Hacker Newsnew | past | comments | ask | show | jobs | submit | from login

Agentic Search Models (softwaredoug.com) 2 points by Tomte 2 days ago | past | discuss Semantic Search Without Embeddings (softwaredoug.com) 3 points by fagnerbrack 2 days ago | past | discuss Can agents replace the search stack? (softwaredoug.com) 3 points by gmays 10 days ago | past | discuss Can agents replace the search stack? (softwaredoug.com) 3 points by speckx 16 days ago | past Is grep all you need for agentic search? (softwaredoug.com) 4 points by ingve 38 days ago | past Semantic Search Without Embeddings (softwaredoug.com) 4 points by handfuloflight 41 days ago | past The tests are the code now (softwaredoug.com) 7 points by zdw 64 days ago | past | 2 comments Reasoning boosts search relevance 15-30% (softwaredoug.com) 3 points by gmays 66 days ago | past Can BM25 Be a Probability? (softwaredoug.com) 4 points by Tomte 69 days ago | past | 2 comments Ralph, too, needs a test train split (softwaredoug.com) 3 points by JnBrymn 3 months ago | past Train Ralph Like an ML Model (softwaredoug.com) 1 point by softwaredoug 3 months ago | past Hyperfocus vs. Perspective as a Staff Engineer (2023) (softwaredoug.com) 2 points by softwaredoug 3 months ago | past Semantic Search Without Embeddings (softwaredoug.com) 4 points by softwaredoug 4 months ago | past Orthogonality Expected at High Dimensions (2022) (softwaredoug.com) 3 points by softwaredoug 4 months ago | past RAG Isn't a Vector Search Problem (softwaredoug.com) 4 points by JnBrymn 5 months ago | past RAG users want affordances, not vectors (softwaredoug.com) 2 points by Tomte 5 months ago | past Liberating Search from the Search Engine (softwaredoug.com) 3 points by softwaredoug 6 months ago | past | 1 comment LLM Judges aren't the shortcut you think (softwaredoug.com) 2 points by speckx 6 months ago | past LLM As A Judge is not the shortcut you think (softwaredoug.com) 1 point by softwaredoug 6 months ago | past An agent-coded search reranker (softwaredoug.com) 1 point by softwaredoug 6 months ago | past General purpose agentic loop in 40 lines of Python (softwaredoug.com) 2 points by freediver 6 months ago | past General purpose agentic loop in 40 lines of Python (softwaredoug.com) 3 points by softwaredoug 7 months ago | past Do well-written, clear instructions beat few-shotting for tiny-LLMs? (softwaredoug.com) 2 points by sebg 7 months ago | past Reasoning boosts search relevance 15-30% (softwaredoug.com) 3 points by JnBrymn 7 months ago | past Agents turn simple keyword search into compelling search experiences (softwaredoug.com) 67 points by softwaredoug 7 months ago | past | 35 comments BM25F from Scratch (softwaredoug.com) 3 points by softwaredoug 7 months ago | past The scapegoats guide to organizational 'transformation' (softwaredoug.com) 3 points by JnBrymn 8 months ago | past Do well-written, clear instructions beat few-shotting for tiny-LLMs? (softwaredoug.com) 3 points by zdw 8 months ago | past OpenAI lost the plot on 'boring' LLM use-cases (softwaredoug.com) 3 points by mooreds 8 months ago | past OpenAI has lost the plot on boring LLM use cases (softwaredoug.com) 1 point by softwaredoug 8 months ago | past More

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: