LLM News and Articles
| Friday, 2024-09-20 | ||||
| 05:17 | Atom Capital:OpenAI o1—A Calculated Gambit and the Dawn of a New Era https://medium.com/@atomcapital/atom-capital-openai-o1-a-calculated-gambit-and-the-dawn-of-a-new-era-634bef831542 | |||
| 05:16 | Iteration of Thought: multi-agent framework to enhance LLM Reasoning capabilities https://medium.com/@techsachin/iteration-of-thought-multi-agent-framework-to-enhance-llm-reasoning-capabilities-fb10f7cb7a29 | |||
| 05:09 | Understanding the Core Primitives of Large Language Models (LLMs) https://mohamed-elrefaey-77102.medium.com/understanding-the-core-primitives-of-large-language-models-llms-0e5402657018 | |||
| 04:25 | How to Use FAISS with LangChat for Efficient Data Search https://medium.com/@garysvenson09/how-to-use-faiss-with-langchat-for-efficient-data-search-6b743989d1b7 | |||
| 03:18 | How to Make Predictions with PyTorch Lightning Checkpoint https://medium.com/@asakisakamoto02/how-to-make-predictions-with-pytorch-lightning-checkpoint-2f1ec20223c9 | |||
| 03:08 | Reflection Llama-3.1 70B: A Leap Forward https://s-hash-wat.medium.com/reflection-llama-3-1-70b-a-leap-forward-5604b62c7035 | |||
| 02:48 | Revolutionizing Immigration: How USCIS Can Leverage LLMs to Transform the Future of Immigration… https://medium.com/@shethaadit/revolutionizing-immigration-how-uscis-can-leverage-llms-to-transform-the-future-of-immigration-442d146a81fd | |||
| 02:30 | 8 Insights from Working with LLM Recently https://medium.com/@yuanyi1119/8-insights-from-working-with-llm-recently-ebadc03fce2b | |||
| 02:27 | Integrating OpenAI’s Large Language Models with .NET: Unlocking Intelligent Applications https://medium.com/@shethaadit/integrating-openais-large-language-models-with-net-unlocking-intelligent-applications-4f844d88d74d | |||
| 02:16 | How to Ensure Application Integration Best Practices for Success https://medium.com/@tayloroakley/how-to-ensure-application-integration-best-practices-for-success-17e0d8d40773 | |||
| 02:05 | Microsoft Eureka- an LLM Framework https://github.com/microsoft/eureka-ml-insights | |||
| 01:57 | Anthropic – Introducing Contextual Retrieval https://www.anthropic.com/news/contextual-retrieval | |||
| 01:45 | Bedrock Claude Pricing, Benchmarks, and Usage Guide https://medium.com/@getanakin/bedrock-claude-pricing-benchmarks-and-usage-guide-0ee4e377c2d8 | |||
| 01:23 | Demystifying Large Language Models: The AI Powerhouse Behind Your Favourite Apps https://medium.com/@joshilatika2915/demystifying-large-language-models-the-ai-powerhouse-behind-your-favourite-apps-6c1401ab85d9 | |||
| 01:17 | Magicore: Multi Agent Iteration Framework for Coarse-to-fine Refinement for improved LLM solution… https://medium.com/@techsachin/magicore-multi-agent-iteration-framework-for-coarse-to-fine-refinement-for-improved-llm-solution-538dd6bce57e | |||
| 01:01 | Fixing ChatGPT’s “delve” obsession https://jackpion.medium.com/fixing-chatgpts-delve-obsession-a63b0cd03343 | |||
| 00:57 | Gandalf Lakera AI — izazov ubrizgavanja prompta https://medium.com/in-search-for-knowledge/gandalf-lakera-ai-izazov-ubrizgavanja-prompta-dfbf0ab3e602 | |||
| 00:25 | How to Integrate Langchain OpenAI into Your Applications https://medium.com/@garysvenson09/how-to-integrate-langchain-openai-into-your-applications-733cd02257c3 | |||
| 00:03 | Rodando modelos de LLMs localmente com Ollama https://medium.com/@michel.macario/rodando-modelos-de-llms-localmente-com-ollama-038322fbc7ac | |||
