sbagencyWeb search with RAG // SearchGPTWhy not re-index all web information into a vector database and perform a similarity search and LLM-generation // real-time1d ago1d ago
sbagencyLLMs reasoning // knowledge representationFor a man with a hammer (LLM), everything starts to look like nails (texts)4d ago4d ago
sbagencyData quality & preparation // key success factor in AI/NLP/RAGBoring , but true— “garbage in, garbage out”, “gold in, gold out”:)5d ago5d ago
sbagencyAI agents as the interface to the digital world // hackathonThe event kicked off with excitement, featuring over 20 prizes and a focus on innovative developments in AI and agents. The main speaker, a…6d ago6d ago
sbagencyKnowledge graphs // look beautiful, but are they useful?Knowledge graphs are a very limited form of knowledge representation (The loss of many aspects, details) compared to natural language6d ago6d ago
sbagencyBetter reasoning with augmented generation // Reasoning + RAGIRCoT — Interleaving Retrieval with CoT Reasoning6d ago6d ago
sbagencyCatastrophic Forgetting // is FT isn’t the answer/solution?LLMs/NNs suffer from suboptimal weight manipulation but there are some techniques to improve itJul 20Jul 20
sbagencyKnowledge/language maps // better answers for LLM/RAGNaive RAG does not work well // a new (old) method using “language maps” is proposed to improve quality, but it looks like old good…Jul 20Jul 20
sbagencyWhy AI-Agents? // compound & extensible, not monolithic limitedAgents are an abstraction that provides unlimited capabilities to solve real-world tasks // plan, act, analyze (reflect, memorize, etc.)…Jul 19Jul 19