LLM News and Articles
| Monday, 2024-09-02 | ||||
| 02:44 | Combining Vector Databases to Build Your Own Travel Recommendation System(Travel Assistant… https://medium.com/@gipitoma01/combining-vector-databases-to-build-your-own-travel-recommendation-system-travel-assistant-84bed14fb75c | |||
| 02:40 | AI Unveiled: A Comprehensive Journey from Basics to Future Frontiers https://harishkumar329.medium.com/ai-unveiled-a-comprehensive-journey-from-basics-to-future-frontiers-7fa1226805bd | |||
| 01:31 | Building a Generative AI Model with Markov Chains: “I love you” = [1,4,3] https://medium.com/@venkatachalam.sps/building-a-generative-ai-model-with-markov-chains-i-love-you-1-4-3-a72a6217c400 | |||
| 01:08 | How to Use SuperPrompt and Never Worry About Prompt Engineering Again https://towards-agi.medium.com/how-to-use-superprompt-and-never-worry-about-prompt-engineering-again-a50126290cfa | |||
| 01:02 | Training GPT-2 From Scratch: A Step-by-Step Guide https://levelup.gitconnected.com/training-gpt-2-from-scratch-a-step-by-step-guide-844bb7fc5f94 | |||
| 00:53 | What is Arx.0.3 Model and Who Made It? https://towards-agi.medium.com/what-is-arx-0-3-model-and-who-made-it-2c1b660ea44e | |||
| 00:27 | Perplexity AI: More Than Just a “Google Killer” — It’s Redefining Search and Content Creation https://medium.com/@digitalsarra/perplexity-ai-more-than-just-a-google-killer-its-redefining-search-and-content-creation-8757da5ae7bd | |||
| Sunday, 2024-09-01 | ||||
| 23:42 | Learn the fundamentals of LLM and Prompt Engineering with this Langchain + Streamlit Portfolio… https://medium.com/@Architekt.exe/learn-the-fundamentals-of-llm-and-prompt-engineering-with-this-langchain-streamlit-portfolio-74ef6a2288ad | |||
| 23:10 | Pengenalan Generative AI dan Membuat Agent Chatbot dengan Vertex AI https://junkevin.medium.com/pengenalan-generative-ai-dan-membuat-agent-chatbot-dengan-vertex-ai-e7ed2eebfbed | |||
| 22:54 | Run Gemma 2: 2B — 9B — 27B https://awstip.com/run-gemma-2-2b-9b-27b-763e9c69b003 | |||
| 22:47 | Don’t Judge An LLM Only By The Web App https://medium.com/@impure/dont-judge-an-llm-only-by-the-web-app-0a47d29390c3 | |||
| 22:43 | A layered glossary for Generative AI-Language Models https://medium.com/@bytesandroadmap/a-layered-glossary-for-generative-ai-language-models-7ddc4bb60ca6 | |||
| 22:37 | Removing Watermarks from Document Images with OpenCV and Tkinter: A Step-by-Step Guide https://medium.com/@monsuralirana/removing-watermarks-from-document-images-with-opencv-and-tkinter-a-step-by-step-guide-745e833c677b | |||
| 21:18 | AI-Workers Unite! https://medium.com/@twilger/ai-workers-unite-c6ff12a0f0b5 | |||
| 19:58 | Using Claude AI API: A Beginner’s Guide https://medium.com/@tomskiecke/using-claude-ai-api-a-beginners-guide-02f973ffd0e7 | |||
| 19:55 | ChromaDB: Seu banco de dados vetorial open-source nativo para IA https://medium.com/@mdbaraujo/chromadb-seu-banco-de-dados-vetorial-open-source-nativo-para-ia-5f60ac66597b | |||
| 19:32 | The Hugging Face Hub is a vast repository, currently hosting 750K+ public models, offering a… https://medium.com/@amanatulla1606/the-hugging-face-hub-is-a-vast-repository-currently-hosting-750k-public-models-offering-a-7736fab4ba1b | |||
| 19:22 | The 5 Most Under-Rated Tools on Hugging Face https://medium.com/@amanatulla1606/the-5-most-under-rated-tools-on-hugging-face-9f83c6c30b6c | |||
