LLM News and Articles
| Tuesday, 2025-11-04 | ||||
| 00:49 | Ollama run DeepSeek-R1 local — it is so easy! https://medium.com/@michael.harms_57592/ollama-run-deepseek-r1-local-it-is-so-easy-1c15e0a1daff | |||
| 00:27 | AI Regurg https://ejhilbert.medium.com/ai-regurg-96ba59a44521 | |||
| 00:22 | From Content Vending Machine to Thought Partner https://medium.com/@talia.levitt/from-content-vending-machine-to-thought-partner-e2ceb4273f08 | |||
| 00:22 | The Swiss Army Knife for AI https://medium.com/@paulnegz1/the-swiss-army-knife-for-ai-257ef36a4af3 | |||
| 00:01 | Understanding Tokenization in Large Language Models https://pub.towardsai.net/understanding-tokenization-in-large-language-models-25402f51461e | |||
| Monday, 2025-11-03 | ||||
| 23:08 | How to Create Unlimited Free Websites with GitHub Pages: A Complete Guide https://medium.com/@ferreradaniel/how-to-create-unlimited-free-websites-with-github-pages-a-complete-guide-608cfd4fffcc | |||
| 23:05 | How to Fine-Tune and Train Your Own spaCy Model for Named Entity Recognition (NER) https://medium.com/@nchamseddin/how-to-fine-tune-and-train-your-own-spacy-model-for-named-entity-recognition-ner-530d0f5240e1 | |||
| 22:33 | The Vocabulary of Experience: Lessons in Leadership from Large Language Models https://mallikarao.medium.com/the-vocabulary-of-experience-lessons-in-leadership-from-large-language-models-534bfac57d5d | |||
| 22:02 | Architecture Design Principles for Large Language Models https://pub.towardsai.net/architecture-design-principles-for-large-language-models-c104e35e47e9 | |||
| 21:55 | OpenAI’s ChatGPT-6: A Deep Dive into Early Features and Future Capabilities https://medium.com/@ferreradaniel/openais-chatgpt-6-a-deep-dive-into-early-features-and-future-capabilities-52536ab2aa01 | |||
| 21:41 | Perplexity's new AI tool aims to simplify patent research https://www.theverge.com/news/811340/perplexity-ai-patent-research-tool | |||
| 21:35 | Do You Know What an LLM Really Is? https://ziga-petek.medium.com/do-you-know-what-an-llm-really-is-21a758bf99bd | |||
| 21:27 | Get Free Tokens for OpenAI API: A Simple Guide https://medium.com/@denishartl/get-free-tokens-for-openai-api-a-simple-guide-3a9a76d51e29 | |||
| 21:27 | DPO: “Classification” Perspektifinden Anlaşılması Gereken Optimizasyon https://medium.com/@omeryalcin48/dpo-classification-perspektifinden-anla%C5%9F%C4%B1lmas%C4%B1-gereken-optimizasyon-72a8e2fa4887 | |||
| 21:20 | Trust Center: Patunayan na Tumatakbo ang Iyong mga Application nang Eksakto ayon sa Ipangako https://medium.com/@Phala_Pilipinas/trust-center-patunayan-na-tumatakbo-ang-iyong-mga-application-nang-eksakto-ayon-sa-ipangako-8c6b6a714ea8 | |||
| 21:11 | LLM-Assisted Web Data Extraction with ScrapeGraphAI: A Practical 2025 Walkthrough https://medium.com/@isabelarodriguez361/llm-assisted-web-data-extraction-with-scrapegraphai-a-practical-2025-walkthrough-ee56960394db | |||
| 21:00 | Microsoft Agent Lightning: The Inside Story on the AI Model Powering the Next Generation of Windows https://medium.com/@ferreradaniel/microsoft-agent-lightning-the-inside-story-on-the-ai-model-powering-the-next-generation-of-windows-30051ee86a1b | |||
| 20:57 | Time, Film, and AI: On Duration and Discrete Frames https://medium.com/@yoonsen/time-film-and-ai-on-duration-and-discrete-frames-87ee376ab521 | |||
| 20:41 | Generative AI for Project Managers by Cloud Commercial Holdings https://medium.com/@jeffkessie450/generative-ai-for-project-managers-by-cloud-commercial-holdings-47d763fb910f | |||
