LLM News and Articles
| Tuesday, 2024-08-20 | ||||
| 04:54 | How to Effortlessly Extract Receipt Information with OCR and GPT-4o mini https://towardsdatascience.com/how-to-effortlessly-extract-receipt-information-with-ocr-and-gpt-4o-mini-0825b4ac1fea | |||
| 04:29 | A Cutting-Edge Framework for Evaluating LLM Output https://medium.com/cwan-engineering/a-cutting-edge-framework-for-evaluating-llm-output-edab53373514 | |||
| 04:13 | ChatGPT makes a user complain that a library is missing a feature it never had https://twitter.com/lemire/status/1825627821089370249 | |||
| 03:52 | Using instructor with a private Azure endpoint https://dipam44.medium.com/using-instructor-with-a-private-azure-endpoint-df03c40e4c71 | |||
| 03:41 | The AI Arms Race: A Deep Dive into the Top LLMs https://ai.plainenglish.io/the-ai-arms-race-a-deep-dive-into-the-top-llms-091e645ee200 | |||
| 02:23 | GenAI — Storing Tables Metadata for Query Generation https://verticalserve.medium.com/genai-storing-tables-metadata-for-query-generation-693f8bf04741 | |||
| 01:39 | Embedding Trust into Text-to-SQL AI Agents https://towardsdatascience.com/embedding-trust-into-text-to-sql-ai-agents-3f15d0ddaf1a | |||
| 00:39 | KOALA (K-layer Optimized Adversarial Learning Architecture): An Orthogonal Technique for Draft Head Optimization https://www.marktechpost.com/2024/08/19/koala-k-layer-optimized-adversarial-learning-architecture-an-orthogonal-technique-for-draft-head-optimization/ | |||
| 00:21 | Building a End to End Multi-Modal RAG System Using AWS Bedrock And Langchain https://medium.com/@aaryangupta2201/building-a-multi-modal-rag-system-using-aws-bedrock-and-langchain-e8fd44736efa | |||
| 00:21 | Building a End to End Multi-Modal RAG System Using AWS Bedrock And Langchain https://faun.pub/building-a-multi-modal-rag-system-using-aws-bedrock-and-langchain-e8fd44736efa | |||
| 00:11 | TOXIGEN explained: A short summary for busy readers https://medium.com/@minhle_0210/toxigen-explained-a-short-summary-for-busy-readers-4b2592d647b3 | |||
| Monday, 2024-08-19 | ||||
| 23:40 | Meta Agent Search : Automated System Design Creation for LLM based Agentic Systems https://medium.com/@techsachin/meta-agent-search-automated-system-design-creation-for-llm-based-agentic-systems-a5e2de9f3f46 | |||
| 22:23 | AI Trust & Safety — A New Tech Stack Requires New Solutions https://medium.com/wtv-in-the-flow/ai-trust-safety-65e944041ad8 | |||
| 22:03 | GPT-Free Art https://www.gpt-free.art/ | |||
| 21:39 | How to Get Structured Output from LLMs Applications Using Pydantic and Instrutor https://medium.com/@pedro.aquino.se/how-to-get-structured-output-from-llms-applications-using-pydantic-and-instrutor-87d237c03073 | |||
| 21:20 | How to Generate Structured Outputs with Google’s Gemini API: A Comprehensive Guide https://medium.com/@mohammed97ashraf/how-to-generate-structured-outputs-with-googles-gemini-api-a-comprehensive-guide-384421650e21 | |||
| 20:54 | Finetune llama 3.1 https://medium.com/@csheehan1/finetune-llama-3-1-bfbd5ca0c1eb | |||
| 19:07 | Why I Prefer OpenAI’s SDK for LLM Function Calling Over Abstractions https://medium.com/@vijayvikramsingh85/why-i-prefer-openais-sdk-for-llm-function-calling-over-abstractions-b5e4e276e769 | |||
| 19:00 | Analyzing the Stock Market with AI https://medium.com/neuml/analyzing-the-stock-market-with-ai-df3a17ce0b4f | |||
| 18:56 | LSTM vs. Transformers: A Comparative Study in Sequence Generation https://sanchezsanchezsergio418.medium.com/lstm-vs-transformers-a-comparative-study-in-sequence-generation-310375867131 | |||
| 18:35 | StepByStep: Understanding RAG Basics, its Patterns, and its Stages — Part One: Data Loaders https://medium.com/@ignacioperezzv/stepbystep-understanding-rag-basics-its-patterns-and-its-stages-part-one-data-loaders-e5c81727d0ea | |||
