Sitemap - 2024 - Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots

Agentic X

Structural Advancements Developed for Language Models to Support Application Creation

The Shifting Vocabulary of AI (Updated)

Large Behaviour Models

How Did We Go From Large Language Models to Large Behaviour Models?

Safety Challenges For Generative AI Agents In Autonomous Machines

The Evolution of AI Agents & Agentic Systems

LLaVA-o1

Anthropicโ€™s Claude 3.5 Computer Use Framework (AI Agent)

xAI UI & Management Console

Revolutionising AI Agents With Computer Use Tools

Six Years Of Prompt Engineering

The Focus Is Shifting From AI Agents To AI Agent Tool Use

Four Levels of RAG โ€” Research from Microsoft

Building Conversational AI Agents By Integrating Reasoning, Speaking & Acting With LLMs

What Defines An AI Agent?

Adversarial Attacks On ๐—”๐—œ ๐—”๐—ด๐—ฒ๐—ป๐˜ ๐—–๐—ผ๐—บ๐—ฝ๐˜‚๐˜๐—ฒ๐—ฟ ๐—œ๐—ป๐˜๐—ฒ๐—ฟ๐—ณ๐—ฎ๐—ฐ๐—ฒ๐˜€ (๐—”๐—–๐—œ) ๐˜ƒ๐—ถ๐—ฎ ๐—ฃ๐—ผ๐—ฝ-๐—จ๐—ฝ๐˜€

Language Models Emerging Technologies

Anthropic ACI (AI Agent Computer Interface)

Whatโ€™s Your Definition Of An AI Agent?

Make Every Application An AI Agent

Contrasting RPA, Chatbots & AI Agents

AI Agent Computer Interface (ACI)

The Advent Of Open Agentic Frameworks & Agent Computer Interfaces (ACI)

Windows Agent Arena (WAA)

UI-Focused AI Agent

Judging AI Agents

AI Agents Beyond The Screen

Language Model Categorisation

5 Levels Of AI Agents (Updated)

OpenAI Prompt Caching

Demystifying Large Language Model Function Calling

OpenAI o1 Reasoning Models

LLM Symbolic Reasoning For Visual AI Agents

Chain-Of-Symbol Prompting To Improve Spatial Reasoning

Real-World Agentic Applications

The Role of Small Models in the LLM Era

Small Language Model (SLM) Efficiency, Performance & Potential

ChainBuddy

AgentLite Is A Lightweight Framework for Building AI Agents

Outline-Driven RAG & Web Research Prototype

The Evolution of Grounding & Planning In AI Agents

The Shifting Vocabulary of AI

An AI Agent Architecture & Framework Is Emerging

Emergence of Large Action Models (LAMs) and Their Impact on AI Agents

Large Action Models

Strategic Chain-of-Thought (SCoT)

The Shift From Large Language Models to Smaller, Vision-Enhanced Models & The Rise of AI Agentsโ€” Version 6

Agentic Discovery

AI Agents

AI Web Agents

Small Language Models Supporting Large Language Models

The History & Future of Prompt Engineering

Simplifying LLM Optimisation

Agentic Discovery

Seeding GPT-4o-mini Using Fine-Tuning

Dialog Flow Generation To Constrain LLM-Based Chatbots

AppAgent v2 With Advanced Agent for Flexible Mobile Interactions

Multi-Modal Agentic Applications

Flows Are So Back

Fine-Tuning OpenAI GPT-4o mini

27 Unique Dev Challenges: A Recent Study Explored the Top Challenges Faced by LLM Developers

LangGraph Agents By LangChain

WeKnow-RAG

AI Agents With Human In The Loop

AI Agent Evaluation Framework From Apple

RAG Foundry By Intel

OpenAI Enhanced Their API With Robust Structured Output Capabilities

AI Agents

Agent AI: Agentic Applications Are Software Systems With A Foundation Model AI Backbone & Defined Autonomy via Tools