| 20:39 | Why your agents suck (and the need for ontology) https://medium.com/@mitchbregs/why-your-agents-suck-and-the-need-for-ontology-a2cf88bd8c31 | |||
| 20:29 | How to Run Qwen3-VL Locally on Your Device https://medium.com/@DiffEff/how-to-run-qwen3-vl-locally-on-your-device-f43baddebc9e | |||
| 20:09 | Building a Text-to-SQL app with OpenAI and DuckDB https://medium.com/@prasadms.it83/building-a-text-to-sql-app-with-openai-and-duckdb-99c82e36dd72 | |||
| 20:06 | The Cantor Experiment: Forcing a GPT-5-Class AI to Forget a Century of Math https://romainpeter.substack.com/p/the-cantor-experiment-forcing-a-gpt | |||
| 20:01 | Month in 4 Papers (October 2025) https://pub.towardsai.net/month-in-4-papers-october-2025-3d96edced85a | |||
| 19:55 | The Mind of Machines: How Large Language Models Think, Communicate, and Power the AI Revolution https://medium.com/closedaitaken/the-mind-of-machines-how-large-language-models-think-communicate-and-power-the-ai-revolution-4f938181e45f | |||
| 19:52 | Show HN: React-like Declarative DSL for building synthetic LLM datasets https://github.com/qforge-dev/torque | |||
| 19:45 | OpenAI Made a B Loss Last Quarter, Microsoft Results Indicate https://www.wsj.com/livecoverage/stock-market-today-dow-sp-500-nasdaq-10-31-2025/card/openai-made-a-12-billion-loss-last-quarter-microsoft-results-indicate-e71BLjJA0e2XBthQZA5X | |||
| 19:43 | Sync Vs Async https://raahulgupta.medium.com/sync-vs-async-db8669dfdf98 | |||
| 19:42 | Running Large Transformer Models on Mobile and Edge Devices https://mtugrull.medium.com/running-large-transformer-models-on-mobile-and-edge-devices-6a965093794b | |||
| 19:41 | Writing an LLM from scratch, part 26 – evaluating the fine-tuned model https://www.gilesthomas.com/2025/11/llm-from-scratch-26-evaluating-the-fine-tuned-model | |||
| 19:34 | Mobil ve Uç Cihazlarda Büyük Transformer Modellerini Çalıştırmak https://mtugrull.medium.com/mobil-ve-u%C3%A7-cihazlarda-b%C3%BCy%C3%BCk-transformer-modellerini-%C3%A7al%C4%B1%C5%9Ft%C4%B1rmak-9c787fafc4b0 | |||
| 19:28 | FreakWAN: A floor-routing WAN implementing a chat over bare-LoRa (no LoRaWAN) https://github.com/antirez/freakwan | |||
| 19:17 | AI and Multidimensionality: Meet Uranus-3B https://medium.com/@AntonioVFranco/ai-and-multidimensionality-meet-uranus-3b-577e6b4b5e87 | |||
| 19:14 | Show HN: Extrai – An open-source tool to fight LLM randomness in data extraction https://github.com/Telsho/Extrai | |||
| 19:05 | Introspection in AI: A Glimmer of Self-Awareness in Large Language Models https://noailabs.medium.com/introspection-in-ai-a-glimmer-of-self-awareness-in-large-language-models-541abf50383a | |||
| 18:53 | Bringing locally running LLM into your NodeJS project https://medium.com/@6akcuk/bringing-locally-running-llm-into-your-nodejs-project-197151163db1 | |||
| 18:39 | The Tasteful Machine https://medium.com/@yotam.mano/the-tasteful-machine-6af4e6ecfb1e | |||
| 18:31 | OpenAI signs B cloud computing deal with Amazon https://www.theguardian.com/technology/2025/nov/03/openai-cloud-computing-deal-amazon-aws-datacentres-nvidia-chips | |||
| 18:16 | Agent-o-rama: build, trace, evaluate, and monitor LLM agents in Java or Clojure https://blog.redplanetlabs.com/2025/11/03/introducing-agent-o-rama-build-trace-evaluate-and-monitor-stateful-llm-agents-in-java-or-clojure/ | |||
| 17:27 | The Age of Small Language Models: Why Smaller Is the Next Smarter https://medium.com/@dexodusgenesis/the-age-of-small-language-models-why-smaller-is-the-next-smarter-53a0c5f5b1bd | |||
| 16:44 | All Data and AI Weekly #214: 03-Nov-2025 https://medium.com/@tspann/all-data-and-ai-weekly-214-03-nov-2025-8e770584d459 | |||