| 18:41 | Did Early ChatGPT-4 Adopters Change Other Digital Payments? Exploratory Evidence https://papers.ssrn.com/sol3/papers.cfm | |||
| 18:24 | Hallucinations in AI Chatbots and Large Language Models: WHAT and WHY https://medium.com/@SYNCOG/hallucinations-in-ai-chatbots-and-large-language-models-what-and-why-c5d8526eba4c | |||
| 18:09 | LLM Evaluation Metrics : RAG, Offline metrics(MRR, NDCG), ROUGE, BLEU https://medium.com/@ramachandran1985/llm-evaluation-metrics-rag-offline-metrics-mrr-ndcg-rouge-bleu-1145761da900 | |||
| 18:01 | Model Quantization: Making AI Models Faster and Smaller https://medium.com/@ishan.modi24/model-quantization-making-ai-models-faster-and-smaller-60fac2cae27f | |||
| 18:01 | Can AI Negotiate for You and Win You More Deals? https://pub.towardsai.net/can-ai-negotiate-for-you-and-win-you-more-deals-eb73c52dc3ab | |||
| 17:45 | Chart-to-table with LVLMs (part 1) https://medium.com/@degrandisluca95/chart-to-table-with-lvlms-part-1-55b2dd30c0e9 | |||
| 17:37 | Running LLMs on your computer locally — the hardware! https://michael-mcanally.medium.com/running-llms-on-your-computer-locally-75717bd38d5e | |||
| 17:37 | Why Opensource LLMs https://lotuschain.medium.com/why-opensource-llms-a54162b3ba6e | |||
| 16:46 | Apple and Nvidia in talks to invest in ChatGPT https://www.businesstoday.in/technology/news/story/apple-nvidia-in-talks-to-invest-in-chatgpt-maker-openai-potentially-valuing-company-over-100-billion-443624-2024-08-30 | |||
| 16:01 | Have we stopped to think about what LLMs actually model? https://mdbconsultant.medium.com/have-we-stopped-to-think-about-what-llms-actually-model-3fe0de75b414 | |||
| 15:57 | LLM Cost Optimization https://medium.com/@bijit211987/optimizing-llms-for-cost-087e923c7fd0 | |||
| 15:48 | Enhancing Retrieval-Augmented Generation (RAG) with Python https://kovendhanv.medium.com/enhancing-retrieval-augmented-generation-rag-with-python-f5ca8c96561c | |||
| 15:48 | Enhancing Retrieval-Augmented Generation (RAG) with Python https://medium.com/analytics-vidhya/enhancing-retrieval-augmented-generation-rag-with-python-f5ca8c96561c | |||
| 15:31 | Maximal Marginal Relevance https://medium.com/@adergunov/maximal-marginal-relevance-144c23b42be5 | |||
| 15:22 | Craft Accurate Market Update Summaries with Generative AI https://medium.datadriveninvestor.com/craft-accurate-market-update-summaries-with-generative-ai-4d984d6fa0e7 | |||
| 15:21 | Best Practices for RAG Pipeline https://masteringllm.medium.com/best-practices-for-rag-pipeline-8c12a8096453 | |||
| 15:07 | Claude repousse les limites du développement : Création d’une Todo List en temps réel sous mes yeux! https://medium.com/@aliamine.ghazeli/claude-repousse-les-limites-du-d%C3%A9veloppement-cr%C3%A9ation-dune-todo-list-en-temps-r%C3%A9el-sous-mes-yeux-f7b90215a25b | |||
| 14:56 | AI LLMs and their Reasoning Potential https://medium.com/@faiz.neet/ai-llms-and-their-reasoning-potential-6434cda3af96 | |||
| 14:51 | OpenAI in Talks for Deal That Would Value Company at 0B https://www.nytimes.com/2024/08/28/technology/openai-valuation-funding-deal.html | |||
| 14:40 | To Fine Tune or Retrieve that is the question — Fine Tuning vs RAG in LLMs https://medium.com/@ashutosh.bagga92/to-fine-tune-or-retrieve-that-is-the-question-fine-tuning-vs-rag-in-llms-8bc790d6e22f | |||
| 14:13 | How to Develop a LLM https://dhirajpatra.medium.com/how-to-develop-a-llm-02105479eb51 | |||
