BRICS AI Economics

Tag: large language models

post-image
Nov, 3 2026

Prompt Engineering for LLMs: Core Principles and Proven Patterns

Emily Fies
5
Master prompt engineering for LLMs with core principles like specificity and context. Learn proven patterns including few-shot, chain-of-thought, and role assignment to boost AI accuracy.
post-image
Oct, 7 2026

Curriculum and Blending: How to Mix Datasets for Better Large Language Models

Emily Fies
9
Discover how curriculum learning and dataset blending optimize LLM training. Learn strategies for ordering data, measuring difficulty, and improving performance without extra compute.
post-image
Oct, 4 2026

Self-Attention in Transformers: How LLMs Understand Context

Emily Fies
5
Discover how self-attention powers Large Language Models. Learn the QKV framework, multi-head mechanics, and why this 2017 innovation revolutionized AI understanding.
post-image
Oct, 1 2026

Context Windows in LLMs: Limits, Trade-Offs & Best Practices

Emily Fies
0
Explore how LLM context windows work, from token limits to hardware constraints. Learn why bigger isn't always better and discover best practices for managing long conversations and documents efficiently.
post-image
Sep, 29 2026

Document Re-Ranking: Boosting RAG Relevance for LLMs

Emily Fies
5
Boost RAG accuracy with document re-ranking. Learn how cross-encoders solve vector search limitations, improve LLM factuality, and optimize retrieval pipelines.
post-image
Sep, 18 2026

Multi-Turn Conversations with LLMs: Managing Conversation State

Emily Fies
10
Discover why LLMs fail in multi-turn chats and how to fix it. Learn about loss masking, Review-Instruct, and strategies to manage conversation state for reliable AI.
post-image
Aug, 9 2026

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

Emily Fies
10
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.
post-image
Aug, 7 2026

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

Emily Fies
5
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.
post-image
Jul, 30 2026

How Large Language Models Use Probabilities to Choose Words and Phrases

Emily Fies
0
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.
post-image
Jul, 18 2026

Causal vs Bidirectional Attention: Tradeoffs in Modern LLMs

Emily Fies
7
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.
post-image
Jun, 28 2026

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

Emily Fies
5
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.
post-image
Jun, 22 2026

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

Emily Fies
0
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.

Categories

Latest Courses

Popular Tags