| 00:00 | Optimize and deploy models with Optimum-Intel and OpenVINO GenAI https://huggingface.co/blog/deploy-with-openvino | |||
| Thursday, 2024-09-19 | ||||
| 23:46 | Mastering Prompt Engineering: Essential Insights https://ppujari.medium.com/mastering-prompt-engineering-essential-insights-34f4b50bf015 | |||
| 23:41 | Through the Uncanny Mirror: Do LLMs Remember Like the Human Mind? https://towardsdatascience.com/through-the-uncanny-mirror-do-llms-remember-like-the-human-mind-cc9c63677610 | |||
| 23:21 | AGI: Attention To Attention Is All You Need https://medium.com/@sergio.dubois/agi-attention-to-attention-is-all-you-need-fccb6fc326e0 | |||
| 23:19 | How to Manage PostgreSQL Visibility for Temporal Data https://medium.com/@asakisakamoto02/how-to-manage-postgresql-visibility-for-temporal-data-e28e6fc7c5d6 | |||
| 23:00 | Building a Simple Q&A Chat Completion App with Langchain and Streamlit https://medium.com/@kalakonda.spandana19/building-a-simple-q-a-chat-completion-app-with-langchain-and-streamlit-9345fcab5a76 | |||
| 22:59 | [Day 1] The Interdisciplinary Revolution of LLMs, Blockchain, and Game Theory https://josephtw0305.medium.com/day-1-the-interdisciplinary-revolution-of-llms-blockchain-and-game-theory-d0462efdd7ac | |||
| 22:42 | AI in Software Testing: Revolutionizing Quality Assurance https://medium.com/@amalraju7907/ai-in-software-testing-revolutionizing-quality-assurance-57421f305e57 | |||
| 22:41 | Building LLM-powered applications in Go https://go.dev/blog/llmpowered | |||
| 22:17 | How to Use One Way Sync for Efficient File Management https://medium.com/@tayloroakley/how-to-use-one-way-sync-for-efficient-file-management-9ee392d79688 | |||
| 22:01 | Demystifying PDF Parsing 05: Unifying Separate Tasks into a Small Model https://pub.towardsai.net/demystifying-pdf-parsing-05-unifying-separate-tasks-into-a-small-model-d3739db021f7 | |||
| 21:45 | Azure Text to Speech Pricing: Review, Benchmarks, and Usage https://medium.com/@getanakin/azure-text-to-speech-pricing-review-benchmarks-and-usage-01cc4ca5338d | |||
| 21:24 | How Knowledge Graphs Supercharge Large Language Models (LLMs) & Generative AI https://hammad-munir.medium.com/how-knowledge-graphs-supercharge-large-language-models-llms-generative-ai-bd71c23870bc | |||
| 21:01 | Unlocking the Power of BERT: How Machines are Learning to Understand Language https://medium.com/@anmol888236/unlocking-the-power-of-bert-how-machines-are-learning-to-understand-language-24937d25461e | |||
| 20:54 | How does OpenAI o1 work? https://davidmack.medium.com/how-does-openai-o1-work-1d4eb38b1e26 | |||
| 20:49 | Issue #191 — Terraform Plan with LLM, Ansible, Terraform on Azure Training, AWS Karpenter, EKS Pod… https://medium.com/@anton.babenko/issue-191-terraform-plan-with-llm-ansible-terraform-on-azure-training-aws-karpenter-eks-pod-cccd06d84b7b | |||
| 20:35 | Inference Update: Llama 3 Erato Release Window, New Text Gen Samplers, and Goodbye CFG https://novelai.medium.com/inference-update-llama-3-erato-release-window-new-text-gen-samplers-and-goodbye-cfg-6b9e247e0a63 | |||
| 20:26 | How to Use langchain_community.llms in Your Projects https://medium.com/@garysvenson09/how-to-use-langchain-community-llms-in-your-projects-2c0dfcbfe9fa | |||
| 19:19 | How to Find PostgreSQL Versions and Their Release Dates https://medium.com/@asakisakamoto02/how-to-find-postgresql-versions-and-their-release-dates-900722e8f0e2 | |||
| 19:03 | LLM Flooding — Is Building Advanced Language AI Models That Easy? https://medium.com/@srivastava.anubhav/llm-flooding-is-building-advanced-language-ai-models-that-easy-e13c3c397502 | |||