| 14:12 | All the best AI companies are not the new early stage startups https://medium.com/trajectory-ventures/all-the-best-ai-companies-are-not-the-new-early-stage-startups-01e4e0ee2da4 | |||
| 14:02 | Components of Retrieval-Augmented Generation (RAG) https://medium.com/@punya8147_26846/components-of-retrieval-augmented-generation-rag-e3447eeaac85 | |||
| 13:52 | Ranking AI Responses: Measuring and Comparing Model Accuracy with Real-World Use Cases https://medium.com/@punya8147_26846/ranking-ai-responses-measuring-and-comparing-model-accuracy-with-real-world-use-cases-93cab05dcaff | |||
| 13:42 | LLMs Alignment, Fine-tuning, RAG // most popular techniques https://sbagency.medium.com/llms-alignment-fine-tuning-rag-most-popular-techniques-0d8da4afa9f2 | |||
| 13:00 | Load and Split Data using LangChain https://blog.gopenai.com/load-and-split-data-using-langchain-ac20d2422000 | |||
| 12:41 | Building a Recipe Recommender with LangChain and Gemini on Vertex AI https://medium.com/ml-concepts/building-a-recipe-recommender-with-langchain-and-gemini-on-vertex-ai-77db6f6c5952 | |||
| 12:41 | Hierarchical Indices: Enhancing RAG Systems https://medium.com/@nirdiamant21/hierarchical-indices-enhancing-rag-systems-43c06330c085 | |||
| 12:10 | How I Developed an Efficient Retrieval-Augmented Generation (RAG) Pipeline https://aadhil-imam.medium.com/how-i-developed-an-efficient-retrieval-augmented-generation-rag-pipeline-9647847036e6 | |||
| 12:01 | OpenAI API: From Basics to Chatbot Implementation with GPT-4o Mini & Streamlit. https://pub.towardsai.net/openai-api-from-basics-to-chatbot-implementation-with-gpt-4o-mini-streamlit-1c4de9c3c311 | |||
| 12:01 | Illustrated GLiNER https://medium.com/@shahrukhx01/illustrated-gliner-e6971e4c8c52 | |||
| 11:55 | Fine-tuning large language models (LLMs https://medium.com/@mir.global.academy/fine-tuning-large-language-models-llms-95b270adc574 | |||
| 11:28 | Apple Will Save AI https://lucas-mcgregor.medium.com/apple-will-save-ai-f38ec90114e6 | |||
| 10:54 | Case Study — Custom LLM Powered Knowledge Base for Real Estate Industry using Gemma and MongoDB https://medium.com/impulsiveweb/case-study-custom-llm-powered-knowledge-base-for-real-estate-industry-using-gemma-and-mongodb-1b62c7d9ff94 | |||
| 10:38 | Generation Sampling in LLMs: Implementation and Explanation https://medium.com/@parulsharma_8357/generation-sampling-in-llms-implementation-and-explanation-861981cca187 | |||
| 09:51 | Unveiling the Powerhouses: A Deep Dive into Cerebras and Ollama Running LLaMA 3.1 8B https://medium.com/@hafizaljohari/unveiling-the-powerhouses-a-deep-dive-into-cerebras-and-ollama-running-llama-3-1-8b-2245192a6817 | |||
| 09:50 | Decoding A.I./LLM Transformers: A 500-word Guide https://medium.com/@SYNCOG/decoding-a-i-llm-transformers-a-500-word-guide-318e0a4bc921 | |||
| 09:40 | 5 Levels of Building Chatbot Apps with Haystack — Level 2 https://medium.com/@armantunga/5-levels-of-building-chatbot-apps-with-haystack-level-2-437a207ae784 | |||
| 09:13 | Build your own Llama 3 architecture from scratch using PyTorch https://pub.towardsai.net/build-your-own-llama-3-architecture-from-scratch-using-pytorch-2ce1ecaa901c | |||
| 08:58 | Best Practices in Prompt Engineering: A Real-World Guide https://medium.com/@saeedhajebi/best-practices-in-prompt-engineering-a-real-world-guide-2781d192d60d | |||
| 08:57 | Digital Humans: When AI Gets a Face https://medium.com/@naman1011/digital-humans-when-ai-gets-a-face-64f080198d0c | |||
