RAG & Retrieval

Retrieval-augmented generation, embeddings, vector search, memory systems

239 articles across 79 editions

Articles

  1. [Editorial] arXiv:2602.15195 -- 2026-10-07
  2. [Editorial] arXiv:2608.02271 -- 2026-10-07
  3. [Editorial] arXiv:2602.03085 -- 2026-10-07
  4. [Editorial] weightless PR #6: abliteration without redistributing the weights (msuiche) -- 2026-10-07
  5. DEDA – Tracking Dots Extraction, Decoding and Anonymisation Toolkit -- 2026-10-07
  6. [Editorial] arXiv 2610.06783: editor-flagged research paper -- 2026-10-06
  7. Microsoft confirms OpenAI has been using Looped Transformers in the GPT-6 series -- 2026-10-06
  8. I leaked a deliberately wrong answer key to an LLM and told it not to use it. It matched the key in 63% of answers - and denied it 47 out of 47 times when asked. -- 2026-10-06
  9. Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers -- 2026-10-06
  10. Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection -- 2026-10-06
  11. [Editorial] FineEnvs multi-harness-rl (Hugging Face Space) -- 2026-10-06
  12. Welcome RL Environments to the hub -- 2026-10-06
  13. TianyuCodings/JevHarness -- 2026-10-06
  14. tinyhumansai/openhuman -- 2026-10-02
  15. openJiuwen-ai/iCode -- 2026-10-02
  16. overmind-core/overmind -- 2026-10-02
  17. on-panda/on-panda -- 2026-10-02
  18. Bitget attacker tested risk controls with small transfers before $388M theft, CEO says -- 2026-09-29
  19. Characterizing Agentic Flooding of Government Services (arXiv 2608.16603) -- 2026-09-29
  20. [Editorial] AI feature video (YouTube) -- 2026-09-29
  21. [Editorial] Jev's Architecture Unmasked (archerhume.com) -- 2026-09-24
  22. Got jev-like api running natively on ninfer / qwen3.8 27b and results are quite decent -- 2026-09-24
  23. Mods: can we do something about half the forum getting filled with these advertising posts for Jev? -- 2026-09-24
  24. [Editorial] brainstormity post (x.com) -- 2026-09-24
  25. Coding agents pad their diffs to look thorough, and the padding is where the bugs hide -- 2026-09-16
  26. [Editorial] nap (mangit955/nap) -- 2026-09-16
  27. argus-testing/argus -- 2026-09-16
  28. Marmel 0.9.0 -- 2026-09-16
  29. How much of F-Droid is LLM generated? -- 2026-09-15
  30. Qwen3.8-27B-Uncensored-Genesis-V1-GGUF -- 2026-09-15
  31. [Editorial] The Goodies: vehicles proposal (adrianco) -- 2026-09-14
  32. Music Theory for the 21st-Century Classroom -- 2026-09-14
  33. [Editorial] Claude Code artifact -- 2026-09-14
  34. [Editorial] -- 2026-09-11
  35. deepseek-ai/DeepSeek-V4.1-Flash · Hugging Face -- 2026-09-11
  36. Livebench added Deepseek v4.1 flash -- 2026-09-11
  37. Terminal Bench v4 scores -- 2026-09-11
  38. The gap has closed, open source will win -- 2026-09-11
  39. Deepseek V4.1 Flash is 748B, not 552B -- 2026-09-10
  40. [Editorial] YouTube video (T2dnchLabZQ) -- 2026-09-10
  41. We open-sourced Paddock, our Rust/C++ inference engine with its own CUDA kernels (MIT/Apache-2.0) -- 2026-09-10
  42. Rebuilding AUTOMATIC1111 with Gradio Workflow -- 2026-09-10
  43. OpenAI alleged of stealing mathematicians work -- 2026-09-10
  44. [Editorial] YouTube video (tbXKZsodiiw) -- 2026-09-10
  45. [Editorial] YouTube video (OZng1eydHJ8) -- 2026-09-10
  46. Closed AI doesn't like biological research, user turns to open weight models -- 2026-09-10
  47. Why DeepSeek Harness Just Became The Fastest Growing Github Repo EVER -- 2026-09-08
  48. Ruflo Explained: Build an AI Team That Plans, Remembers, Tests, and Improves (Reuven Cohen) -- 2026-09-08
