LLM News and Articles
Tuesday, 2024-10-29 | ||||
23:38 | How Paradigms Are Born — From Trial and Error to Self-Optimizing LLM Development Frameworks https://medium.com/artificial-intelligence-ai/how-paradigms-are-born-from-trial-and-error-to-self-optimizing-llm-development-frameworks-7e37f102a1bd | |||
22:18 | Claude 3.5 — The King of Document Intelligence https://levelup.gitconnected.com/claude-3-5-the-king-of-document-intelligence-f57bea1d209d | |||
22:18 | Evaluate & Elevate RAG Performance: Pre-Production https://levelup.gitconnected.com/evaluate-elevate-rag-performance-pre-production-6ce4f557387b | |||
22:17 | The Terrifying Truth About How Smart AI Really Is https://levelup.gitconnected.com/the-terrifying-truth-about-how-smart-ai-really-is-6a3c352cdc1a | |||
22:00 | VLMs and LLMs: The Dynamic Duo Revolutionizing AI https://medium.com/@kaushik.alakal.prakash/vlms-and-llms-the-dynamic-duo-revolutionizing-ai-fcd5562dbde5 | |||
21:15 | Part I — End-To-End RAG Building https://medium.com/@tushar.ganguli/part-i-end-to-end-rag-building-b87b958ef822 | |||
21:05 | Technical Security Challenges for LLM Design and Architecture https://medium.com/@paulnexus85/technical-security-challenges-for-llm-design-and-architecture-37535d373aff | |||
20:49 | LLM systems architecture — on Agentic Workflows https://medium.com/@baronlior/llm-systems-architecture-on-agentic-workflows-7aa6c9045973 | |||
20:17 | AI’nt That Easy #23: AI Agents in 2024 - A Practical Guide to When, Why, and Why Not https://aakriti-aggarwal.medium.com/aint-that-easy-23-ai-agents-in-2024-a-practical-guide-to-when-why-and-why-not-acc1b84b221a | |||
20:08 | OpenAI will start using AMD chips and could make its own AI hardware in 2026 https://www.theverge.com/2024/10/29/24282843/openai-custom-hardware-amd-nvidia-ai-chips | |||
20:03 | Knowledge Table Making Extraction Cool Again (with Rules) https://medium.com/enterprise-rag/knowledge-table-making-extraction-cool-again-with-rules-e37362c575d0 | |||
20:02 | How to Build Lightweight GraphRAG with SQLite https://medium.com/@tejeswar_79802/how-to-build-lightweight-graphrag-with-sqlite-04ddcb661f05 | |||
19:57 | Pdf-extract-API – OCR with marker-pdf and transform with Llama – single API call https://github.com/CatchTheTornado/pdf-extract-api | |||
19:57 | Concurrency and Parallelism in Python https://medium.com/@tejeswar_79802/concurrency-and-parallelism-in-python-5daa8fddcddd | |||
19:41 | ChatGPT now allows you to search through chat history https://twitter.com/OpenAI/status/1851340615344406781 | |||
19:40 | My initial foray into the world of Agents https://medium.com/tr-labs-ml-engineering-blog/my-initial-foray-into-the-world-of-agents-2a484c8da3e3 | |||
19:34 | A Beginner’s Guide to Large Language Models (LLMs) [Part01] https://blog.gopenai.com/a-beginners-guide-to-large-language-models-llms-part01-83308872b409 | |||
19:12 | GPT-NL is weggegooid geld https://medium.com/@bar.luttels/gpt-nl-is-weggegooid-geld-5d0dd9bf3de8 | |||
18:27 | Lookout! It’s an Evalanche! https://medium.com/snowflake/lookout-its-an-evalanche-cac23f983970 | |||
18:01 | Retrieval-Augmented Generation: Why naive RAG is not enough (and some ways to improve it) https://medium.com/@jerome.o.diaz/retrieval-augmented-generation-why-naive-rag-is-not-enough-and-some-ways-to-improve-it-b24e8234ebe5 | |||
17:39 | LangChain Magic: Cutting-Edge Techniques for Text Generation https://medium.com/@itsmybestview/langchain-magic-cutting-edge-techniques-for-text-generation-e09e64299998 | |||
17:25 | Guide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCode https://eamag.me/2024/How-to-use-local-LLMs-like-qwen-coder-for-autocomplete | |||
