思想与社会2021 · 分享于 Hacker News
RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
探索《RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yjiayuanzhang ·
Show HN: I made a better Perplexity for developers
185 赞同75 评论
Yslyall ·
What I learned using private LLMs to write an undergraduate history essay
123 赞同81 评论
Ybschmidt1 ·
Show HN: Ragdoll Studio (fka Arthas.AI) is the FOSS alternative to character.ai
95 赞同24 评论
Ysamwillis ·
Anthropic - Introducing 100K Token Context Windows, Around 75,000 Words
69 赞同24 评论
Yzone411 ·
Grok
21 赞同16 评论
Yyla92 ·
Headstart accelerates software development by up to 100x with Claude
15 赞同35 评论
Ymakaimc ·
Emerging Architectures for LLM Applications
13 赞同7 评论
Yreachableceo ·
Is anyone using self hosted LLM day to day and training it like a new employee
6 赞同0 评论
Yjiayuanzhang ·
Show HN: Devv – AI search engine for devs, built on a custom search index
6 赞同7 评论
Ytosh ·
GPU-Accelerated LLM on a $100 Orange Pi
5 赞同0 评论
Yczue ·
How do domain-specific chatbots work? A retrieval augmented generation overview
3 赞同1 评论
Yjinqueeny ·
Teach your LLM to answer with facts, not fiction
2 赞同0 评论
Yartex_xh ·
Jina AI Launches First Open-Source 8K Text Embedding, Rivaling OpenAI
2 赞同0 评论
Yteleforce ·
RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
2 赞同0 评论
Yemil_sorensen ·
We taught a small LLM to throw away 68% of our RAG context
2 赞同0 评论
Ycl42 ·
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
1 赞同0 评论
YGeorgeDewar ·
Wolfram Alpha as the Way to Bring Computational Knowledge Superpowers to ChatGPT
1 赞同0 评论
Yswyx ·
How to implement Q&A against your docs with GPT3 embeddings and Datasette
1 赞同0 评论