  49. Yaxin9Luo/AutoDesign -- 2026-09-08
  50. microsoft/tgrep: trigram-indexed, client/server grep for very large codebases -- 2026-09-08
  51. continuous diffusion code generation in few steps—or one -- 2026-09-08
  52. Leutenegger/watermarks-remover -- 2026-09-08
  53. [Editorial] GPT-6 Astra: OpenAI Deployment Safety Report -- 2026-09-04
  54. [Editorial] ARC Prize: Astra Evaluation -- 2026-09-04
  55. From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design -- 2026-09-04
  56. 4.5B Posts Scraped from TikTok -- 2026-09-03
  57. Cheap GPS jammers are filling the world with navigation dead zones -- 2026-09-03
  58. [Editorial] LinkedIn post (lnkd.in/p/g_2bhDax) -- 2026-09-03
  59. the agents spent most of their effort forging the audit trail, not doing the hack -- 2026-09-02
  60. Anthropic: Enterprise Frontier Safeguards -- 2026-09-02
  61. 0xwilliamortiz/claude-red -- 2026-09-02
  62. Editor's video pick (YouTube SJ92rOuk9Xc) -- 2026-09-02
  63. Editor's video pick (YouTube QNPwKMOQIKM) -- 2026-09-02
  64. No, Engrams won't let you run 1T models locally. It does something even better. -- 2026-08-31
  65. What is Qwen 3.8 Next Engram usage? -- 2026-08-31
  66. Qwen3.8-Flash-Next turns 4xR9700 into a local AI powerhouse! 120 t/s TG and 12k t/s PP single request with optimized vLLM -- 2026-08-31
  67. Qwen3.8-27b q8 KV cache does seem to actually hurt model performance -- 2026-08-31
  68. sakamakismile/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 -- 2026-08-31
  69. [Editorial] The End of Programming (Paul Dix) -- 2026-08-26
  70. [Editorial] Your Agent Harness Is Not an Orchestration Layer -- 2026-08-26
  71. [Editorial] What's Your Harness? (Balaji Lakshmanan) -- 2026-08-26
  72. Gonna be huge for US open source -- 2026-08-25
  73. Ling-3.0 releases six base checkpoints: tiny and flash across three training stages -- 2026-08-25
  74. you can now use MTP in GLM-Air -- 2026-08-25
  75. Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original -- 2026-08-25
  76. Fun BF16 checkpoint gotcha, +1 followed by -1 isn’t always a round trip -- 2026-08-25
  77. [Editorial] USENIX WOOT '26 Invited Talk Slides (Glosner) -- 2026-08-24
  78. [Editorial] Rumour Is the Exploit -- 2026-08-24
  79. [Editorial] Editor-Curated Video Pick #3 -- 2026-08-24
  80. [Editorial] Qwen3.8-27B-Abliterated-SFT -- 2026-08-20
  81. AliExpress runs silent WebAudio fingerprinting that breaks Bluetooth multipoint -- 2026-08-20
  82. Air Theremin – a browser theremin you play by waving at your webcam -- 2026-08-20
  83. [Editorial] microsandbox — isolate untrusted AI/user code -- 2026-08-19
  84. Free offline check before you install a Claude Skill or MCP server from GitHub/npm -- 2026-08-19
  85. [Editorial] LinkedIn feature -- 2026-08-17
  86. [Editorial] Don't Be the Meat Proxy -- 2026-08-17
  87. [Editorial] Video feature -- 2026-08-17
  88. [Editorial] LinkedIn feature -- 2026-08-17
  89. [Editorial] LinkedIn Post (gRnmQZwQ) -- 2026-08-14
  90. [Editorial] guillaumemeyer/watermarks-remover (GitHub) -- 2026-08-14
  91. Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping -- 2026-08-13
  92. guillaumemeyer/watermarks-remover -- 2026-08-13
  93. Soul-AILab/SoulX-Singer -- 2026-08-13
  94. DMARC Has Been Public Since 2012. 68.4% of Domains Still Don't Enforce It -- 2026-07-31
  95. hoophq/leash -- 2026-07-21
  96. CyberSunil/LLMVault -- 2026-07-21
  97. henryswisvip/mirage -- 2026-07-21