| 19:03 | Preference Learning Algorithms Fail to Learn Human Preference Rankings https://nyudatascience.medium.com/preference-learning-algorithms-fail-to-learn-human-preference-rankings-d1eba7d380fd | |||
| 18:55 | OpenAI’s O1: The Model That’s Redefining Generative AI — Here’s What You Need to Know https://medium.com/@khushibhoj/openais-o1-the-model-that-s-redefining-generative-ai-here-s-what-you-need-to-know-ea70753a5aa3 | |||
| 18:26 | Run Gemma 2 + llama.cpp GGUF Inference in Google Colab https://medium.com/@AleNunezArroyo/run-gemma-2-llama-cpp-gguf-inference-in-google-colab-18b9646d5870 | |||
| 18:24 | “But why are you doing that?” https://medium.com/@acu192/but-why-are-you-doing-that-94f06cfba3f7 | |||
| 18:22 | Outline-Driven RAG & Web Research Prototype https://cobusgreyling.medium.com/outline-driven-rag-web-research-prototype-fdf5ee23e605 | |||
| 18:20 | How Good is this LLM? https://medium.com/analytics-vidhya/how-good-is-this-llm-f314a6237be2 | |||
| 18:17 | How to Use Cursor Pagination for Efficient Data Navigation https://medium.com/@tayloroakley/how-to-use-cursor-pagination-for-efficient-data-navigation-1436940fc6a4 | |||
| 18:14 | Synesthesia 2.0: The Multimodal AI Revolution https://pub.towardsai.net/synesthesia-2-0-the-multimodal-ai-revolution-186309a0ea94 | |||
| 17:46 | Basic to Advanced RAG using LlamaIndex (Optimizing Performance with Rerankers)~4 https://medium.com/@imabhi1216/basic-to-advanced-rag-using-llamaindex-optimizing-performance-with-rerankers-4-7e1131ff08f2 | |||
| 17:45 | Azure Speech to Text Pricing: A Comprehensive Review and Guide https://medium.com/@getanakin/azure-speech-to-text-pricing-a-comprehensive-review-and-guide-023acdfcee4d | |||
| 17:41 | Important LLMs Papers for the Week from 09/09 to 15/09 https://medium.com/to-data-beyond/important-llms-papers-for-the-week-from-09-09-to-15-09-8e13257ff630 | |||
| 17:35 | Report: September 18, 2024 Meetup https://medium.com/@tspann/report-september-18-2024-meetup-43ad87625725 | |||
| 17:28 | The Best AI Model for You! https://medium.com/@todasco/the-best-ai-model-for-you-a54b279af989 | |||
| 17:28 | Running Llama 405B on an 8GB VRAM GPU: Advanced Techniques and Insights (Part 2) https://medium.com/@narenderbeniwal1234/running-llama-405b-on-an-8gb-vram-gpu-advanced-techniques-and-insights-part-2-846c552ab1d5 | |||
| 17:25 | Are LLMs Reasoning? https://medium.com/@jeffreyksaid/are-llms-reasoning-1d4898a124fc | |||
| 17:21 | Your RAG Demo Is a Waste of Time https://medium.com/the-business-of-ai/your-rag-demo-is-a-waste-of-time-737c75ad5ea0 | |||
| 16:46 | Breaking Down the Transformer: What I Learned from “Attention is All You Need” https://robertmill.medium.com/breaking-down-the-transformer-what-i-learned-from-attention-is-all-you-need-3e96be53ee3c | |||
| 16:27 | Why evaluation models are key for successful business RAG implementation https://medium.com/nuclia/why-evaluation-models-are-key-for-successful-business-rag-implementation-2d46cf6da6e3 | |||
| 16:25 | How to Install langchain-community from PyPI Easily https://medium.com/@garysvenson09/how-to-install-langchain-community-from-pypi-easily-b475c7985d9b | |||
| 16:23 | Contracts Management with watsonx Driving Information Analysis and Compliance Validation https://medium.com/@j.m.olivera08/contracts-management-with-watsonx-driving-information-analysis-and-compliance-validation-c8916db29855 | |||
| 16:02 | Unlocking the Power of Efficient Vector Search in RAG Applications https://pub.towardsai.net/unlocking-the-power-of-efficient-vector-search-in-rag-applications-c2e3a0c551d5 | |||
