Cobus GreylingAssertions Are Like Guardrails for LLM AppsDSPy Assertions are a different approach to guardrails, which asserts computational constraints on foundation models.6h ago6h ago
Cobus GreylingRAGTruthIn essence, RAGTruth is a large-scale corpus of naturally generated hallucinations, featuring detailed word-level annotations specifically…3d ago3d ago
Cobus GreylingDSPy & The Principle Of AssertionsIn February 2024, a study introduced Assertions to the DSPy framework. These Assertions serve as both constraints and guides for Language…4d ago4d ago
Cobus GreylingUsing DSPy For A RAG ImplementationRAG enables LLMs to adaptively access real-time knowledge, providing insightful responses beyond their original training. Yet, implementing…5d ago15d ago1
Cobus GreylingAn Introduction To DSPyDeclarative Self-Improving Language Programs (DSPy) aims to separate the program flow from the prompts. While also optimising prompts based…6d ago16d ago1
Cobus GreylingControllable Agents For RAG With Human In The Loop ChatThis demo from LlamaIndex is a good example of how the capabilities of agents and RAG are merging & how HITL can be used to solve for long…May 27May 27
Cobus GreylingHow Would The Architecture For An LLM Agent Platform Look?A recent study explored how LLM-based agent architecture might look in the future. This architecture is segmented into three stages…May 24May 24
Cobus GreylingHILL: Solving for LLM Hallucination & SlopHILL is a prototypical User Interface which highlight hallucinations to LLM users, enabling them to assess the factual correctness of an…May 23May 23
Cobus GreylingTeaching LLMs To Say “I don’t Know”Rather than fabricating information when presented with unfamiliar inputs, models should rather recognise untrained knowledge & express…May 22May 22
Cobus GreylingComparing LLM Agents to Chains: Differences, Advantages & DisadvantagesIn this article I put into plain terms the difference between chains and agents, and what will work best for certain applications.May 21May 21