| 16:38 | Show HN: Krnel-Graph, a Library for LLM representation engineering and control https://github.com/krnel-ai/krnel-graph/tree/main/examples/01-guardrail-comparisons | |||
| 16:15 | Analyzing LLM Architectural Advances: From GPT-1 to DeepSeek-V3 https://medium.com/@lmpo/analyzing-llm-architectural-advances-from-gpt-1-to-deepseek-v3-a33431910b3f | |||
| 16:13 | Is LLM know about Things that Wikipedia Don't ? https://medium.com/@malipallandri/is-llm-know-about-things-that-wikipedia-dont-b745a05dea66 | |||
| 16:08 | The Truth About Decoders: LLMs Use 50x More Data https://medium.com/@vikramlingam/the-truth-about-decoders-llms-use-50x-more-data-f40bf3949666 | |||
| 16:08 | The Deadlock of Context Hallucination with Model Context Protocol https://medium.com/@usmanaslam712/the-deadlock-of-context-hallucination-with-model-context-protocol-f5d9021a9266 | |||
| 16:05 | DeepSeek-OCR: Tackling Full-Page Documents with 100 Tokens, Compared to Traditional Methods’ 6000 https://ai-engineering-trend.medium.com/deepseek-ocr-tackling-full-page-documents-with-100-tokens-compared-to-traditional-methods-6000-a40e50f80489 | |||
| 16:02 | AI in Pocket https://medium.com/@Web3comVC/ai-in-pocket-ea34dbaf2b10 | |||
| 16:02 | This AI Learns to ‘Think’: A New Model for Data Science https://pub.towardsai.net/this-ai-learns-to-think-a-new-model-for-data-science-48ebe9535086 | |||
| 16:00 | An Update on the Silence (And the Unvarnished Truth) https://medium.com/@Sparksinthedark/an-update-on-the-silence-and-the-unvarnished-truth-35312887d32f | |||
| 15:46 | TOON Format https://morihosseini.medium.com/toon-format-11d5847608f3 | |||
| 15:29 | Would you use Chat GPT to cheat at hobbies? https://www.thecut.com/article/would-you-use-chatgpt-to-cheat-at-hobbies.html | |||
| 15:16 | 2025’s Most Stolen gRPC Streaming Secret (And How to Hijack It for Real-Time LLM Feeds) https://medium.com/c-sharp-programming/2025s-most-stolen-grpc-streaming-secret-and-how-to-hijack-it-for-real-time-llm-feeds-17ff014efadc | |||
| 15:15 | OpenAI Can Never Claim AGI Is Here https://theahura.substack.com/p/tech-things-openai-can-never-claim | |||
| 15:13 | OpenAI, Amazon strike B agreement for ChatGPT maker to use AWS https://www.reuters.com/business/retail-consumer/openai-amazon-strike-38-billion-agreement-chatgpt-maker-use-aws-2025-11-03/ | |||
| 15:11 | GenAI Series #3: Large Language Models (LLMs): From Digital Scribe to Reasoning Engine https://medium.com/@hhilalalpak/genai-series-3-large-language-models-llms-from-digital-scribe-to-reasoning-engine-73f948910a63 | |||
| 15:00 | OpenAI signs B compute deal with Amazon https://www.cnbc.com/2025/11/03/open-ai-amazon-aws-cloud-deal.html | |||
| 14:46 | Benchmarking AI Agents: Stop Trusting Headline Scores, Start Measuring Trade-offs https://medium.com/alan/benchmarking-ai-agents-stop-trusting-headline-scores-start-measuring-trade-offs-0fdae3a418cf | |||
| 14:35 | Understanding LangChain and LangGraph: A Beginner’s Guide to AI Workflows https://medium.com/data-science-collective/understanding-langchain-and-langgraph-a-beginners-guide-to-ai-workflows-ad21cd79aba3 | |||
| 14:30 | Understanding the Difference Between AI, ML, DL, LLM, and Generative AI https://medium.com/@iobune_66385/understanding-the-difference-between-ai-ml-dl-llm-and-generative-ai-b19aa74ba061 | |||
| 14:21 | Beyond ChatGPT: Unpacking the Future of AI Agents https://medium.com/@imda-biztech/beyond-chatgpt-unpacking-the-future-of-ai-agents-ce19017b1780 | |||
| 14:20 | OpenAI signs B cloud computing deal with Amazon https://www.nytimes.com/2025/11/03/technology/openai-amazon-cloud-computing.html | |||
| 14:13 | Inside AI Safety Practices: Practical Approaches https://medium.com/@imda-biztech/inside-ai-safety-practices-practical-approaches-5de58456bdc5 | |||
| 14:12 | Miniax M2: China’s 230B AI Model That’s Redefining Open-Source Agentic Intelligence https://medium.com/@greekofai/miniax-m2-chinas-230b-ai-model-that-s-redefining-open-source-agentic-intelligence-c2efb861b8b3 | |||
| 14:09 | AWS and OpenAI announce multi-year strategic partnership https://www.aboutamazon.com/news/aws/aws-open-ai-workloads-compute-infrastructure | |||
| 14:02 | AWS and OpenAI announce multi-year strategic partnership https://openai.com/index/aws-and-openai-partnership/ | |||
| 14:01 | Building Intelligent RAG Systems: A Deep-Thinking Agentic Approach with LangGraph https://pub.towardsai.net/building-intelligent-rag-systems-a-deep-thinking-agentic-approach-with-langgraph-b65e3b3f9b5f | |||
| 13:58 | 3 Experiments That Reveal the Shocking Inner Life of AI Introduction: Is Anybody Home? https://medium.com/@AnthonyLaneau/3-experiments-that-reveal-the-shocking-inner-life-of-ai-introduction-is-anybody-home-e228d00c8389 | |||
| 13:53 | When Machines Learn to Read: DeepSeek OCR Explained https://ai.gopubby.com/when-machines-learn-to-read-deepseek-ocr-explained-8b3bfcae50f5 | |||
| 13:43 | OpenAI releases open safety reasoning models https://medium.com/magic-ai/openai-releases-open-safety-reasoning-models-3cb79dcca474 | |||
| 13:40 | 7 Steps to Master Large Language Models https://ai.plainenglish.io/7-steps-to-master-large-language-models-e1ef9eecb04f | |||
| 13:08 | 345e Game Free Download (Real Money APK) in Pakistan 2025 https://medium.com/@vrapkfamily/345e-game-free-download-real-money-apk-in-pakistan-2025-74d929664dcc | |||
| 13:00 | Sam Altman says OpenAI will have a 'legitimate AI researcher' by 2028 https://techcrunch.com/2025/10/28/sam-altman-says-openai-will-have-a-legitimate-ai-researcher-by-2028/ | |||
| 12:46 | Automating Tag Generation for GitHub Projects Using n8n, Gemini, and PostgreSQL https://medium.com/@sagarj.scaleteam/automating-tag-generation-for-github-projects-using-n8n-gemini-and-postgresql-16e218f647eb | |||
| 12:43 | What’s the ROI of 100% Automated QA in the Contact Center? https://medium.com/@max.s_33396/whats-the-roi-of-100-automated-qa-in-the-contact-center-83301aefb446 | |||
| 12:26 | Agentic Detection Creation: From Sigma to Splunk Rules (or any platform) https://detect.fyi/agentic-detection-creation-from-sigma-to-splunk-rules-or-any-platform-4697e13d9ee3 | |||
| 12:05 | OSS Alternative to Open WebUI – ChatGPT-Like UI, API and CLI https://github.com/ServiceStack/llms | |||
| 12:00 | How to Make LLMs Deterministic: A Complete Guide for DeepSeek and vLLM Users https://thamizhelango.medium.com/how-to-make-llms-deterministic-a-complete-guide-for-deepseek-and-vllm-users-bf0016652336 | |||
| 11:47 | Top LLM Papers of the Week (November Week 1, 2025) https://medium.com/@kalyanks/top-llm-papers-of-the-week-november-week-1-2025-f081731de09f | |||
| 11:45 | Reading Between the Commits: What GitHub’s Octoverse 2025 Tells Us About the Next Developer Decade https://medium.com/@gajaoncloud/reading-between-the-commits-what-githubs-octoverse-2025-tells-us-about-the-next-developer-decade-0167a7f237f6 | |||
| 11:44 | SAP AI Training | Free Recorded Demo for Beginners & Pros! https://medium.com/@pravin.visualpath/sap-ai-training-free-recorded-demo-for-beginners-pros-ed9ab41668f4 | |||
| 11:24 | Sparse Autoencoders and Awesome Tools to See What LLMs Are “Thinking” https://medium.com/@dvirla84/sparse-autoencoders-and-awesome-tools-to-see-what-llms-are-thinking-2bd6bcdd4153 | |||
| 11:23 | Key Problems Every General LLM Faces : Accuracy, Hallucinations, and Conformance https://medium.com/@joycebirkins/key-problems-every-general-llm-faces-accuracy-hallucinations-and-conformance-7d1ade3b5fb2 | |||
| 11:20 | A New Multi-Agent Engine for the Competitive Intelligence Platform https://medium.com/@theweekenddev0/a-new-multi-agent-engine-for-the-competitive-intelligence-platform-10b92406c3b3 | |||
| 10:21 | JSON vs TOON — A new era of structured input? https://medium.com/medialesson/json-vs-toon-a-new-era-of-structured-input-19cbb7fc552b | |||
| 10:16 | Error and Exception Handling in Applications https://medium.com/@spacholski99/error-and-exception-handling-in-applications-7cc9ddeebe21 | |||
| 10:11 | Sub 10ms RAG on CPU: 1.5bit Quantisation with Qdrant and fastRTC for Real-Time AI Agents https://niranjanakella.medium.com/sub-10ms-rag-on-cpu-1-5bit-quantisation-with-qdrant-and-fastrtc-for-real-time-ai-agents-282f9f65c974 | |||
| 10:02 | Building a production-ready Attack Surface Management Agent with AWS Bedrock while staying within… https://engineering.doit.com/building-a-production-ready-attack-surface-management-agent-with-aws-bedrock-while-staying-within-c530501e6739 | |||
| 09:52 | Sam Altman says 'enough' to questions about OpenAI's revenue https://techcrunch.com/2025/11/02/sam-altman-says-enough-to-questions-about-openais-revenue/ | |||
| 09:31 | I Built a Real-Time AI App. The Hardest Part Wasn’t the LLM — It Was the Data. https://medium.com/@himanshu675/i-built-a-real-time-ai-app-the-hardest-part-wasnt-the-llm-it-was-the-data-9a0cea514130 | |||
| 08:43 | Paper Review: Chronos-2: From Univariate to Universal Forecasting https://artgor.medium.com/paper-review-chronos-2-from-univariate-to-universal-forecasting-3d929623e078 | |||
| 08:41 | The Transactional Graph-Enhanced LLM: A Definitive Guide to Read/Write Chatbots for Relational Data https://medium.com/@shivamuttam9/the-transactional-graph-enhanced-llm-a-definitive-guide-to-read-write-chatbots-for-relational-data-6e1b280cefee | |||
| 08:30 | Simplicity is still in fashion (loveholidays AI diary #3) https://tech.loveholidays.com/simplicity-is-still-in-fashion-loveholidays-ai-diary-3-afe391b3e270 | |||
| 08:26 | 1,000 Agents Later: Lessons in Building AI That Doesn’t Break https://medium.com/@nomannayeem/1-000-agents-later-lessons-in-building-ai-that-doesnt-break-f72d47292b45 | |||
| 08:26 | Listing UI is Dead, Long Live AI Chat UI https://medium.com/tapsilat/listing-ui-is-dead-long-live-ai-chat-ui-4cd63b319232 | |||
| 08:01 | Fine-Tuning LLMs for Agentic Graphrag Optimization on Consumer Hardware- An RL Approach https://autognosi.medium.com/fine-tuning-llms-for-agentic-graphrag-optimization-on-consumer-hardware-an-rl-approach-7cd01af71e9b | |||
| 07:57 | I wrote about AI’s chatbot gold rush: billion in just 33 months — from 2023 to now, November… https://medium.com/@barnascript/i-wrote-about-ais-chatbot-gold-rush-52-billion-in-just-33-months-from-2023-to-now-november-684a589b3ccb | |||
| 07:51 | Retrieval Augmented Generation https://shahrukh0603.medium.com/retrieval-augmented-generation-78d91d142380 | |||
| 07:45 | The Judgement on AI Awakening: Language, Illusion, and the Human Echo https://ai.plainenglish.io/the-judgement-on-ai-awakening-language-illusion-and-the-human-echo-89f06f0d6002 | |||
| 07:38 | The Collapse of Centralized AI Discovery https://medium.com/@tim_62250/the-collapse-of-centralized-ai-discovery-504b9b8e0514 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124