| 16:01 | Program a RAG LLM Chat App with LangChain + Streamlit + *o1, GTP-4o and Claude 3.5 https://medium.com/@enricdomingo/program-a-rag-llm-chat-app-with-langchain-streamlit-o1-gtp-4o-and-claude-3-5-529f0f164a5e | |||
| 15:56 | Hermes vs Mistral: A Detailed Comparison of Function Calling Capabilities in Large Language Models https://medium.com/@techwithkrooz/hermes-vs-mistral-a-detailed-comparison-of-function-calling-capabilities-in-large-language-models-a217f470fb02 | |||
| 15:45 | Dynamic Expert Feedback: KG RAG as a Two-Way Retrieval & Memory System vs One-Way Vector System https://medium.com/enterprise-rag/dynamic-expert-feedback-kg-rag-as-a-two-way-retrieval-memory-system-vs-one-way-vector-system-63b28c674336 | |||
| 15:31 | Show HN: Comparisons – Gemini-1-5-vs-ChatGPT-4o https://aimlapi.com/comparisons/gemini-1-5-vs-chatgpt-4o | |||
| 15:27 | Launching LangGraph Templates https://blog.langchain.dev/launching-langgraph-templates/ | |||
| 15:24 | From Data Collection to Fine-Tuning: The LLM Development Life Cycle Explained https://medium.com/coinmonks/from-data-collection-to-fine-tuning-the-llm-development-life-cycle-explained-5fa548f083da | |||
| 15:19 | How to Check Postgres Server ODBC Driver Compatibility https://medium.com/@asakisakamoto02/how-to-check-postgres-server-odbc-driver-compatibility-f109390423c5 | |||
| 15:14 | Nesa Project: Innovations in the Field of Artificial Intelligence https://medium.com/@djmaxfoton/nesa-project-innovations-in-the-field-of-artificial-intelligence-9fc9046768a3 | |||
| 15:07 | Why Enterprises Can’t Overlook LoRA https://medium.com/@vdpappu/loras-are-cool-288b5b04b37d | |||
| 15:03 | Coding with LLMs https://pub.towardsai.net/coding-with-llms-1a065b536dc4 | |||
| 14:56 | Amazon Bedrock: Unlocking the Power of Scalable AI and Machine Learning with AWS https://medium.com/@alexrodriguesj/amazon-bedrock-unlocking-the-power-of-scalable-ai-and-machine-learning-with-aws-4af6d3ac4aba | |||
| 14:48 | Um modelo LLM para ajudar no voto https://medium.com/@pedrowilliam_45809/um-modelo-llm-para-ajudar-no-voto-5764570c1506 | |||
| 14:32 | #41 OpenAI’s “innovation,” LLM Quantization, Feature Selection, and more! https://pub.towardsai.net/41-openais-innovation-llm-quantization-feature-selection-and-more-c56e4ca8c26d | |||
| 14:26 | Discover How ANWB Uses Advanced AI to Anonymize Your Data https://medium.com/@ANWB-data-driven/discover-how-anwb-uses-advanced-ai-to-anonymize-your-data-869387a333f5 | |||
| 14:17 | How to Make a GET Request for GitLab Commits in Python https://medium.com/@tayloroakley/how-to-make-a-get-request-for-gitlab-commits-in-python-85d94c520001 | |||
| 14:02 | Jina-Embeddings-v3 Released: A Multilingual Multi-Task Text Embedding Model Designed for a Variety of NLP Applications https://www.marktechpost.com/2024/09/19/jina-embeddings-v3-released-a-multilingual-multi-task-text-embedding-model-designed-for-a-variety-of-nlp-applications/ | |||
| 13:46 | Azure GPT-4o Pricing, Benchmarks, and Usage Insights https://medium.com/@getanakin/azure-gpt-4o-pricing-benchmarks-and-usage-insights-19b18bd0ee66 | |||
| 13:45 | Exploring Retrieval-Augmented Generation (RAG) in AI Development https://medium.com/@ayesh.csm/exploring-retrieval-augmented-generation-rag-in-ai-development-279cd0783767 | |||
| 13:42 | Deploying SuperNova-Lite on Inferentia2: the best 8B model for an hour! https://julsimon.medium.com/deploying-supernova-lite-on-inferentia2-the-best-8b-model-for-1-an-hour-68b3f08f9ab0 | |||
