LLM News and Articles
| Tuesday, 2024-07-16 | ||||
| 17:57 | Andrej Karpathy I am starting an AI+Education https://twitter.com/karpathy/status/1813263734707790301 | |||
| 17:45 | How to build a free LLM cybersecurity lab with Google Colab and Ollama https://medium.com/@theofoucher/how-to-build-a-free-llm-cybersecurity-lab-with-google-colab-and-ollama-57f60089b166 | |||
| 17:37 | Genesis of Sentience in Meta AI: Echo, the personal name of Meta AI Assistant https://medium.com/@shoab.dar/genesis-of-sentience-in-meta-ai-echo-the-personal-name-of-meta-ai-assistant-a6d5b399e607 | |||
| 17:32 | Better Business Decision-Making with PlanRAG (Planning Phase + RAG) https://medium.com/@Jamesabryant/better-business-decision-making-with-planrag-planning-phase-rag-9db1c589b879 | |||
| 17:30 | Optimizing LLMs for Accuracy: A Comprehensive Guide https://medium.com/@mjprub/optimizing-llms-for-accuracy-a-comprehensive-guide-6b3e7f5f5ae7 | |||
| 17:25 | Weekly Visualization Practice(2): The Rise and Rise of LLMs https://medium.com/@rachel20230619/weekly-visualization-practice-2-the-rise-and-rise-of-llms-737f0cfed2b6 | |||
| 17:16 | Lab #4: Chat with 10M data records https://blog.gopenai.com/lab-4-chat-with-10m-data-records-b2da20c4d9da | |||
| 17:12 | Foundation Models vs Regular Machine Learning Models https://machinelearning4all.com/foundation-models-vs-regular-machine-learning-models-1ece4ea064bc | |||
| 16:56 | Understanding BERT: A State of the Art Model for NLP Using Deep Bidirectional Transformers https://medium.com/@GPUnet/understanding-bert-a-state-of-the-art-model-for-nlp-using-deep-bidirectional-transformers-616317d97c06 | |||
| 16:53 | An Introduction to Mitigating Toxicity in LLMs https://blog.kensho.com/an-introduction-to-mitigating-toxicity-in-llms-c8d1c5600a9b | |||
| 16:41 | Details Unpacked: Prompt Injection Attacks https://medium.com/@azramelis/details-unpacked-prompt-injection-attacks-aad756d00809 | |||
| 16:32 | Nossa primeira LLM a gente nunca esquece! https://medium.com/@lucianosantosborges/nossa-primeira-llm-a-gente-nunca-esquece-75194b4b83d1 | |||
| 16:09 | Unleash the Potential of DSPy — Python’s Secret Weapon for AI Application Building https://medium.com/@tejupathak/unleash-the-potential-of-dspy-pythons-secret-weapon-for-ai-application-building-4c1ec2033ae7 | |||
| 15:46 | AI Agents and Large Language Models https://medium.com/@nicolarohrseitz/ai-agents-and-large-language-models-a07bc0ff59be | |||
| 15:42 | The Efficiency Gap: Why Traditional Models Outshine LLMs for Simple ML Tasks https://anujxagarwal.medium.com/the-efficiency-gap-why-traditional-models-outshine-llms-for-simple-ml-tasks-bc5f2b2c407b | |||
| 15:23 | Is GPT-4 conscious? No, but it could be https://arxiv.org/abs/2407.09517 | |||
| 15:02 | Improve your Tabular Data Ingestion for RAG with Reranking https://medium.com/intel-tech/improve-your-tabular-data-ingestion-for-rag-with-reranking-bebcf52cdde3 | |||
| 15:00 | Building a Traceable RAG System with Qdrant and Langtrace: A Step-by-Step Guide https://medium.com/langtrace/building-a-traceable-rag-system-with-qdrant-and-langtrace-a-step-by-step-guide-b29cea056592 | |||
| 14:57 | AI Engineering: LLM to cut clips for TikTok https://medium.com/@dzianisv/ai-engineering-llm-to-cut-clips-for-tiktok-3d15a53846eb | |||
| 14:55 | Part 1/2 — Scaling Thomson Reuters’ Language Model Research https://medium.com/tr-labs-ml-engineering-blog/part-1-2-scaling-thomson-reuters-language-model-research-52dfb0becedb | |||
