Your vector search cannot tell "which services use Redis" from "which services do NOT use Redis". Both embed to nearly the same point, because the model encodes the topic and not the logic.Same blind spot hits exact identifiers like ERR_CONNECTION_REFUSED or JIRA-4521, multi-hop questions, and anything time scoped.Not a bug in your index, it is what embeddings are. Hybrid search, metadata filters and reranking are the patches.https://www.adaptiverecall.com/vector-search/#RAG #AI
Related
The boy who cried….. I’ve shit my pants again. Does anyone even listen to him anymore? #brexit #BrexitLies #politics #to...
The boy who cried….. I’ve shit my pants again. Does anyone even listen to him anymore? #brexit #BrexitLies #politics #toryscum #tories #conservatives #ukpolitics #bbc #news #EU #La...
Human Interface Guidelines from various platformsArticle URL: https://unsung.aresluna.org/i-think-theres-a-lot-of-value-...
Human Interface Guidelines from various platformsArticle URL: https://unsung.aresluna.org/i-think-theres-a-lot-of-value-in-these/ Comments URL: https://news.ycombinator.com/item?id...
"Expert Witness" who did nothing but use ChatGPT to make stuff up. 😬 https://infosec.exchange/@josephcox/117111490746162...
"Expert Witness" who did nothing but use ChatGPT to make stuff up. 😬 https://infosec.exchange/@josephcox/117111490746162211#AI #chatgpt #law