Applied LLMs
Putting language models to work: retrieval, prompting, evaluation and the behavior you only learn in production.
Best notes
- What stays valuable when anyone can build anything
As AI makes building cheap, value concentrates in judgment (inside) and trust (outside): the two inputs it cannot mass-produce. A lens on what to own in the AI era.
- Better engineering
A personal take on how AI is changing software development and why better engineering still comes down to human judgment, not just better tools.
- Composing the Dwarves video pipeline
A behind-the-scenes look at how we built our video pipeline for long-form explainers and short-form content, from script to screen, with AI in the loop.
- AI-powered consulting sprints for rapid clarity
AI-powered consulting sprints for rapid clarity and breakthrough
- Building a scalable social listening data pipeline
We partnered with Plot to build a robust data pipeline that processes millions of social media posts daily, providing AI-powered insights into brand performance.
Reports
- Composing the Dwarves video pipeline
A behind-the-scenes look at how we built our video pipeline for long-form explainers and short-form content, from script to screen, with AI in the loop.
Case studies
- AI-powered consulting sprints for rapid clarity
AI-powered consulting sprints for rapid clarity and breakthrough
- Building a scalable social listening data pipeline
We partnered with Plot to build a robust data pipeline that processes millions of social media posts daily, providing AI-powered insights into brand performance.
Writing
- What stays valuable when anyone can build anything
As AI makes building cheap, value concentrates in judgment (inside) and trust (outside): the two inputs it cannot mass-produce. A lens on what to own in the AI era.
- Better engineering
A personal take on how AI is changing software development and why better engineering still comes down to human judgment, not just better tools.
- Engineers in the AI landscape: architects, tinkerers, planners, and the vibers
Exploring the new archetypes of software engineers in the age of AI: architects, tinkerers, planners, and vibers.
- Skillmaxing
A guide for talents on how to cultivate the mindset and skills to become a proven, AI-augmented engineer, inspired by the principles of vetting top-tier individuals.
Research notes
- How to use Claude to build the system prompt
Building the use case: how to use Claude to build the system prompt
- Prompt formula
Most prompts fail because they lack structure, but a six-part formula transforms vague requests into precise AI instructions. The difference lies in knowing which…
- Mental models for prompting
Essential mental models to improve your LLM interactions and prompt engineering effectiveness
- Natural language to database queries: Text-to-MongoDB
An exploration of natural language to database query systems using MongoDB, examining system prompts and implications for data engineering and agentic workflows.
- Model selection
Learn how to choose the right AI model for your needs. Explore key factors like accuracy, privacy, and cost. Compare commercial vs open-source options and API vs…
- Evaluation guidelines for LLM applications, part 1: the evaluation checklist
A product evaluation checklist and the business and user expectations to settle before integrating a third-party LLM into an application.
- Evaluation guidelines for LLM applications, part 2: types of evaluation and considerations
The difference between model evaluations and product evaluations, plus coverage, monitoring, user feedback and when fine-tuning is needed.
- Prevent prompt injection
Nowadays, Large Language Models (LLMs) have become integral to various applications. However, with great power comes great responsibility, and the rise of LLMs has…
Show all 42 notes
- Evaluating caching in RAG systems
Caching is a vital technique that boosts performance by storing frequently accessed information. Let's see how it works with RAG. In this article, we will know how cache…
- Evaluating search engine in RAG systems
Hybrid search comes to solving problems in vector search and full-text search. Let's see how it works. In this article, we will know how hybrid search approach and how…
- Streamlining internal tool development with managed LLMOps: A Dify case study
Discover how managed LLMOps platforms like Dify streamline the development of AI-powered internal tools. Learn about the challenges of integrating LLMs, the benefits of…
- Thumbs up and thumbs down pattern
The article talks about how important human feedback is for making large language models better, especially using thumbs up and down. It explains the Pearson correlation…
- Design feedback mechanism for LLM applications
Improving AI models requires collecting accurate user feedback,which can be difficult. The article explores more into the importance of collecting human feedback and…
- A grand unified theory of the AI hype cycle
An exploration of the cyclical nature of AI development, tracing the rise and fall of new technologies within the field, and how this pattern has repeated throughout…
- Choosing a vector database for LLM applications
An overview of vector databases and their application in LLM systems. This article covers the history and core concepts of vector databases, their use cases,…
- LSTM
Long Short-Term Memory (LSTM) networks are a crucial advancement for sequential data, addressing the exploding and vanishing gradient problems in traditional RNNs. This…
