding transformer models AI code security enterprise AI GitHub Copilot

© 2026. All rights reserved.