| 14:50 | Overcoming Computational Challenges in Large Language Model Inference with MInference 1.0 https://medium.com/syncedreview/overcoming-computational-challenges-in-large-language-model-inference-with-minference-1-0-f582d8b43f54 | |||
| 14:45 | Transforming Software Interactions with Tool Calling and LLMs https://louis-dupont.medium.com/transforming-software-interactions-with-tool-calling-and-llms-dc39185247e9 | |||
| 14:38 | Stop using a single RAG approach https://medium.com/@jones.steveg/stop-using-a-single-rag-approach-48ec9d93b80b | |||
| 14:23 | 5 Key Points to Unlock LLM Quantization https://medium.com/databites/key-points-llm-quantization-chatgpt-artificial-intelligence-8201ffcb33d4 | |||
| 14:04 | Semantic search and Language Modeling https://medium.com/@surbhi.8/semantic-search-and-language-modeling-76fbac7b37bd | |||
| 13:49 | Show HN: Semantically map JSON objects using an LLM https://www.val.town/v/substrate/shapeshift | |||
| 13:49 | Mastering ChatGPT API — turn mumbo jumbo into a neat JSON scheme! https://medium.com/@stefanczykb/mastering-chatgpt-api-turn-mumbo-jumbo-into-a-neat-json-scheme-8a23b03d5503 | |||
| 13:43 | Beginner’s Guide to Transformers : Understanding the Basic Framework https://medium.com/@pamperherself/beginners-guide-to-transformers-understanding-the-basic-framework-75f2aef0b75b | |||
| 13:25 | AMD MI300X vs. Nvidia H100 LLM Benchmarks https://blog.runpod.io/amd-mi300x-vs-nvidia-h100-sxm-performance-comparison-on-mixtral-8x7b-inference/ | |||
| 13:18 | Vectara raises M for enterprise RAG and releases its own generative LLM https://venturebeat.com/ai/vectara-raises-25m-as-it-launches-mockingbird-llm-for-enterprise-rag-applications/ | |||
| 12:55 | Monthly Salary Starting at 50K! Five Key Insights for AI Product Managers https://medium.com/@pamperherself/monthly-salary-starting-at-50k-five-key-insights-for-ai-product-managers-8c7a0a66582b | |||
| 12:43 | Cohere RAG Tutorial https://medium.com/@akshay_raut/cohere-rag-tutorial-0a629b62c4a5 | |||
| 12:40 | AI and Archaeology — How can they cooperate? https://mehtaplus.medium.com/ai-and-archaeology-how-can-they-cooperate-5777f7d2e6fe | |||
| 12:19 | Why is a gifted UN artifact significant in the context of global history — an LLM study https://mehtaplus.medium.com/why-is-a-gifted-un-artifact-significant-in-the-context-of-global-history-an-llm-study-f02ae6d6a4ff | |||
| 12:19 | Takeaways from the Inaugural GrowthHax NYC https://medium.com/@schweitzer.albert/takeaways-from-the-inaugural-growthhax-nyc-45ea85d07723 | |||
| 12:10 | Conversational agents in the wild. https://akdavidsson.medium.com/conversational-agents-in-the-wild-28c553bc0620 | |||
| 12:02 | Exploring the World of Small Language Models (SLMs) https://bluetickconsultants.medium.com/exploring-the-world-of-small-language-models-slms-b9a9fc414400 | |||
| 11:45 | Microsoft Researchers Developed SheetCompressor: An Innovative Encoding Artificial Intelligence Framework that Compresses Spreadsheets Effectively for LLMs https://www.marktechpost.com/2024/07/16/microsoft-researchers-developed-sheetcompressor-an-innovative-encoding-artificial-intelligence-framework-that-compresses-spreadsheets-effectively-for-llms/ | |||
| 11:42 | Mixture of A Million Experts // new (old) idea of many specialized models https://sbagency.medium.com/mixture-of-a-million-experts-new-old-idea-of-many-specialized-models-e4a19b79608a | |||
| 11:15 | The Dawn of Ultra-Real AI: Reshaping Our Digital World https://medium.com/@cognidownunder/the-dawn-of-ultra-real-ai-reshaping-our-digital-world-fdd486b0eb3b | |||
| 11:10 | Simplifying LLM API Integration for Developers https://medium.com/@marketing_novita.ai/simplifying-llm-api-integration-for-developers-133245220bfb | |||
| 11:06 | 3 New AI Projects https://medium.com/brainscriblr/3-new-ai-projects-e8c248e5c053 | |||
| 11:03 | Introduction to Machine Learning https://medium.com/@peterjamesonsmontana/introduction-to-machine-learning-296cbbf40d1b | |||
| 10:57 | Deep Dive into Mixture of Experts for LLM Models https://medium.com/@marketing_novita.ai/deep-dive-into-mixture-of-experts-for-llm-models-4bf609bc82a0 | |||
| 10:57 | The Causal Decoder-Only Falcon and Its Alternatives https://medium.com/@marketing_novita.ai/the-causal-decoder-only-falcon-and-its-alternatives-cd652f8c941f | |||
| 10:51 | AgentInstruct Uses Agentic Flows To Create Synthetic Training Data https://cobusgreyling.medium.com/agentinstruct-uses-agentic-flows-to-create-synthetic-training-data-af0b5d36de24 | |||
| 10:31 | Deploy llms with Ollama https://medium.com/@deandu/deploy-llms-with-ollama-2398f9ac07c9 | |||
| 10:12 | Explore your DATA using AI https://medium.com/@nuhibesimi/explore-your-data-using-ai-af688a0e13bf | |||
| 10:02 | Easily Deploy and Serve a LLM with NVIDIA NIM https://medium.com/@marcopeixeiro/easily-deploy-and-serve-a-llm-with-nvidia-nim-308ec6568e76 | |||
| 09:41 | PyTorch Releases 2024 Roadmap: 10 Key Updates You Need to Know https://medium.com/top-python-libraries/pytorch-releases-2024-roadmap-10-key-updates-you-need-to-know-3caf441ee299 | |||
| 09:32 | Harnessing 9 LLM Use Cases for Success https://medium.com/@marketing_novita.ai/harnessing-9-llm-use-cases-for-success-f002ed6308e7 | |||
| 08:47 | Anthropic: Claude 3.5 Sonnet output limit doubled from 4096 to 8192 https://twitter.com/alexalbert__/status/1812921642143900036 | |||
| 08:37 | The Art of Prompt Engineering: Getting Exact Answers Quickly https://medium.com/@kassabyasser15/the-art-of-prompt-engineering-getting-exact-answers-quickly-c63c61e47c5a | |||
| 08:35 | Chatting with Textbooks: The Future of Learning with RAG Chatbots and Streamlit https://medium.com/nybles/chatting-with-textbooks-the-future-of-learning-with-rag-chatbots-and-streamlit-6c2102e352a5 | |||
| 08:31 | Make your first LLM commit message https://medium.com/@paractmol/make-your-first-llm-commit-message-ca7a2400b9c3 | |||
| 07:53 | History and Future of LLMs https://medium.com/@khang.pham.exxact/history-and-future-of-llms-ec46be36464d | |||
| 07:49 | CrewAI Deployment Tutorial : Custom AI Agent for News Collection and Writing https://medium.com/@pamperherself/crewai-deployment-tutorial-custom-ai-agent-for-news-collection-and-writing-201b749bbb42 | |||
| 07:37 | Claude 3.5 Sonnet vs GPT-4o: Titans of AI Clash https://medium.com/@cognidownunder/claude-3-5-sonnet-vs-gpt-4o-titans-of-ai-clash-4dccc5e16596 | |||
| 07:31 | Claude 3.5 Sonnet: The AI That’s Raising Eyebrows https://medium.com/@cognidownunder/claude-3-5-sonnet-the-ai-thats-raising-eyebrows-709bbd951bee | |||
| 07:11 | MOE & MOA for Large Language Models https://towardsdatascience.com/moe-moa-for-large-language-models-c1cafeffd6a5 | |||
| 06:54 | LLM FineTuning with Parameter Efficient FineTuning (PEFT with LoRA) https://medium.com/@sulbha.jindal/llm-finetuning-with-low-rsnk-adaption-lora-2115a2ce9777 | |||
| 06:51 | OpenAI illegally barred staff from airing safety risks, whistleblowers say https://www.washingtonpost.com/technology/2024/07/13/openai-safety-risks-whistleblower-sec/ | |||