- Quantization for large language models
As large language models (LLMs) continue to evolve, their parameter counts grow exponentially, with some models reaching trillions of parameters. This exponential growth…
- GraphRAG - building a knowledge graph for RAG system
In baseline Retrieval Augmented Generation (RAG), sometimes the result might not be accurate as expected since the query itself have multiple layers of reasoning or the…
- Guardrails in llm
Inspite of having strength to process and produce highly coherent human-like, behavior of LLM is unpredictable, so the need of a safety mechanisms and boundaries that…
- ReAct(reason + act) in LLM
Working with Large Language Models (LLMs) may seem straightforward at first glance. Initially, we might think that simply prompting the AI model with a task is…
- ReWOO: Reasoning without observation - a deeper look
In the process of improving Large Language Model (LLM) performance, many techniques have been proposed. The Augmented Language Model (ALM) approach boosted LLM accuracy…
- Logging
Logs are like the footprints of your LLM, tracking every move it makes. We will look at how logging can help you see beneath the top layer of a system, which can help…
- Metrics
Metrics give you the rundown on how your LLM’s performing. We will show how to use these metrics to identify issues, increase efficiency, and make changes for improved…
- Tracing
Tracing is like following your LLM’s journey, step by step. We will explain how tracing makes it easy to identify and address problems by allowing you to track the…
- Intent classification by LLM
User intent classification is a crucial aspect of conversational AI, start with machine learning models, but now advanced language models (LLMs) are being explored for…
- LLM as a judge
With the robust growth of LLM models currently, there is a new method is used to evaluate the performance of large language models (LLMs): LLM-as-a-Judge, also known as…
- Use cases for LLM applications
Explore the diverse applications of large language models (LLMs) and AI in both enterprise and consumer sectors. Learn about key use cases across data analysis, content…
- The rise of AI applications with LLM
Discover how the rapid surge in artificial intelligence, led by models like ChatGPT, Claude, and Gemini, is reshaping industries and democratizing AI development. This…
- Journey of thought prompting: Harnessing AI to craft better prompts
Journey of Thought Prompting is an innovative technique that leverages AI to craft more effective prompts for large language models. This approach uses the analytical…
- What is Generative UI?
An introduction to Generative UI (genUI), a user interface that generates interactive elements in response to user needs using AI, enhancing UX in chat applications. The…
- Proximal policy optimization
Proximal policy optimization (PPO) is an algorithm that aims to improve the stability of training by avoiding overly large policy updates. It is a popular and effective…
- Multimodal: in rag
In spite of having taken the world by storm, Large Language Models(LLM) still has some limitations such as limited context window and a knowledge cutoff date.…
- History of structured outputs for LLMs
When Large Language Models (LLMs) becomes popular and an essential tool for growing businesses, it signals a transition toward more complex and efficient data…
- Developing rapidly with generative AI
Generative AI overview and the different stages of building an LLM-powered feature
- A story map for building with LLMs
A comprehensive guide outlining the journey for engineers developing applications on top of Large Language Models (LLMs), covering key stages from understanding AI…
- Adversarial prompting in prompt engineering
An overview of adversarial prompting in prompt engineering, focusing on understanding risks associated with Large Language Models (LLMs) and strategies for mitigating…
- LLM's accuracy - self refinement
An overview of self-refinement, a technique where Large Language Models (LLMs) evaluate and improve their own output without the need for supervised data or…
- Reward model
A Reward model is a critical component in Reinforcement Learning for Large Language Models (LLMs), designed to evaluate and score the quality of generated responses. It…
- Q learning
An introduction to Q-learning, a model-free reinforcement learning algorithm used to learn optimal policies in Markov Decision Processes.
- Building blocks of a RAG pipeline
How chunking, hierarchical tree summaries, re-ranking, query caching and vector-store chat memory fit together around a vector database in an LLM application.
- Introduction to reinforcement learning and its application with LLMs
An introduction to Reinforcement Learning (RL), a machine learning method where an agent learns to make decisions by interacting with an environment. This article covers…
- Foundation models: the latest advancement in AI
An overview of foundation models, their versatility in generative AI tasks, and their impact across various domains like NLP, image generation, and scientific research.…
Playbooks
- Create slides with Overleaf and ChatGPT
This article shares a workflow for making slide decks with Overleaf and ChatGPT. It solves issues like slow content creation using ChatGPT and formats with Overleaf’s…
Series
Tags in this topic
Writers
nnhuyhoang10, datnguyennnx9, monotykamary9, zlatanpham9, tieubao7, thanhpn5, innnotruong2, lmquang2