| 08:49 | Is OpenAI Worth 0B? https://techcrunch.com/2024/08/31/is-openai-worth-100b/ | |||
| 08:12 | TypedDict: Where and How to Use It https://medium.com/@joshuanishanth120/typeddict-where-and-how-to-use-it-595942f8ea88 | |||
| 08:12 | The Rise of RAGStack: Empowering GenAI with Data Stacks https://medium.com/@ajayverma23/the-rise-of-ragstack-empowering-genai-with-data-stacks-276f607bcc78 | |||
| 07:59 | Pydantic in LLM Agents: How to Use!!! https://medium.com/@joshuanishanth120/pydantic-in-llm-agents-how-to-use-efed842e4163 | |||
| 07:42 | Think Like an LLM: Unlocking the Power of AI by Adopting Its Perspective https://irahulkharat.medium.com/think-like-an-llm-unlocking-the-power-of-ai-by-adopting-its-perspective-bf1fceb59f76 | |||
| 07:32 | The Rise of Teacher Models: Knowledge Distillation in LLMs https://generativeai.pub/the-rise-of-teacher-models-knowledge-distillation-in-llms-456682b093bf | |||
| 07:29 | Retrieval-Augmented Generation: Doing a small project with RAG https://generativeai.pub/retrieval-augmented-generation-doing-a-small-project-with-rag-63ae15abc7cb | |||
| 07:29 | Next.js+LLM-101-Chat App-(2) https://medium.com/@samanosrima/next-js-llm-101-chat-app-2-5e0eb64f758a | |||
| 07:27 | How to Build a Research Paper Analysis Chatbot Using Google’s Gemini LLM https://medium.com/@imabhi1216/how-to-build-a-research-paper-analysis-chatbot-using-googles-gemini-llm-6fcedcf8ce7d | |||
| 07:19 | Demystifying Large Language Models: A Comprehensive Guide https://medium.com/@anandvlinkedin/demystifying-large-language-models-a-comprehensive-guide-1c025befc96b | |||
| 07:06 | Next.js+LLM-101-Chat App- New project(1) https://medium.com/@samanosrima/next-js-llm-101-chat-app-6aeb89af75a6 | |||
| 05:22 | ChatGPT with confidence scores https://david-gilbertson.medium.com/chatgpt-with-confidence-scores-65966f7077fe | |||
| 04:42 | Deploying Advanced AI Models Locally: LLaMA3, Phi, and OpenWebUI Made Easy. https://medium.com/@ink_pixels/deploying-advanced-ai-models-locally-llama3-phi-and-openwebui-made-easy-f638b18f4e31 | |||
| 04:19 | The Power of Collaboration: LLM Agents in Multi-Agent Systems https://medium.com/@yashbhardwaj.1912/the-power-of-collaboration-llm-agents-in-multi-agent-systems-8c0441157f14 | |||
| 03:42 | Vector Databases: Revolutionizing Data Retrieval in the AI Era https://vabnix.medium.com/vector-databases-revolutionizing-data-retrieval-in-the-ai-era-d2c0fba903e3 | |||
| 02:36 | Starting With Ollama https://ibrhmahmd.medium.com/starting-with-ollama-cfbdc69be5eb | |||
| 02:21 | Right-Sizing GPUs for LLMs https://medium.com/@bijit211987/right-sizing-gpus-for-llms-cbbdb0744c1b | |||
| 00:52 | Trained GPT to analyze body fat% within 5% error of DEXA scan https://apps.apple.com/us/app/sculptai-body-fat-calories/id6587549869 | |||
| 00:49 | RAG-LAB: an open-source lighter, faster and cheaper RAG toolkit https://medium.com/@vincentli_48285/rag-lab-an-open-source-lighter-faster-and-cheaper-rag-toolkit-1a53a9db2f63 | |||
| Saturday, 2024-08-31 | ||||
| 23:49 | Revolutionizing Customer Experience: Building Geico’s Virtual Assistant, Kate https://medium.com/@jaywang.recsys/revolutionizing-customer-experience-building-geicos-virtual-assistant-kate-6ff801fa4ab9 | |||
| 23:39 | Prompt Engineering vs Prompt Tuning : Is there any difference ? https://msaqib-genai.medium.com/prompt-engineering-vs-prompt-tuning-is-there-any-difference-585dabfed7f7 | |||