| 17:50 | AI is a Feature, Not a Product. https://medium.com/@caseyjohnsonwv/ai-is-a-feature-not-a-product-0b2ba03dd6fd | |||
| 17:46 | Why Achieving Higher Accuracy in Next LLM Models Is Becoming More Difficult https://ai.plainenglish.io/why-achieving-higher-accuracy-in-next-llm-models-is-becoming-more-difficult-4615bd0a5977 | |||
| 17:39 | Overcoming the AI Data Crisis: A New Solution to Model Collapse https://nyudatascience.medium.com/overcoming-the-ai-data-crisis-a-new-solution-to-model-collapse-ddc5b382e182 | |||
| 17:38 | Building LLM Apps: How Is It Different from Traditional Software? https://medium.com/@anindyaju99/building-llm-apps-how-is-it-different-from-traditional-software-b0054a1e1087 | |||
| 17:37 | What is Pruning and knowledge Distillation in LLM? https://ai.plainenglish.io/what-is-pruning-and-knowledge-distillation-in-llm-a2cceca369c5 | |||
| 17:34 | LLAMA 3: A New Frontier in Large Language Models https://medium.com/@siladityaghosh/llama-3-a-new-frontier-in-large-language-models-d60d0edcc383 | |||
| 17:11 | How does LLM work? https://medium.com/@aasthad27/how-does-llm-work-bbf72335592f | |||
| 16:44 | Automated code reviews with LLMs https://craft.faire.com/automated-code-reviews-with-llms-cf2cc51bb6d3 | |||
| 16:26 | IntellaNOVA Newsletter #18 — From Vector Databases Dilemma & Snowflake’s Universal Search to… https://medium.com/@ibbyrahmani/intellanova-newsletter-18-from-vector-databases-dilemma-snowflakes-universal-search-to-c1425415a413 | |||
| 16:18 | Building an easy fast and light LLM on your local laptop https://medium.com/@kamelyoussef1996/building-an-easy-fast-and-light-llm-on-your-local-laptop-a42516112d1a | |||
| 16:10 | Unlocking GPT-2: An Interactive Guide to Understanding Text Generation with Transformer Explainer https://medium.com/@xjaroo.iphone/unlocking-gpt-2-an-interactive-guide-to-understanding-text-generation-with-transformer-explainer-719588f04d1f | |||
| 15:51 | Building a legal chatbot using large language models (LLMs) https://medium.com/@sivaprasadbose/building-a-legal-chatbot-using-large-language-models-llms-6e1796ee167c | |||
| 15:33 | Unveiling the Power of Mixture of Workflows for Financial Data Insights https://medium.com/@manthapavankumar11/unveiling-the-power-of-mixture-of-workflows-for-financial-data-insights-c97a4634ebfe | |||
| 15:31 | RAG vs. Traditional LLMs: The AI Showdown You Need to Know About https://medium.com/@shribadal/rag-vs-traditional-llms-the-ai-showdown-you-need-to-know-about-4d1a5d59ba62 | |||
| 15:25 | Generative AI Adoption Roadblocks, Pit Stops, Crashes, and Destinations https://medium.com/@Kyle_AI/generative-ai-adoption-roadblocks-pit-stops-crashes-and-destinations-ae033e8dbe27 | |||
| 15:14 | How Far Can Prompt Engineering Go? https://angelina-yang.medium.com/how-far-can-prompt-engineering-go-cb9da95db34b | |||
| 15:07 | ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA datasets with… https://medium.com/@EleventhHourEnthusiast/convkgyarn-spinning-configurable-and-scalable-conversational-knowledge-graph-qa-datasets-with-1ca68eacfa44 | |||
| 15:07 | Improving LLM-based KGQA for multi-hop Question Answering with implicit reasoning in few-shot… https://medium.com/@EleventhHourEnthusiast/improving-llm-based-kgqa-for-multi-hop-question-answering-with-implicit-reasoning-in-few-shot-323f4a1e68f1 | |||
| 15:01 | From Bias to Security: A Data Product Manager’s Guide to LLM Safety https://medium.com/@lex.dpm/from-bias-to-security-a-data-product-managers-guide-to-llm-safety-3bfa7c478e6c | |||