LLM-Driven Synthetic Data Generation, Curation & Evaluation

Creating Synthetic Training Data

OpenAI Acquired Rockset

LangGraph Introduced SubGraphs

AI Agents: Exploring Agentic Applications

LangChain Based Plan & Execute AI Agent With GPT-4o-mini

LangChain Search AI Agent Using GPT-4o-mini

Large Language Model Use & Augmentation

WebVoyager AI Agent

GPT-4o mini

RAG Implementations Fail Due To Insufficient Focus On Question Intent

Agentic AI: Creating An AI Agent Which Can Navigate The Internet

AgentInstruct Uses Agentic Flows To Create Synthetic Training Data

LangSmith, LangGraph Cloud & LangGraph Studio

Speculative RAG By Google Research

Moving From Natural Language Understanding To Mobile UI Understanding

Teaching Small Language Models to Reason

Our Human Creativity Is Becoming More Uniform Due To ChatGPT

Evaluating The Quality Of RAG & Long-Context LLM Output

LLM Disruption in Chatbot Development Frameworks

TinyStories Is A Synthetic DataSet Created With GPT-4 & Used To Train Phi-3

LangGraph Studio From LangChain

LangGraph Cloud

LangChain Just Launched LangGraph Cloud

RAG Survey & Available Research

TinyStories

FlowMind Is An Automatic Workflow Generator

Can Conversation Designers Excel As Data Designers?

Phi-3 Is A Small Language Model Which Can Run On Your Phone

LangGraph From LangChain Explained In Simple Terms

DR-RAG: Applying Dynamic Document Relevance To Question-Answering RAG

Creating A Benchmark Taxonomy For Prompt Engineering

Language Agent Tree Search โ€” LATS

Tree Of Thoughts Prompting (ToT)

Using Fine-Tuning To Imbed Hidden Messages In Language Models

Implementing Chain-of-Thought Principles in Fine-Tuning Data for RAG Systems

Assertions Are Like Guardrails for LLM Apps

RAGTruth

DSPy & The Principle Of Assertions

Using DSPy For A RAG Implementation

An Introduction To DSPy

Controllable Agents For RAG With Human In The Loop Chat

How Would The Architecture For An LLM Agent Platform Look?

HILL: Solving for LLM Hallucination & Slop

Teaching LLMs To Say โ€œI donโ€™t Knowโ€

Comparing LLM Agents to Chains: Differences, Advantages & Disadvantages

Can Minor Document Typos Comprehensively Disrupt RAG Retriever & Reader Components?

Enterprise Prompt Engineering Practices

Five Levels Of AI Agents

GALE Is A Next-Gen Generative AI Productivity Suite

The Conversational AI Technology Landscape: Version 5.0

A Short History Of LLMs & Conversational UIs

Large Language Model (LLM) Stack โ€” Version 6

A Short History Of Chatbots

LangChain Chatbot Framework With Retrievers

Building The Most Basic LangChain Chatbot

Data Design For Fine-Tuning LLM Long Context Windows

The Importance Of Granular Data Design For Fine-Tuning

LangChain Structured Output Parser Using OpenAI

Three Considerations For Private Open-Source LLM Instances

Intents Are Not Going Awayโ€ฆRoNID Is A New Intent Discovery Framework

The Large Language Model Landscape โ€” Version 5

LLMs Excel At In-Context Learning (ICL), But What About Long In-context Learning?

Using LLMs For Autonomous Vehicles

Matching Retrieved Context With Question Context Using LogProbs With OpenAI for RAG

Rapid Development Of Intelligent Generative AI APIs

RAG, Hallucination & Structure: Research By ServiceNow

Data Design For Fine-Tuning To Improve Small Language Model Behaviour

No-Code Deployment & Orchestration Of Open-Sourced Foundation Models

LlamaIndex Agent Step-Wise Execution Framework With Agent Runners & Agent Workers

The Case For An AI Productivity Suite

Putting AI To Work

Step-Wise Controllable Agents From LlamaIndex

Improve Conversational UIs Using Social Intelligence

RAG Implementations Are Becoming More Agent-Like

Agentic Search-Augmented Factuality Evaluator (SAFE) For LLMs

FaaF: Facts As A Function For Evaluating RAG

Disambiguation: Using Dynamic Context In Crafting Effective RAG Question Suggestions

FIT-RAG: Are RAG Architectures Settling On A Standardised Approach?