17:19 | OpenAI builds first chip with Broadcom and TSMC, scales back foundry ambition https://www.reuters.com/technology/artificial-intelligence/openai-builds-first-chip-with-broadcom-tsmc-scales-back-foundry-ambition-2024-10-29/ | |||
17:16 | An Agentic Approach to Textual Data Extraction Using LLMs and LangGraph https://towardsdatascience.com/an-agentic-approach-to-textual-data-extraction-using-llms-and-langgraph-8abb12af16f2 | |||
17:14 | Building Your Own AI Group Chat: A Journey into Custom Universes and Characters https://towardsdatascience.com/building-your-own-ai-group-chat-a-journey-into-custom-universes-and-characters-73634ee0253b | |||
17:07 | Retrieval-Augmented Generation (RAG) https://medium.com/@minimaldevops/retrieval-augmented-generation-rag-225c3313e5e4 | |||
17:02 | Logické myšlení velkých jazykových modelů https://medium.com/@lukysoon/logick%C3%A9-my%C5%A1len%C3%AD-velk%C3%BDch-jazykov%C3%BDch-model%C5%AF-2b4130c8a4b8 | |||
16:58 | From Code to English: The Evolving Language of Programming https://timothy-urista.medium.com/from-code-to-english-the-evolving-language-of-programming-a2d8a2b51d8d | |||
16:52 | Ollama ConnectError: [Errno 99] Cannot assign requested address https://medium.com/@infinityai/ollama-connecterror-errno-99-cannot-assign-requested-address-f0facad8027a | |||
16:29 | Building an Advanced AI-Powered Project: RAG, LLMs, Prompt Engineering, Data Science, and Machine… https://medium.com/@pratikabnave97/building-an-advanced-ai-powered-project-rag-llms-prompt-engineering-data-science-and-machine-aa22cda55299 | |||
16:20 | GitHub cuts AI deals with Google, Anthropic https://www.bloomberg.com/news/articles/2024-10-29/microsoft-s-github-unit-cuts-ai-deals-with-google-anthropic | |||
16:19 | Data Science Trends to Watch in 2025: The Rise of Generative AI, LLMs, Advanced Prompt Engineering… https://medium.com/@pratikabnave97/data-science-trends-to-watch-in-2025-the-rise-of-generative-ai-llms-advanced-prompt-engineering-b030d627b804 | |||
16:18 | Want Better Answers from Your Data? Discover the Power of Knowledge Graphs and LLMs! https://medium.com/@noahgothacked/want-better-answers-from-your-data-discover-the-power-of-knowledge-graphs-and-llms-927117868cd2 | |||
15:45 | How I Passed the “AWS Certified Machine Learning — Specialty”: A Journey from Prep to Certification https://medium.com/@rtvarma98/how-i-passed-the-aws-certified-machine-learning-specialty-a-journey-from-prep-to-certification-fd465ee5501b | |||
15:37 | An Introduction to AI Prompt Engineering and Input Tokenization https://medium.com/@mikka123/an-introduction-to-ai-prompt-engineering-and-input-tokenization-e0ce3b6695d8 | |||
15:35 | Exploring Top Vector Databases: A Detailed Comparison https://medium.com/vannguardai/exploring-top-vector-databases-a-detailed-comparison-6d4d0e21162e | |||
15:33 | Become a Master Prompt Engineer with ChatGPT Canvas https://medium.com/@jordan_gibbs/become-a-master-prompt-engineer-with-chatgpt-canvas-c4eebb8e4c23 | |||
15:29 | Quantum Computing 101: Essential Knowledge for Every Data Scientist https://medium.com/@jagansaravana27/quantum-computing-101-essential-knowledge-for-every-data-scientist-c0f31e7100e0 | |||
15:29 | Anthropic Raises the Bar with Claude 3.5 Sonnet https://medium.com/skymod-tech/anthropic-raises-the-bar-with-claude-3-5-sonnet-330196210b08 | |||
15:28 | Understanding Population-Based Training (PBT): A New Approach to Machine Learning https://medium.com/@punya8147_26846/understanding-population-based-training-pbt-a-new-approach-to-machine-learning-afe51b7f651a | |||