| 23:37 | Revolutionizing Claims Processing at Geico with Generative AI https://medium.com/@jaywang.recsys/revolutionizing-claims-processing-at-geico-with-generative-ai-f2c1d19b2ec6 | |||
| 23:00 | Defending Large Language Models (LLMs): Best Practices for Security https://cluelesszay.medium.com/defending-large-language-models-llms-best-practices-for-security-a85d4a6df622 | |||
| 22:35 | How Early Adopters Gain a Competitive Edge with Generative AI — and Why You Should Too https://medium.com/@christianleivabeltran/how-early-adopters-gain-a-competitive-edge-with-generative-ai-and-why-you-should-too-679eb6eba096 | |||
| 21:41 | An Introduction To Me https://medium.com/@collinreykillian/an-introduction-to-me-a799badf9ffe | |||
| 20:38 | Local LLM Generated Knowledge Graphs Powered by Local Neo4j https://ai.gopubby.com/local-llm-generated-knowledge-graphs-powered-by-local-neo4j-4111c5234993 | |||
| 20:08 | Running LLaMA3.1 https://medium.com/@monsuralirana/running-llama3-1-729a909b2ee8 | |||
| 19:56 | The Threat to OpenAI https://www.wsj.com/tech/ai/ai-chatgpt-nvidia-apple-facebook-383943d1 | |||
| 19:54 | ChatGPT is not just for professionals https://medium.com/@marocsofiane20/chatgpt-is-not-just-for-professionals-48c85dbc989b | |||
| 18:38 | Enhancing GenAI Capabilities: RAG and Natural Language to SQL Generation https://medium.com/@tejasgupta2703/enhancing-genai-capabilities-rag-and-natural-language-to-sql-generation-87ef9cedbfde | |||
| 18:32 | Aider: Your AI Pair Programming Partner https://medium.com/@omkamal/aider-your-ai-pair-programming-partner-0b6527aa0550 | |||
| 18:05 | The siren song of ChatGPT and junior devs that listen to it https://www.infobip.com/engineering/chat-gpt-and-the-things-i-learned-while-using-it | |||
| 17:37 | Beyond the Basics: RAGLAB’s Transparent and Modular Framework, Elevating Retrieval-Augmented… https://ai.gopubby.com/beyond-the-basics-raglabs-transparent-and-modular-framework-elevating-retrieval-augmented-29f7b3411050 | |||
| 17:37 | Beyond the Basics: RAGLAB’s Transparent and Modular Framework, Elevating Retrieval-Augmented… https://readqvick.medium.com/beyond-the-basics-raglabs-transparent-and-modular-framework-elevating-retrieval-augmented-29f7b3411050 | |||
| 17:29 | How publishers need to adapt in the era of RAG https://sarah-packowski.medium.com/how-publishers-need-to-adapt-in-the-era-of-rag-64ebe2c95540 | |||
| 17:25 | Bring Back the Good Old Timee Spelling Correctors https://medium.com/inkwell-atlas/bring-back-the-good-old-timee-spelling-correctors-59df8da4de17 | |||
| 17:07 | Simple React UI for Chatting with PDF using AI Locally https://medium.com/@magesh27/simple-react-ui-for-chatting-with-pdf-using-ai-locally-730720fe888e | |||
| 16:37 | Ollama PDF Chat Bot: A Streamlit-Based PDF Chat Application https://medium.com/@raj.varun454/ollama-pdf-chat-bot-a-streamlit-based-pdf-chat-application-5279aa786483 | |||
| 16:37 | Ollama PDF Chat Bot: A Streamlit-Based PDF Chat Application https://medium.com/@raj.ini/ollama-pdf-chat-bot-a-streamlit-based-pdf-chat-application-5279aa786483 | |||
| 16:16 | Transformers Architecture vs GPT Architecture https://medium.com/@ahmeterdempmk/transformers-architecture-vs-gpt-architecture-e6ef54d0e442 | |||
| 15:42 | Supervised Fine-tuning dilemma (What’s up with all those configurations?) https://medium.com/@anas.aberchih1/supervised-fine-tuning-dilemma-whats-up-with-all-those-configurations-a1f9040bb74e | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803