Hackernews posts about LLM/RAG

1. Show HN: Home Page as a Chatbot (github.com)
   1 points by vladoh 2 days ago | discuss
2. Show HN: A 150M model that extracts verbatim evidence spans for RAG, no LLM call (huggingface.co)
   6 points by justacoolname 26 days ago | discuss
3. Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion (github.com)
   381 points by engomez 11 days ago | 173 comments
4. Attribute Knowledge RAG Pattern for Governed AI Agents (superml.dev)
   2 points by bps1418 about 5 hours ago | discuss
5. Compress tool outputs, logs, files, RAG chunks before LLM for 60-95% less tokens (github.com)
   4 points by gmays 17 days ago | discuss
6. Ask HN: The next evolutionary step in LLM usage?
   3 points by tomaytotomato 26 days ago | 2 comments
7. Show HN: Local RAG memory system that AI can write directly to (github.com)
   3 points by ptobey 23 days ago | 1 comments
8. Bayer's PRINCE: a production agentic RAG system (martinfowler.com)
   4 points by logickkk1 20 days ago | discuss
9. Show HN: Discover content in any YouTube channel with RAG (askchannel.ai)
   3 points by nexus2045 9 days ago | discuss
10. Ragit – chat with any folder of documents using a local LLM (github.com)
    2 points by atshu21 6 days ago | discuss
11. Show HN: BetterDB, MIT Valkey-native context layer for AI agents (github.com)
    5 points by kaliades 10 days ago | 1 comments
12. Superintellignce is still decades away
    3 points by lamprouge 7 days ago | 1 comments
13. Show HN: Sibyl – self-hosted cross-agent memory for AI coding agents (github.com)
    3 points by hyperb1iss 6 days ago | discuss
14. Show HN: Models Pie – LLMs ranked by fast / cheap / good tradeoffs (modelspie.com)
    4 points by willks 19 days ago | 1 comments
15. An LLM verifier rated math proofs near-perfect; an expert found 17% correct (korbonits.com)
    3 points by korbonits 11 days ago | discuss
16. Show HN: WifeBench – My wife vibes LLM rankings (www.wifebench.com)
    2 points by fristovic 2 days ago | discuss
17. Testing 67 Models: Combining LLMs Rarely Beats the Best Single Model (huggingface.co)
    2 points by josefchen 10 days ago | discuss
18. Combining LLMs Rarely Beats the Best Single Model, I tested 67 frontier models (arxiv.org)
    1 points by josefchen 10 days ago | discuss
19. LLM KOSH (github.com)
    2 points by rastogivaibhav 6 days ago | discuss
20. High Performance Distributed Inference with Ray Serve LLM (www.anyscale.com)
    3 points by robertnishihara 18 days ago | discuss
21. UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs (arxiv.org)
    2 points by matt_d 24 days ago | discuss
22. Show HN: Preseason.ai – Open-source benchmark of devtool choices, ranked by LLM (www.preseason.ai)
    2 points by widenrun 29 days ago | discuss
23. Show HN: Have your agent consult other models (github.com)
    3 points by rane 23 days ago | 1 comments
24. Consult-LLM – A second opinion from another model right in your existing agent (github.com)
    2 points by tiahura 4 days ago | discuss
25. Show HN: Crespo – Tree-sitter AST blueprints instead of raw code for LLMs (github.com)
    14 points by ByteJoseph 15 days ago | 1 comments
26. Measuring Search Ranking Quality with LLM Judged NDCG (corvi.careers)
    2 points by sp1982 13 days ago | discuss
27. Ask HN: Releasing code under AGPLv3, but want to block LLM reconstruction?
    5 points by zionsati 26 days ago | 3 comments
28. Show HN: Codify – Terraform for Dev Environments (codifycli.com)
    3 points by kevinwang5658 21 days ago | discuss
29. The LLM industry must keep the RAM prices at absurd levels (infosec.exchange)
    4 points by ndr42 18 days ago | discuss
30. Show HN: AdvertBench, ranking the ability of LLMs to create image ads (advertbench.com)
    3 points by joegibbs 16 days ago | discuss