Tag: large language models

Aug, 9 2026

How Autoregressive Generation Works: Step-by-Step Token Production in LLMs

Emily Fies

Explore how autoregressive generation works in large language models. Learn the step-by-step process of token production, causal masking, and the limitations of sequential AI text generation.

Aug, 7 2026

How Think-Tokens Change Generation: Reasoning Traces in Modern Large Language Models

Emily Fies

Explore how think-tokens and reasoning traces transform LLM generation, boosting accuracy by 37% while adding latency. Learn the mechanics, efficiency trade-offs, and optimization strategies for modern AI models.

Jul, 30 2026

How Large Language Models Use Probabilities to Choose Words and Phrases

Emily Fies

Explore how Large Language Models use conditional probability, softmax functions, and decoding strategies like top-p and temperature to choose words. Learn why this statistical approach leads to both impressive creativity and occasional hallucinations.

Jul, 18 2026

Causal vs Bidirectional Attention: Tradeoffs in Modern LLMs

Emily Fies

Explore the critical tradeoffs between causal and bidirectional attention in modern LLMs. Learn how these mechanisms impact performance, speed, and suitability for different AI tasks.

Jun, 28 2026

What Makes a Language Model 'Large': Beyond Parameter Counts and Into Capabilities

Emily Fies

Explore what truly makes a language model 'large' in 2026. From emergent capabilities to Virtual Logical Depth, discover why parameter counts no longer define AI performance.

Jun, 22 2026

Hybrid Recurrent-Transformer Models: Do They Actually Help LLMs?

Emily Fies

Explore how hybrid recurrent-transformer models combine Mamba and attention to solve LLM scaling issues. Learn about sequential vs. parallel designs, real-world examples like Hunyuan-TurboS, and performance trade-offs.

Jun, 10 2026

Semantic Search with LLMs: How AI Transforms Keyword Matching into Intent Understanding

Emily Fies

Discover how Large Language Models transform search from keyword matching to intent understanding. Learn about vector embeddings, query expansion, and re-ranking strategies for building smarter, semantic search systems.

Mar, 27 2026

Robustness and Generalization Tests for Large Language Model Reliability

Emily Fies

Learn essential robustness testing methods for LLMs beyond standard benchmarks, including adversarial stress tests, OOD validation, and real-world deployment readiness.

Feb, 24 2026

Long-Form Generation with Large Language Models: How to Keep Structure, Coherence, and Facts Accurate

Emily Fies

Long-form generation with large language models can produce detailed content, but structure, coherence, and facts often break down. Learn how to guide AI for reliable long-form output using outlines, RAG, and human review.

Feb, 2 2026

How Curriculum and Data Mixtures Speed Up Large Language Model Scaling

Emily Fies

Smart data ordering and mixtures can boost LLM performance by up to 15% without larger models. Learn how curriculum learning works, what mixtures to use, and whether it’s worth the effort for your team.

Jan, 23 2026

Why Transformers Power Modern Large Language Models: The Core Concepts You Need

Emily Fies

Transformers revolutionized AI by letting language models understand context instantly. Learn how self-attention, positional encoding, and multi-head attention power today’s top LLMs - and why they’re replacing older models.

Jan, 23 2026

Why Transformers Power Modern Large Language Models: The Core Concepts You Need

Emily Fies

Transformers revolutionized AI by enabling large language models to understand context across long texts using self-attention. This article explains how they work, why they beat older models, and what’s changing in 2025.

Tag: large language models

How Autoregressive Generation Works: Step-by-Step Token Production in LLMs

How Think-Tokens Change Generation: Reasoning Traces in Modern Large Language Models

How Large Language Models Use Probabilities to Choose Words and Phrases

Causal vs Bidirectional Attention: Tradeoffs in Modern LLMs

What Makes a Language Model 'Large': Beyond Parameter Counts and Into Capabilities

Hybrid Recurrent-Transformer Models: Do They Actually Help LLMs?

Semantic Search with LLMs: How AI Transforms Keyword Matching into Intent Understanding

Robustness and Generalization Tests for Large Language Model Reliability

Long-Form Generation with Large Language Models: How to Keep Structure, Coherence, and Facts Accurate

How Curriculum and Data Mixtures Speed Up Large Language Model Scaling

Why Transformers Power Modern Large Language Models: The Core Concepts You Need

Why Transformers Power Modern Large Language Models: The Core Concepts You Need

Categories

Latest Courses

Biotech and Generative AI: Molecule Generation and Lab Notebooks

Knowledge Management with LLMs: Building Enterprise Q&A Over Internal Documents

Debugging Hallucinated APIs: Prompts That Force Real Dependencies

LLM Portfolio Management Strategy: Balancing APIs, Open-Source, and Custom Models

Tokens and Vocabulary in Large Language Models: How Text Becomes Computation

Popular Tags