| 14:54 | Blended RAG: Revolutionizing Retrieval-Augmented Generation for Generative Q&A Systems https://medium.com/towards-generative-ai/blended-rag-revolutionizing-retrieval-augmented-generation-for-generative-q-a-systems-cedeb160a88b | |||
| 14:47 | Self-reasoning AI // Multi-step approach, looks like Agentic RAG https://sbagency.medium.com/self-reasoning-ai-multi-step-approach-looks-like-agentic-rag-a69c7b235404 | |||
| 14:35 | Ollama now supports tool calling with popular models in local LLM https://ollama.com/blog/tool-support | |||
| 14:33 | Alan-Özgü LLM Projesi: Yapay Zeka Nasıl Yanıt Oluşturur? https://medium.com/@abdulvahapmutlu/alan-%C3%B6zg%C3%BC-llm-projesi-yapay-zeka-nas%C4%B1l-yan%C4%B1t-olu%C5%9Fturur-28d334320170 | |||
| 14:20 | Is Claude 3.5 Sonnet Getting Dumber? You Might Not Be Hallucinating https://towards-agi.medium.com/is-claude-3-5-sonnet-getting-dumber-you-might-not-be-hallucinating-f64c6cf7df44 | |||
| 14:02 | AI Agents in Enterprise Production Environments https://ogre51.medium.com/ai-agents-in-enterprise-production-environments-fbcd8d1e9026 | |||
| 13:47 | Evaluating Summarisation: A Roadmap to Measuring LLM Success https://medium.com/@aartijha96/evaluating-summarisation-a-roadmap-to-measuring-llm-success-76218ac90cd0 | |||
| 13:29 | Yipada: A smooth, boundless paraphraser https://medium.com/@olafeezee/yipada-a-smooth-boundless-paraphraser-f301020d94ab | |||
| 13:17 | The Transformer Model: Revolutionizing Natural Language Processing https://medium.com/@siladityaghosh/the-transformer-model-revolutionizing-natural-language-processing-3e863a69ecfb | |||
| 12:48 | Practical Uses and Success with LLM Models, RAG Databases, Langchain https://medium.com/profil-software-blog/practical-uses-and-success-with-llm-models-rag-databases-langchain-1c97bd6039bc | |||
| 12:45 | How I created and published a custom GPT in under 15 minutes https://medium.com/@woyera/how-i-created-and-published-a-custom-gpt-in-under-15-minutes-44283ca25df8 | |||
| 12:45 | Fine-Tuning Large Language Models Using LoRA: (Must read before fine tuning) https://medium.com/@mirzasamaddanat/fine-tuning-large-language-models-using-lora-must-read-before-fine-tuning-ec9630458b18 | |||
| 12:43 | Introductory LLM: Tiny-ShakeSpeareGPT https://olamidipupo.medium.com/introductory-llm-tiny-shakespearegpt-977ce1416acb | |||
| 12:40 | Training a Large Language Model: Essential Steps and Processes https://taylor-mark110.medium.com/training-a-large-language-model-essential-steps-and-processes-701cfd7533f2 | |||
| 12:31 | How to create a custom chatbot using Mistral https://medium.com/@abdulrahmanrihan/how-to-create-a-custom-chatbot-using-mistral-bfa492b3185d | |||
| 12:29 | ColPali Explained: Bridging the Gap Between Text and Visual Content https://medium.com/@shashankvats/colpali-explained-bridging-the-gap-between-text-and-visual-content-d3dad7ac01f0 | |||
| 12:24 | Leveraging LLMs: Building a Streamlit App that Interacts with Your Data https://medium.com/@venkatekkuluri/leveraging-llms-building-a-streamlit-app-for-converting-text-to-sql-and-executing-queries-in-5036ed61a84e | |||
| 12:02 | vLLM and LLM-compressor are here https://bkarak.medium.com/vllm-and-llm-compressor-are-here-0f1bab7b32bc | |||
| 11:31 | Required GPU Memory For Serving LLMs With A Simple Formula https://medium.com/physics-and-machine-learning/required-gpu-memory-for-serving-llms-with-a-simple-formula-01cd2f0ea310 | |||
| 11:30 | Ready to take a BITE? This little-known Technique Makes any LLM Work Like a Charm https://medium.com/@florian.schneider88/ready-to-take-a-bite-this-little-known-technique-makes-any-llm-work-like-a-charm-ba790994bca5 | |||