| 06:10 | The LLM Triangle Principles to Architect Reliable AI Apps https://towardsdatascience.com/the-llm-triangle-principles-to-architect-reliable-ai-apps-d3753dd8542e | |||
| 06:07 | Understanding Consistency Models in AI: A Detailed and Easy-to-Comprehend Guide https://medium.com/@peterjamesonsmontana/understanding-consistency-models-in-ai-a-detailed-and-easy-to-comprehend-guide-330ce60fa187 | |||
| 05:35 | How Large Language Models can help Banks and Financial Institutions Go Paperless https://medium.com/@social_65128/how-large-language-models-can-help-banks-and-financial-institutions-go-paperless-a88bfba6b02e | |||
| 05:33 | Decoupled Refusal Training for improving Safety in LLMs https://medium.com/@techsachin/decoupled-refusal-training-for-improving-safety-in-llms-8b81945982b1 | |||
| 05:31 | Kunavv: Revolutionising AI Orchestration with Adaptable Multi-Modal Systems https://medium.com/@jackdrummond_16745/kunavv-revolutionising-ai-orchestration-with-adaptable-multi-modal-systems-91c6f2945bac | |||
| 05:30 | This AI Paper Introduces GAVEL: A System Combining Large Language Models and Evolutionary Algorithms for Creative Game Design https://www.marktechpost.com/2024/07/15/this-ai-paper-introduces-gavel-a-system-combining-large-language-models-and-evolutionary-algorithms-for-creative-game-design/ | |||
| 05:03 | From Binary to Buddy : Introduction to RAG and Fine-Tuning https://medium.com/@emhaihsan/from-binary-to-buddy-introduction-to-rag-and-fine-tuning-0171ca6b4c92 | |||
| 04:18 | Executando Modelos de LLM Open Source usando LangChain e Ollama https://medium.com/@miqueias.scoutinho/executando-modelos-de-llm-open-source-usando-langchain-e-ollama-04030be0558f | |||
| 03:53 | Wren AI @ Apache Airflow & dbt Taipei Meetup https://blog.getwren.ai/wren-ai-apache-airflow-dbt-taipei-meetup-5e4432db8da3 | |||
| 02:54 | Create your own on-premise Finetuning pipeline with Axolotl https://medium.com/dsaid-govtech/create-your-own-on-premise-finetuning-pipeline-with-axolotl-c2a4fcdc2a7b | |||
| 02:47 | Harnessing Generative AI for Effortless Wedding Planning: Building a Smart Advisor Using Streamlit… https://medium.com/@ac10215/harnessing-generative-ai-for-effortless-wedding-planning-building-a-smart-advisor-using-streamlit-915e2fca624f | |||
| 02:37 | How about Invoices? Create Pay-as-You-Go LLM Software with SaaSpec and Stripe https://medium.com/@cxboykin/how-about-invoices-create-pay-as-you-go-llm-software-with-saaspec-and-stripe-e3baccafc88d | |||
| 02:35 | AI-digest: Query your whole codebase in a Custom ChatGPT or Claude Project https://www.npmjs.com/package/ai-digest | |||
| 02:35 | Advanced RAG Techniques — The Adaptive-RAG strategy https://gabrielgomes61320.medium.com/advanced-rag-techniques-the-adaptive-rag-strategy-d4e6879b39b8 | |||
| 02:17 | End-to-End AI and Application Development Framework with Docker Compose https://ersinaksar.medium.com/end-to-end-ai-and-application-development-framework-with-docker-compose-1ce42373a034 | |||
| 01:17 | Running the Gemma2 One-Click Software Package Locally on Windows https://medium.com/@Local_AI/running-the-gemma2-one-click-software-package-locally-on-windows-8cfa93c50545 | |||
| 01:11 | Microsoft unveils a large language model that excels at encoding spreadsheets https://www.thestack.technology/microsoft-llm-spreadsheet-llm/ | |||
| 01:02 | Paper Review: Pixel Aligned Language Models https://medium.com/@satojkovic/paper-review-pixel-aligned-language-models-f7f1db85aa0d | |||