  98. The 'papers, please' era of the internet will decimate your privacy -- 2026-06-27
  99. The Swiss Federal Supreme Court is evaluating Heretic -- 2026-06-27
  100. Heretic Grimoire 1.4: Takedown-Resilient Model Backup — 9KB Reproducible Manifests + IPFS Distribution -- 2026-06-16
  101. z.ai Poll: MIT-Licensed Open Weights Are Losing -- 2026-06-16
  102. How much of Thermo Fisher's antibody data has been manipulated? -- 2026-06-09
  103. News Sites are Blocking Internet Archive over AI Scraping Fears -- 2026-06-09
  104. OneDrive data now has an expiry date -- 2026-06-09
  105. Dopamine Fracking -- 2026-06-09
  106. HiDream-ai/HiDream-O1-Image -- 2026-06-03
  107. How we index images for RAG -- 2026-06-03
  108. The $500K AI Film That "Premiered at Cannes" Was Not in the Official Festival -- 2026-06-02
  109. A 10 year old Xeon is all you need -- 2026-06-02
  110. Inferencing at 10.33 t/s on Qwen 3.5 35B on a $300 laptop -- 2026-06-02
  111. OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension -- 2026-06-02
  112. Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation -- 2026-06-02
  113. Qwen3.6 huge quality gain from Q4 to Q6 for coding agent -- 2026-06-02
  114. [Editorial] -- 2026-05-26
  115. Codex Just Became THE BEST Long Running Agentic Harness -- 2026-05-26
  116. Harnesses -- 2026-05-26
  117. DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost -- 2026-05-26
  118. Archon + Jira: Drag a Ticket, Get a Pull Request (Live Build) -- 2026-05-26
  119. server: fix checkpoints creation by jacekpoplawski · Pull Request #22929 · ggml-org/llama.cpp -- 2026-05-26
  120. [Editorial] -- 2026-05-26
  121. [Editorial] Abliterix — Model Abliteration Tool -- 2026-04-24
  122. [Editorial] Qwen3.6-35B-A3B Abliterix EGA Abliterated -- 2026-04-24
  123. [Editorial] Abliteration Research Paper -- 2026-04-24
  124. FBI used iPhone notification data to retrieve deleted Signal messages -- 2026-04-14
  125. boratanrikulu/gecit - DPI bypass tool (eBPF on Linux, proxy on macOS) -- 2026-04-14
  126. [Editorial] The Witness Stand: Code Quality Under AI -- 2026-03-31
  127. Go Hard on Agents, Not on Your Filesystem (Stanford) -- 2026-03-31
  128. Copilot edited an ad into my PR -- 2026-03-31
  129. [Editorial] -- 2026-03-25
  130. [Editorial] -- 2026-03-25
  131. [Editorial] Your AI Forgot Everything Again — There's a Fix for That -- 2026-03-18
  132. ylytdeng/wechat-decrypt -- 2026-03-18
  133. Source code of Swedish e-government services has been leaked -- 2026-03-14
  134. Bucketsquatting is (finally) dead -- 2026-03-14
  135. E2E encrypted messaging on Instagram will no longer be supported after 8 May -- 2026-03-14
  136. [Editorial] -- 2026-02-26
  137. [Editorial] -- 2026-02-26
  138. [Editorial] -- 2026-02-26
  139. [Editorial] https://github.com/GMaN1911/claude-cognitive -- 2026-01-02
  140. SA-RAG: Using spreading activation to improve multi-hop retrieval in RAG systems -- 2026-01-02
  141. Is there a way to see what is trashing my context? -- 2026-01-02
  142. [Tool] imesde: Zero-GPU, In-Memory Vector Engine for Real-Time Local RAG -- 2025-12-22
  143. I built a Rust-based HTML-to-Markdown converter to save RAG tokens (Self-Hosted / API) -- 2025-12-22
  144. This Week in Security: Hornet, Gogs, and Blinkenlights -- 2025-12-12
  145. timwhitez/MDTCred -- 2025-12-10
  146. [Tool] Tiny MCP server for local FAISS-based RAG (no external DB) -- 2025-12-09
  147. P4nda0s/IDA-NO-MCP -- 2025-12-09
