srijansriv
Ask HN: How do we benchmark data extraction, analysis and subsequent enrichment
I have been working on this system that essentially has to extract data from a bunch or structured and unstructured sources, analyse relevance and correctness of the data (im sorry this part is vague) and using the data obtained to fill forms and create write-ups. i do not want to mindlessly use any llm. i want to improve with proof for each of those (broadly, 3) steps. how do we do that? if...
How do I learn robotics in 2025?
i wish to make something. it should be more accessible than ever and the next thing but only the tech giants seem to capture most of the conversation.
Anthropic BsidesSF Challenge
Multimodal Neural Databases
Re:Multimodal Neural Databases
on Tuesday March 19, 2024 @08:49AM (#39755169)
This, specially the nlp part, strikes me as a primitive version of the RAG-LLM pair
Re:Algorithms for Modern Hardware
on Saturday March 16, 2024 @02:20AM (#39723774)
obligatory mention of cp-alogs: https://cp-algorithms.com/index.html
Re:NLP Algorithms for Clustering AI Content Search Keywords
on Wednesday February 21, 2024 @02:31AM (#39451063)
the first thing that comes to mind is CLIP: https://github.com/openai/CLIP
maybe combining it with some sort of knowledge graph is what you're looking for