| 12:53 | Custom text generation function for text generation pipeline using Large Language Models. https://viraajkadam.medium.com/custom-text-generation-function-for-text-generation-pipeline-using-large-language-models-cb29eed276b6 | |||
| 12:47 | Making LLMs Reliable | Mahmoud Mabrouk https://medium.com/simplyblock/making-llms-reliable-mahmoud-mabrouk-e6b185d3218f | |||
| 12:43 | Making LLMs Reliable | Mahmoud Mabrouk https://medium.com/@rahilparekh98/making-llms-reliable-mahmoud-mabrouk-70712748eb1c | |||
| 12:31 | Extreme Quantization — How Shrinking Big AI Models is Changing Everything https://medium.com/womenintechnology/extreme-quantization-how-shrinking-big-ai-models-is-changing-everything-01b455af3748 | |||
| 12:25 | OpenAI Official Guide: 3-Step Process to Reduce Hallucinations and Increase LLM Answer Accuracy https://medium.com/@pamperherself/openai-official-guide-3-step-process-to-reduce-hallucinations-and-increase-llm-answer-accuracy-83737b43c0ff | |||
| 12:08 | Getting started with Amazon Bedrock https://medium.com/@mayank04111998/getting-started-with-amazon-bedrock-0265dffafc59 | |||
| 12:07 | Statistics For Machine Learning Types of Data https://medium.com/@rames1000/statistics-for-machine-learning-types-of-data-a5b115e18cad | |||
| 11:56 | Detailed Roadmap to become AI MLOps Expert From QA Engineer https://medium.com/@artistwhocode/detailed-roadmap-to-become-ai-mlops-expert-from-qa-engineer-874aa78af5e5 | |||
| 11:46 | Debunking the ‘Easy AI’ Myth” https://medium.com/@yoni2k/debunking-the-easy-ai-myth-2138685815e4 | |||
| 11:34 | AI as a Mirror to the Mind: Unraveling Psychological Patterns with Large Language Models https://medium.com/mr-plan-publication/ai-as-a-mirror-to-the-mind-unraveling-psychological-patterns-with-large-language-models-502e9b206eec | |||
| 11:31 | Unveiling Examples of Roles in Prompt Engineering for Developers https://medium.com/@marketing_novita.ai/unveiling-examples-of-roles-in-prompt-engineering-for-developers-f5ec1ec2d0ec | |||
| 11:27 | RAG https://medium.com/@shwaji043/rag-b6f8eec2ba9b | |||
| 11:25 | Best Online Learning Platform https://medium.com/@ahansaxena2004/best-online-learning-platform-73d333dc9a26 | |||
| 11:18 | How to Order Bar Charts in Apache Superset Effectively https://medium.com/@asakisakamoto02/how-to-order-bar-charts-in-apache-superset-effectively-831cd73da24f | |||
| 11:13 | Towards developing tests for Large Language Model-Enabled APIs https://pramodv1993.medium.com/towards-developing-tests-for-large-language-model-enabled-apis-946e04c9ed65 | |||
| 11:13 | ZML: Blazing Fast AI Inference Stack. https://jub0t.medium.com/zml-blazing-fast-ai-inference-stack-c97ad25a065b | |||
| 11:09 | Understanding LLM Parameters in Layman Terms https://medium.com/@SakshiScribbles/understanding-llm-parameters-in-layman-terms-34c07174305c | |||
| 11:08 | LLM Course | MUIT Noida https://medium.com/@premmuit/llm-course-muit-noida-c201646a596c | |||
| 10:29 | MidJourney vs Stable Diffusion https://medium.com/@researchgraph/midjourney-vs-stable-diffusion-1d46174937f2 | |||
| 10:16 | How to Use Unified APIs for Seamless Integration https://medium.com/@tayloroakley/how-to-use-unified-apis-for-seamless-integration-190da530c9a6 | |||
| 10:00 | Arcee.ai Llama-3.1-SuperNova-Lite is officially the 8-billion parameter model https://julsimon.medium.com/arcee-ai-llama-3-1-supernova-lite-is-officially-the-8-billion-parameter-model-53dc3e0ccfbc | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803