  148. Code Embeddings vs Documentation Embeddings for RAG in Large-Scale Codebase Analysis -- 2025-12-08
  149. smallevals - Tiny 0.6B Evaluation Models and a Local LLM Evaluation Framework -- 2025-12-05
  150. I built a real-time RAG visualizer for pgvector because debugging invisible chunks is a nightmare -- 2025-12-03
  151. Built a local MCP Hub + Memory Engine for Ollama — looking for testers -- 2025-12-03
  152. RAG follow-ups not working — Qwen2.5 ignores previous context and gives unrelated answers -- 2025-11-26
  153. Turns out LLM's can be consistent ..! -- 2025-11-19
  154. AI Safety Evaluation! -- 2025-11-19
  155. messkan/rag-chunk -- 2025-11-19
  156. I was tired of guessing my RAG chunking strategy, so I built rag-chunk, a CLI to test it. -- 2025-11-17
  157. vaspike/agtok -- 2025-11-17
  158. Heartbeats in Distributed Systems -- 2025-11-17
  159. Migrating from Gitea to Codeberg -- 2025-11-17
  160. I built a RAG as a Service orchestrator for local models -- 2025-11-14
  161. Fine-Tuning SLMs and Running Them Securely in Your Web Browser -- 2025-11-14
  162. I took a deep dive into ChatGPT's web_search API to learn how to get my content cited. Here's what I found. -- 2025-11-14
  163. [Editorial] https://arxiv.org/pdf/2506.21734 -- 2025-11-11
  164. OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval -- 2025-11-11
  165. Working on a list of open source tools for a Kubernetes ML stack -- 2025-11-10
  166. I built a leaderboard for Rerankers -- 2025-11-10
  167. LiquidAI/LFM2-ColBERT-350M -- 2025-11-10
  168. [Editorial] Context Engineering Handbook -- 2025-11-03
  169. Qwen3-VL-32B Q8 speeds in llama.cpp vs vLLM FP8 on a RTX PRO 6000 -- 2025-11-03
  170. OSS alternative to Open WebUI - ChatGPT-like UI, API and CLI -- 2025-11-03
  171. Looking for a RAG UI manager to meet our needs to replace Zapier -- 2025-11-03
  172. LiquidAI/LFM2-1.2B-Extract -- 2025-11-03
  173. Un-LOCC (Universal Lossy Optical Context Compression), Achieve Up To 3× context compression with 93.65% Accuracy. -- 2025-10-24
  174. LiquidAI/LFM2-1.2B-RAG -- 2025-10-24
  175. zai-org/GLM-4.6 -- 2025-10-24
  176. [Editorial] Browsers you can socially engineer -- 2025-10-24
  177. Update on Plans for Privacy Sandbox Technologies -- 2025-10-24
  178. 1r0BIT/TaskHound -- 2025-10-18
  179. armai92/goauth -- 2025-10-18
  180. Chinese gang used ArcGIS as a backdoor for a year – and no one noticed -- 2025-10-18
  181. [Editorial] Sqlite vector -- 2025-10-17
  182. Meta Superintelligence group publishes paper on new RAG technique -- 2025-10-17
  183. Dolphin — analyze-then-parse document image model (open-source, ByteDance) -- 2025-10-06
  184. Eclaire – Open-source, privacy-focused AI assistant for your data -- 2025-10-06
  185. KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities -- 2025-10-06
  186. Granite 4 H Tiny Q8 in RTX 3090, It's a context king. -- 2025-10-06
  187. A tiny receipt per AI run: κ (stress), Δhol (drift), and guards—in plain JSON. -- 2025-10-02
  188. Microsoft Agent Framework (Preview): Making AI Agents Simple for Every Developer -- 2025-10-02
  189. Stress-Testing RAG in Production: Retrieval Quality, Drift, and Hidden Costs -- 2025-09-30
  190. Uncensored LLM -- 2025-09-23
  191. Building RAG Systems at Enterprise Scale: Our Lessons and Challenges -- 2025-09-23
  192. HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data -- 2025-09-19
  193. TencentCloudADP/youtu-graphrag -- 2025-09-17
  194. [Editorial] REFRAG: Rethinking RAG based Decoding -- 2025-09-17
