sbagencyCriticGPT to critique other GPTs //Reinforcement learning from human feedback (RLHF) is fundamentally limited by the capacity of humans to correctly evaluate model output…1d ago1d ago
sbagencyKGs + LLMs // convergence of structured and unstructuredHybrid graph and vector search is the future of RAG5d ago5d ago
sbagencyARC Prize 2024 // $1MJean Piaget, defined intelligence as “what you use when you don’t know what to do.”6d ago16d ago1
sbagencyHallucination-free AI // is it possible?)There are some techniques, like RAG, GraphRAG, Knowledge graphs, etc. to reduce hallucinations…6d ago6d ago
sbagencyAdvanced RAG techniques // for better accuracyRetrieval augmented generation (RAG) is a core function of modern AI pipelinesJun 23Jun 23
sbagencyAI generated content {humanization, detection} // AI detecting AIHumanize AI generated contentJun 20Jun 20
sbagencySmall language models // that can run locallySLMs can solve many problems vs LLMs // security, offline work, latency, low hardware work, etc. but how?Jun 18Jun 18
sbagencyNeurosymbolic AI // both methods united + bonus pack (llm-based reasoning)Think fast and slow (hello Khaleman), statistics and logic can work togetherJun 9Jun 9
sbagencyAI-assisted knowledge mappingLLMs are great tools to process unstructured to structured and vice-versa, build knowledge mapsJun 6Jun 6
sbagencyKnowledge/data extraction/distillation from/with LLMs // Hack LLMsFor many real world apps there is no need to use large models, but LLMs can be used as source of data/knowledge and beyondMay 30May 30