15:23 | A Beginner’s Guide to Hyperband and Successive Halving for Model Optimization https://medium.com/@punya8147_26846/a-beginners-guide-to-hyperband-and-successive-halving-for-model-optimization-892416d75080 | |||
15:14 | Unlocking the Power of Bayesian Optimization for Hyperparameter Tuning https://medium.com/@punya8147_26846/unlocking-the-power-of-bayesian-optimization-for-hyperparameter-tuning-0d3c568100d4 | |||
15:12 | LLMs and Mind; Foundations of Biolinguistics Amid the Hype https://medium.com/@carchidi.vince/llms-and-mind-foundations-of-biolinguistics-amid-the-hype-f2878741797c | |||
15:07 | Mastering Random Search Hyperparameter Tuning: A Beginner-Friendly Guide to Boosting Model… https://medium.com/@punya8147_26846/mastering-random-search-hyperparameter-tuning-a-beginner-friendly-guide-to-boosting-model-de8f5f1e1a32 | |||
15:04 | From Concept to Deployment: A Practical Guide to Developing Large Language Models (LLMs) https://wasimconsulting.medium.com/from-concept-to-deployment-a-practical-guide-to-developing-large-language-models-llms-d60b5841cade | |||
15:04 | Developing Large Language Models (LLMs): A Step-by-Step Guide from Concept to Deployment https://medium.com/the-generator/from-concept-to-deployment-a-practical-guide-to-developing-large-language-models-llms-d60b5841cade | |||
14:59 | Mastering Grid Search: A Beginner’s Guide to Hyperparameter Tuning in Machine Learning https://medium.com/@punya8147_26846/mastering-grid-search-a-beginners-guide-to-hyperparameter-tuning-in-machine-learning-bc78bc2723d3 | |||
14:45 | How Companies Are Using LLMs for Customer Support Automation https://medium.com/@punya8147_26846/how-companies-are-using-llms-for-customer-support-automation-34ade885d70d | |||
14:45 | Building a Introductory Gen AI Course for Middle School Students — a mission https://medium.com/@nayan.j.paul/building-a-introductory-gen-ai-course-for-middle-school-students-a-mission-817157a6233a | |||
14:41 | Few good cases for using LLM as Software Architect (part 2) https://medium.com/@deyo.vuk/few-good-cases-for-using-llm-as-software-architect-part-2-0bcd8fd54086 | |||
14:39 | DSPY : Stop Prompting Start Programing https://medium.com/@original2547/dspy-stop-prompting-start-programing-dae2b7e93df8 | |||
14:37 | DBSCAN: Density-Based Spatial Clustering of Applications with Noise https://medium.com/@punya8147_26846/dbscan-density-based-spatial-clustering-of-applications-with-noise-2d98b0fa5158 | |||
14:26 | DSPY : Stop Prompting Start Programing https://medium.com/@original2547/dspy-stop-prompting-start-programing-5abb9e79b027 | |||
12:43 | Dialog Engineering vs Prompt Engineering https://medium.com/@dreamai/dialog-engineering-vs-prompt-engineering-19d985ae43ea | |||
12:40 | Debunking Apple’s claim ‘LLMs don’t perform reasoning’ https://medium.com/@paul.k.pallaghy/debunking-apples-claim-llms-don-t-perform-reasoning-a34891b1f355 | |||
12:27 | The Limits of Large Language Models in Predicting Social Science Experiment Outcomes: An… https://medium.com/@jsmith0475/the-limits-of-large-language-models-in-predicting-social-science-experiment-outcomes-an-3e55de1bbb09 | |||
12:17 | Understanding the Multi-modal Projector in LLaVA https://medium.com/@kuipasta1121/understanding-the-multi-modal-projector-in-llava-d1bc89debbd5 | |||
12:16 | Transformers for Dummies — Word Embeddings https://medium.com/womenintechnology/transformers-for-dummies-word-embeddings-1c9ade5ff500 | |||
12:02 | The Next Evolution in Artificial Intelligence: Agentic AI https://pub.towardsai.net/the-next-evolution-in-artificial-intelligence-agentic-ai-e92e0feb6191 | |||