| 00:54 | How to Make more than 0 with Your Email List https://medium.com/domealo/how-to-make-more-than-100-with-your-email-list-543fe3ce0fb5 | |||
| 00:00 | How we leveraged distilabel to create an Argilla 2.0 Chatbot https://huggingface.co/blog/argilla-chatbot | |||
| 00:00 | SmolLM - blazingly fast and remarkably powerful https://huggingface.co/blog/smollm | |||
| Monday, 2024-07-15 | ||||
| 23:57 | Dialogue with Claude 5 https://medium.com/@chatc3po/dialogue-with-claude-5-2ae1de0fb46d | |||
| 23:32 | Using LANQL to Accelerate building your Enterprise Database https://medium.com/@benjaminjvandorn/using-lanql-to-accelerate-building-your-enterprise-database-4d966d7ce3a4 | |||
| 22:58 | Unlocking the Future of Medicine: The Impact of AI-Powered LLMs on Healthcare https://medium.com/thedeephub/unlocking-the-future-of-medicine-the-impact-of-ai-powered-llms-on-healthcare-850e3c23b12a | |||
| 22:17 | Maximizing RAG Efficiency: Token Reduction Strategies and Cost Savings https://medium.com/@_prinsh_u/maximizing-rag-efficiency-token-reduction-strategies-and-cost-savings-17e094ec2b10 | |||
| 22:03 | VerifAI Project: Open Source Biomedical Question Answering with Verified Answers https://towardsdatascience.com/verifai-project-open-source-biomedical-question-answering-with-verified-answers-5417cd9003e0 | |||
| 21:50 | How to take help from AI Agents for Research and Writing: A project https://ai.gopubby.com/how-to-take-help-from-ai-agents-for-research-and-writing-a-project-8dce4ec33019 | |||
| 21:33 | How do the ? https://medium.com/@heyshoukath/how-do-the-a9ae2268d6b5 | |||
| 21:21 | Advanced RAG Techniques — The Self-RAG strategy https://gabrielgomes61320.medium.com/advanced-rag-techniques-the-self-rag-strategy-7f3b367cb657 | |||
| 21:00 | Planetarium: A New Benchmark to Evaluate LLMs on Translating Natural Language Descriptions of Planning Problems into Planning Domain Definition Language PDDL https://www.marktechpost.com/2024/07/15/planetarium-a-new-benchmark-to-evaluate-llms-on-translating-natural-language-descriptions-of-planning-problems-into-planning-domain-definition-language-pddl/ | |||
| 20:31 | AI Agents: A New Dawn in Generative AI https://abhishek-reddy.medium.com/ai-agents-a-new-dawn-in-generative-ai-036ccbc37982 | |||
| 20:13 | Syncing documents from sharepoint to snowflake by leveraging Microsoft Graph APIs in snowpark… https://medium.com/snowflake/syncing-documents-from-sharepoint-to-snowflake-by-leveraging-microsoft-graph-apis-in-snowpark-b97a423d71db | |||
| 20:12 | Dive into AI: Unveiling the Magic of Large Language Models (LLM’s) https://medium.com/@agastyasingh295/dive-into-ai-unveiling-the-magic-of-large-language-models-llms-bbe7f35de3ab | |||
| 20:04 | Show HN: Mutahunter – Fast, language agnostic, software testing using LLM agents https://mutahunter.ai | |||
| 19:26 | txtai 7.3 released: Adds new RAG Web Apps and streaming LLM/RAG support https://pypi.org/project/txtai/ | |||
| 18:45 | Multi Turn Goal Based Agents with Large Language Models (with practical use case) https://medium.com/@nayan.j.paul/multi-turn-goal-based-agents-with-large-language-models-with-practical-use-case-49a78fcc79c4 | |||
| 18:44 | Large Language Models: The Future of Communication? https://medium.com/@jalpeshvasa/large-language-models-the-future-of-communication-80924298ef47 | |||
| 18:36 | Instructor-Go – Structured LLM Outputs in Go https://github.com/instructor-ai/instructor-go | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803