| 11:18 | Introducing RAG: A Developer’s Guide to a scalable, context-driven LLM system https://medium.com/newnow-blog/introducing-rag-a-developers-guide-to-a-scalable-context-driven-llm-system-cd75102779d2 | |||
| 11:12 | AI-Powered ArXiv Research Tracker: Daily Summaries Using Large Language Models https://medium.com/@santhoshkammari/ai-powered-arxiv-research-tracker-daily-summaries-using-large-language-models-4bf8edd54601 | |||
| 10:46 | Generative AI Interview Questions [LLM] Top 20 — Part : 1 https://medium.com/@simranjeetsingh1497/generative-ai-interview-questions-llm-top-20-part-1-b851c65011b6 | |||
| 10:41 | Bforbank’s #TeamTech in Devoxx 2024 https://medium.com/bforbank-tech/bforbanks-teamtech-in-devoxx-2024-0cce7a0bd7be | |||
| 10:40 | Leveraging AWS Lambda and EventBridge for a Multilingual Slack Bot https://medium.com/serverless-transformation/leveraging-aws-lambda-and-eventbridge-for-a-multilingual-slack-bot-1b5fb9cf1a0e | |||
| 10:34 | Everything about Sora.AI revealed, Why is it revolutionary?? https://medium.com/@dagimbezabih1/everything-about-sora-ai-revealed-why-is-it-revolutionary-39a9ad193a64 | |||
| 10:18 | Fine-Tuning Large Language Models with QLoRA: A Deep Dive into Optimized Training on Finance Data https://kshitijkutumbe.medium.com/fine-tuning-large-language-models-with-qlora-a-deep-dive-into-optimized-training-on-finance-data-6c2db4d0a692 | |||
| 10:02 | Serving Large models (part two): Ollama and TGI https://medium.com/@ayoubkirouane3/serving-large-models-part-two-ollama-and-tgi-c084bbb57050 | |||
| 09:49 | How To Improve the Performance of a RAG Model https://ai.plainenglish.io/how-to-improve-the-performance-of-a-rag-model-562fd65778f6 | |||
| 09:45 | ArabLegalEval: A Multitask AI Benchmark Dataset for Assessing the Arabic Legal Knowledge of LLMs https://www.marktechpost.com/2024/08/19/arablegaleval-a-multitask-ai-benchmark-dataset-for-assessing-the-arabic-legal-knowledge-of-llms/ | |||
| 09:33 | Death by AI Prompts: Example and Generator Development Guide https://medium.com/@marketing_novita.ai/death-by-ai-prompts-example-and-generator-development-guide-034946b3f9aa | |||
| 09:11 | Virtuous Cycle of LLM Improvement https://medium.com/collaborne-engineering/virtuous-cycle-of-llm-improvement-6bc58e1d1216 | |||
| 09:03 | Save 50% on OpenAI: Complete Guide to Batch Requests https://blog.gopenai.com/save-50-on-openai-complete-guide-to-batch-requests-e4019e66ca5d | |||
| 08:57 | The Art of Weight Quantization in Large Language Models: Balancing Precision and Efficiency https://medium.com/@vishal025/the-art-of-weight-quantization-in-large-language-models-balancing-precision-and-efficiency-3f4f518731c3 | |||
| 08:53 | How Retrieval Augmented Generation (RAG) is Shaping the Next Wave of Generative AI https://medium.com/@datalensAI/how-retrieval-augmented-generation-rag-is-shaping-the-next-wave-of-generative-ai-21ada3dcb376 | |||
| 08:31 | RAG — Retrieval Augmented Generation https://medium.com/@merve.din16/rag-retrieval-augmented-generation-45c895d81052 | |||
| 08:29 | The Guide to building Self-Healing Agents using LLMs https://medium.com/@pranav.marla/the-guide-to-building-self-healing-agents-using-llms-0827dc5fc8ee | |||
| 08:22 | Minimum value agent from scratch: with llama3-groq-tool and streamlit UI https://autognosi.medium.com/minimum-value-agent-from-scratch-with-llama3-groq-tool-and-streamlit-ui-05995be3b70f | |||
| 08:18 | Build a Customer Support Assistant with Llama3.1 https://mrmaheshrajput.medium.com/build-a-customer-support-assistant-with-llama3-1-7bf60611e428 | |||
| 08:05 | LangGraph Agents By LangChain https://cobusgreyling.medium.com/langgraph-agents-by-langchain-c1f6ebd86c38 | |||
| 07:43 | Sistemas RAG y su impacto en la IA https://medium.com/@alexandr.ia/sistemas-rag-y-su-impacto-en-la-ia-762f88323a5f | |||