11:33 | The Future of AI: Insights from HPE and Weaviate on Open Source, Agents, and Beyond https://medium.com/@jaydugad10/the-future-of-ai-insights-from-hpe-and-weaviate-on-open-source-agents-and-beyond-510c82ec28a4 | |||
11:12 | LLM’s explained as if you are 5. What goes inside it https://medium.com/@santoshpadma9/llms-explained-as-if-you-are-5-what-goes-inside-it-b70e5c245836 | |||
11:02 | Recent Study Reveals Why LLMs Are Still Struggling with True Logical Reasoning https://aiintransit.medium.com/recent-study-reveals-why-llms-are-still-struggling-with-true-logical-reasoning-fc69886387fa | |||
10:51 | Book Brief: ChatGPT and the Future of AI https://clearpurpose.media/book-brief-chatgpt-and-the-future-of-ai-c2a145fc68b9 | |||
10:50 | Building Market-Ready SaaS and AI Products: A Strategic Guide https://medium.com/@sherifmoh2022/building-market-ready-saas-and-ai-products-a-strategic-guide-408a3a42319a | |||
10:18 | Enhancing E-Commerce Search with AI: Leveraging Self-Hosted Embeddings and Vector Indexing https://medium.com/@ajay.bansal02/enhancing-e-commerce-search-with-ai-leveraging-self-hosted-embeddings-and-vector-indexing-c427af94a566 | |||
10:18 | Meta révolutionne l’Open Source avec NotebookLlama : une alternative puissante et… https://blog.ia-web3.fr/meta-r%C3%A9volutionne-lopen-source-avec-notebookllama-une-alternative-puissante-et-3e18a4854f88 | |||
10:13 | Some important terms in Gen AI https://medium.com/@alzaha2427/some-important-terms-in-gen-ai-626643411e8c | |||
09:52 | Building a Telegram Bot for Real-Time Web Summaries and Q&A with LlamaIndex https://medium.com/@sean_w15723/building-a-telegram-bot-for-real-time-web-summaries-and-q-a-with-llamaindex-e47e44e9976b | |||
09:49 | Attention entropy in transformers https://gauranshiitd.medium.com/attention-entropy-in-transformers-8418421a1ff9 | |||
09:45 | How I placed Chatbot creation within the broader field of AI (and why AI engineer title is… https://medium.com/@MemoonaTahira/how-i-placed-chatbot-creation-within-the-broader-field-of-ai-and-why-ai-engineer-title-is-ed27346dc24e | |||
08:46 | Paper Review: Unbounded: A Generative Infinite Game of Character Life Simulation https://artgor.medium.com/paper-review-unbounded-a-generative-infinite-game-of-character-life-simulation-2c6fc2409954 | |||
08:35 | AI-Driven Insights: Analyzing Jharkhand Assembly Elections 2024 Using Large Language Models https://medium.com/@tabrejmsc2008/ai-driven-insights-analyzing-jharkhand-assembly-elections-2024-using-large-language-models-1147c6f0bf3e | |||
08:21 | Build vs. Buy: LLM Adoption for Web Scraping in Finance https://www.kadoa.com/blog/build-vs-buy | |||
08:08 | 3 Typical Misconceptions About Developing LLM Applications https://medium.com/creative-data/3-typical-misconceptions-about-developing-llm-applications-60fa746847a7 | |||
08:02 | The Common Failure Points of LLM RAG Systems and How to Overcome Them https://medium.com/@sahin.samia/the-common-failure-points-of-llm-rag-systems-and-how-to-overcome-them-926d9090a88f | |||
07:59 | Breaking Ground: Important AI development and announcements https://medium.com/aingineer/breaking-ground-important-ai-development-and-announcements-f3db76bd0d01 | |||
07:56 | Thoughts on Edge Computing: The new rules of Data and AI https://medium.com/@ydgandhi/thoughts-on-edge-computing-the-new-rules-of-data-and-ai-f95e0b469feb | |||
07:19 | AI-Driven Innovations in Legaltech and Regtech https://medium.com/@bART.Solutions/ai-driven-innovations-in-legaltech-and-regtech-4420628068af | |||
07:06 | Prompt 101: Memory Basics of Computer Science https://medium.com/@VA9757/prompt-101-memory-basics-of-computer-science-30f2fe64e6fc | |||