Challenges In Adopting Retrieval-Augmented Generation Solutions

Adaptive-RAG

Retrieval Augmented Fine-Tuning (RAFT)

Complete AI Productivity Suite

DRAGIN: Dynamic RAG Based On Real-Time Information Needs Of LLMs

A New Study Compares RAG & Fine-Tuning For Knowledge Base Use-Cases

A Short History Of RAG

Chain-of-Instructions (CoI) Fine-Tuning & Going Beyond Instruction Tuning

Prompt-RAG

Performing Multiple LLM Calls & Voting On The Best Result Are Subject To Scaling Laws

Please Stop Saying Long Context Windows Will Replace RAG

TinyLlama Is An Open-Source Small Language Model

Agentic RAG: Context-Augmented OpenAI Agents

RAT โ€” Retrieval Augmented Thoughts

LLMs Training SLMs

Exploring the Purpose, Power & Potential of Small Language Models (SLMs)

Large Impact: The Rise of Small Language Models

Large Language Models Excel At In-Context Learning (ICL)

RAG, Data Privacy, Attack Methods & Safe-Prompts

Self-Reflective Retrieval-Augmented Generation (SELF-RAG)

Time-Aware Adaptive RAG (TA-ARE)

Develop Generative Apps Locally

How To Create A LangChain Application That Runs Locally & Offline

Language Model Quantization Explained

Proxy Fine-Tuning LLMs

LLM Drift, Prompt Drift & Cascading

Catastrophic Forgetting In LLMs

Fine-Tuning or RAG?

Leveraging LLM In-Context Learning Abilities

Five Stages Of LLM Implementation [Updated]

Demonstrate, Search, Predict (DSP) for LLMs

T-RAG = RAG + Fine-Tuning + Entity Detection

Run A Small Language Model (SLM) Local & Offline

The Case For Small Language Models

Beyond Chain-of-Thought LLM Reasoning

Comparing Human, LLM & LLM-RAG Responses

Craft Successful Conversational User Interfaces: Align User Intent With Developed Intent

A Benchmark for Verifying Chain-Of-Thought

Seven RAG Engineering Failure Points

OpenAI Agent Query Planning Using LlamaIndex

Corrective RAG (CRAG)

Adding Noise Improves RAG Performance

LLamaIndex Agentic RAG Demo

MultiHop-RAG

Agentic RAG With LlamaIndex

UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue

Chain-of-Symbol Prompting (CoS) For Large Language Models

Prompt-RAG: Vector Embedding Free Retrieval-Augmented Generation

Bulk Data Discovery

Concise Chain-of-Thought (CCoT) Prompting

Visualise & Discover RAG Data

LangSmith by LangChain

Retrieval-Augmented Generation (RAG) vs LLM Fine-Tuning

Understanding LLM User Experience & Expectation

Meta Taxonomy Of Large Language Model Correction & Refinement

Considering Large Language Model Reasoning Step Length

Large Language Model (LLM) SWOT Analysis (Updated)

Chain Of Natural Language Inference (CoNLI)

Validating Low-Confidence LLM Generation

Large Language Model Hallucination Mitigation Techniques

What Is LangChain Expression Language (LCEL)?

Random Chain-Of-Thought For LLMs & Distilling Self-Evaluation Capability

Active Prompting with Chain-of-Thought for Large Language Models

Teaching LLMs To Say, โ€œI donโ€™t knowโ€

Improving Text Embeddings with LLM Generated Synthetic Data

LLM Performance Over Time & Task Contamination