| 07:18 | Comprehensive Guide to Running Large Language Models like LLaMA on CPUs https://kshitijkutumbe.medium.com/comprehensive-guide-to-running-large-language-models-like-llama-on-cpus-71d56739f58d | |||
| 06:50 | Atom Capital: Is AI a Bubble? A Look at the Current State of the AI Industry https://medium.com/@atomcapital/atom-capital-is-ai-a-bubble-a-look-at-the-current-state-of-the-ai-industry-20ab618067d9 | |||
| 06:31 | ChatPaper Review: Stay Updated on AI Research for Free https://medium.com/@chatdocai/chatpaper-review-stay-updated-on-ai-research-for-free-28582642760f | |||
| 06:28 | AI’s Confidence Crisis: When Chatbots Get Cocky https://medium.com/@mindmachina/ais-confidence-crisis-when-chatbots-get-cocky-a1b2edc9d133 | |||
| 06:17 | Chat with your Obsidian notes using the Falcon Mamba 7B model https://python.plainenglish.io/chat-with-your-obsidian-notes-using-the-falcon-mamba-7b-model-606fa220a601 | |||
| 06:00 | Understanding the 27 Unique Challenges in Large Language Model Development: An Empirical Study of Over 29,000 Developer Forum Posts and 54% Unresolved Issues https://www.marktechpost.com/2024/08/18/understanding-the-27-unique-challenges-in-large-language-model-development-an-empirical-study-of-over-29000-developer-forum-posts-and-54-unresolved-issues/ | |||
| 05:22 | LLMs Still Can’t Plan And Reason https://medium.com/aiguys/llms-still-cant-plan-and-reason-1026919225fb | |||
| 05:12 | Knowledge graph extraction using LLMs // Advanced RAG https://sbagency.medium.com/knowledge-graph-extraction-using-llms-advanced-rag-642808c7c876 | |||
| 05:04 | Building a Versatile AI Chatbot with LangGraph: A Step-by-Step Guide https://devendrabogati.medium.com/building-a-versatile-ai-chatbot-with-langgraph-a-step-by-step-guide-10047893972d | |||
| 05:00 | The Challenges of Implementing Retrieval Augmented Generation (RAG) in Production https://www.marktechpost.com/2024/08/18/the-challenges-of-implementing-retrieval-augmented-generation-rag-in-production/ | |||
| 04:55 | Paper Review: Winning Amazon KDD Cup24 https://artgor.medium.com/paper-review-winning-amazon-kdd-cup24-0c4bdac187e2 | |||
| 04:39 | LLM-Powered Summaries: Unlock Business Insights with Chain of Density https://medium.com/@the_manoj_desai/llm-powered-summaries-unlock-business-insights-with-chain-of-density-3ef8fbcca9f2 | |||
| 04:17 | Enhancing Civil Engineering Calculations in Chatbots with CalcTree API Integration https://python.plainenglish.io/enhancing-civil-engineering-calculations-in-chatbots-with-calctree-api-integration-52c4058a6a4b | |||
| 03:51 | End to end LLMOps Pipeline — Part 7- Validating Kubernetes Manifests with kube-score https://devopslearning.medium.com/end-to-end-llmops-pipeline-part-7-validating-kubernetes-manifests-with-kube-score-fa60a19f6581 | |||
| 02:52 | How to Glean Insights from Support Requests Using Prompt Engineering https://medium.com/@sellermichael/how-to-glean-insights-from-support-requests-using-prompt-engineering-2478ca8c1416 | |||
| 02:52 | The Schema Connection: Unlocking Human-like Adaptability in Large Language Models. https://medium.com/@cuba6112/the-schema-connection-unlocking-human-like-adaptability-in-large-language-models-f18ddef0267a | |||
| 01:02 | My conversation with Perplexity AI Pro https://stingraze.medium.com/my-conversation-with-perplexity-ai-pro-be4c3255b9d7 | |||
| 00:00 | Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI https://huggingface.co/blog/llama31-on-vertex-ai | |||
| Sunday, 2024-08-18 | ||||
| 23:15 | 30 days of learning LLM! https://medium.com/@insight_ninja/30-days-of-learning-llm-2c78211216aa | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803