06:51 | Building an AI ChatBot with RAG and LangChain https://medium.com/@shimjaehun/building-an-ai-chatbot-with-rag-and-langchain-083e011348a1 | |||
06:49 | SQLRAG: Transforming Database Interactions with Natural Language and LLMs https://abdulla-ansari.medium.com/sqlrag-transforming-database-interactions-with-natural-language-and-llms-de0a77c31fe5 | |||
06:17 | Episode-0: Cracking Typhoon LLM Inference Performance https://blog.opentyphoon.ai/episode-0-cracking-typhoon-llm-inference-performance-a0b119c5d86c | |||
06:16 | Equal-Width Binning in Machine Learning: A Comprehensive Guide https://medium.com/@punya8147_26846/equal-width-binning-in-machine-learning-a-comprehensive-guide-de31cff32ddc | |||
05:32 | Exploring Retrieval Augmented Generation in DSPy with a Custom Pinecone Retriever https://medium.com/@tsarshah/exploring-retrieval-augmented-generation-in-dspy-with-a-custom-pinecone-retriever-0ba90df2d978 | |||
05:27 | Challenges in Time-Series Feature Engineering https://medium.com/@punya8147_26846/challenges-in-time-series-feature-engineering-3d68cb4dd379 | |||
05:22 | Understanding Time-Series Features in Machine Learning https://medium.com/@punya8147_26846/understanding-time-series-features-in-machine-learning-77f2d5935c6f | |||
05:01 | Introduction to Feature Engineering for Machine Learning https://medium.com/@punya8147_26846/introduction-to-feature-engineering-for-machine-learning-f97bbcd7ed13 | |||
04:57 | An Expanded Context at TED AI ‘24 https://humber.to/an-expanded-context-at-ted-ai-24-44661d86e76b | |||
04:49 | Why NotebookLM Could Be an Awesome Educational Tool for Grad Students: Tips and Tricks for… https://f-i-tushar-eee.medium.com/why-notebooklm-could-be-an-awesome-educational-tool-for-grad-students-tips-and-tricks-for-76243ebdadbf | |||
03:03 | Transformers and self-attention: no illustration deep dive into how they work https://medium.com/@mohammadashtari/transformers-and-self-attention-no-illustration-deep-dive-into-how-they-work-57391bd2b113 | |||
02:53 | Using Large Language Models APIs with Python: A Comprehensive Guide https://medium.com/@lokaregns/using-large-language-models-apis-with-python-a-comprehensive-guide-0020a51bf5b6 | |||
02:28 | Production-Grade AI: What Benchmark Score Should Your LLM Reach? https://stories.riafy.me/production-grade-ai-what-benchmark-score-should-your-llm-reach-abe30ba4319e | |||
02:23 | What Are Large Language Models (LLMs)? https://medium.com/@aiduodigest/what-are-large-language-models-llms-23c70a296560 | |||
02:23 | Ethos, Logos, Pathos: AI’s Human Frontier https://medium.com/@nguyenthanh.asia/ethos-logos-pathos-ais-human-frontier-f43fe288916f | |||
01:33 | Hello Prompt flow (1) https://medium.com/@ilhamfadhil/hello-prompt-flow-1-20a17345fa8f | |||
00:02 | Nook’s Notes: David Youngblood https://medium.com/@blue.pear/nooks-notes-david-youngblood-b91969dfab63 | |||
00:00 | Universal Assisted Generation: Faster Decoding with Any Assistant Model https://huggingface.co/blog/universal_assisted_generation | |||
Monday, 2024-10-28 | ||||
23:38 | Running the STORM AI research system with your local documents https://towardsdatascience.com/running-the-storm-ai-research-system-with-your-local-documents-e413ea2ae064 | |||
23:08 | Germination in A.G.E.
The Blueprint for GenAI Scalability https://medium.com/@dinoage_67004/germination-in-a-g-e-the-blueprint-for-genai-scalability-2f909181caf4 | |||
22:52 | Integrating SharePoint Sites with Azure Blob Storage for a Custom RAG Chatbot Using LangChain and… https://medium.com/@sourabh_sardesai/integrating-sharepoint-sites-with-azure-blob-storage-for-a-custom-rag-chatbot-using-langchain-and-92b93430c005 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110