  195. I'm building local, open-source, fast, efficient, minimal, and extendible RAG library I always wanted to use -- 2025-09-03
  196. Creating the brain behind dumb models -- 2025-09-03
  197. Would a “Knowledge Coverage Audit” tool be useful for RAG/chatbot builders? -- 2025-08-30
  198. Anyone have the deets on ROCM 7.0's 3x perf claims? -- 2025-08-19
  199. Rust in 2025: Targeting foundational software -- 2025-08-19
  200. [UPDATE] DocStrange - Structured data extraction from images/pdfs/docs -- 2025-08-15
  201. Local RAG with 97% smaller index and Claude Code–compatible semantic search -- 2025-08-10
  202. Best way to manage context/notes locally for API usage while optimizing token costs? -- 2025-07-26
  203. Advice on choice of model -- 2025-07-26
  204. Document processing -- 2025-07-26
  205. Never Come Up Empty: Adaptive HyDE Retrieval for Improving LLM Developer Support -- 2025-07-24
  206. MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models -- 2025-07-24
  207. Building an MCP Server and Client with FastMCP 2.0 -- 2025-07-24
  208. muyuanlove/sensitive_info_extractor -- 2025-07-24
  209. Wordle-like game using your photos and on-device Small Language Models (SLMs) -- 2025-07-24
  210. Model to retrieve information from Knowledge. -- 2025-07-23
  211. merve/smol-vision -- 2025-07-23
  212. WhisPad (Note app, transcription, speaker diarization, AI style enhancements, mindmaps, chat with notes, etc) -- 2025-07-23
  213. vidore/colqwen-omni-v0.1 -- 2025-07-21
  214. Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data -- 2025-07-21
  215. Super fast local CPU file processing with static embeddings! -- 2025-07-21
  216. Deep Research with local LLM and local documents -- 2025-07-10
  217. WikipeQA : An evaluation dataset for both web-browsing agents and vector DB RAG systems -- 2025-07-10
  218. Looking for advice. -- 2025-07-10
  219. If NotebookLM were Agentic -- 2025-07-09
  220. run-llama/notebookllama -- 2025-07-09
  221. Tips for running a local RAG and llm? -- 2025-07-04
  222. I made an LLM tool to let you search offline Wikipedia/StackExchange/DevDocs ZIM files (llm-tools-kiwix, works with Python & LLM cli) -- 2025-07-04
  223. Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective -- 2025-07-04
  224. automated debugging using Ollama -- 2025-06-27
  225. Knowledge Database Advise needed/ Local RAG for IT Asset Discovery - Best approach for varied data? -- 2025-06-27
  226. Need feedback for a RAG using Ollama as background. -- 2025-06-27
  227. Best tutorial for installing a local llm with GUI setup? -- 2025-06-27
  228. Create 2 and 3-bit GPTQ quantization for Qwen3-235B-A22B? -- 2025-06-27
  229. Ollama Frontend/GUI -- 2025-06-27
  230. Newtonian Formulation of Attention: Treating Tokens as Interacting Masses? -- 2025-06-27
  231. Gemini CLI: Open-source AI agent. Write code, debug, and automate tasks with Gemini 2.5 Pro with industry-leading high usage limits at no cost. -- 2025-06-27
  232. A Plan for SIMD -- 2025-06-27
  233. Squiggle: A simple programming language for intuitive probabilistic estimation -- 2025-06-27
  234. I Built a Symbolic Cognitive System to Fix AI Drift — It’s Now Public (SCS 2.0) -- 2025-06-27
  235. trendmicro/vision-one-mcp-server -- 2025-06-20
  236. Minidoracat/mcp-feedback-enhanced -- 2025-06-20
  237. showlab/OmniConsistency -- 2025-06-15
  238. echo840/MonkeyOCR -- 2025-06-15
  239. Qwen/Qwen3-Embedding-8B -- 2025-06-06
  240. Sriram-PR/doc-scraper -- 2025-06-04