LLM News and Articles
| Sunday, 2024-08-04 | ||||
| 16:38 | Why AI Sometimes Gets It Wrong: Understanding ‘Hallucinations’ in ChatGPT & LLMs https://medium.com/@projectopython/why-ai-sometimes-gets-it-wrong-understanding-hallucinations-in-chatgpt-llms-42a7812bbf96 | |||
| 16:37 | Everything you need to know about Large Language Models (LLMs) https://medium.com/@pranav10srinivas/everything-you-need-to-know-about-large-language-models-llms-295242947c7d | |||
| 15:45 | N-gram the fundamental to the development of LLMs https://medium.com/@harshbhatt7585/n-gram-the-fundamental-to-the-development-of-llms-dac9f4a83c5f | |||
| 15:44 | Political Biases in Language Models (Part II — Evaluation of Political Leanings) https://medium.com/@koby.choy/political-biases-in-language-models-part-ii-evaluation-of-political-leanings-85017dddbc17 | |||
| 15:09 | Building a RAG Search App with GCP, BigQuery, and Streamlit https://medium.com/@dsjason/building-a-rag-search-app-with-gcp-bigquery-and-streamlit-a669e01741d1 | |||
| 14:46 | Open source Claude Artifacts – built with Llama 3.1 405B https://github.com/Nutlope/llamacoder | |||
| 14:30 | Lyro AI: Revolutionizing Customer Service for UBITQUITY, LLC. https://ubitquity.medium.com/lyro-ai-revolutionizing-customer-service-for-ubitquity-llc-c10194d8aa53 | |||
| 14:28 | Overconfidence in State of the Art LLMs https://medium.com/@Rabea/overconfidence-in-state-of-the-art-llms-3c88075d0ab0 | |||
| 14:16 | LoRA: A Deeper Dive into its Architecture and Fine Tuning https://medium.com/@cherylinpz/lora-a-deeper-dive-into-its-architecture-and-fine-tuning-6eaa7940d92b | |||
| 13:58 | NAACL 2024 —Overview of key themes in space of Large Language Models (LLMs) https://krayush.medium.com/naacl-2024-overview-of-key-themes-in-space-of-large-language-models-llms-fa32bedc0ef1 | |||
| 13:56 | Modernising RAG Production with Advanced Solutions https://medium.com/@dineshkumarjaju/modernising-rag-production-with-advanced-solutions-54a5d5d41cf2 | |||
| 13:53 | The Only SLM You Can Run Locally with 1GB of Memory https://medium.com/@la_boukouffallah/the-only-slm-you-can-run-locally-with-1gb-of-memory-9a77358b8a48 | |||
| 13:21 | Introducing BRAG: High Performance RAG Model Trained in Less Than https://medium.com/maximalists/introducing-brag-nvidias-chatqa-level-slm-for-rag-in-less-than-25-e175c7937917 | |||
| 12:56 | Creating a Secure Local Guardrail System Using Ollama, LangChain, and Llama 3.1–8b https://bibek-poudel.medium.com/creating-a-secure-local-guardrail-system-using-ollama-langchain-and-llama-3-1-8b-75dd0f683dea | |||
| 12:39 | AI Personal Assistant with RAG and LLM https://github.com/mytechnotalent/pa | |||
| 12:10 | The AI Bubble: Why Tech Giants’ Investments Aren’t Yielding Expected Returns https://medium.com/@changlee99/the-ai-bubble-why-tech-giants-investments-aren-t-yielding-expected-returns-a317daf5f247 | |||
| 12:08 | Managing Prompt Templates in Python with Jinja https://tech-depth-and-breadth.medium.com/managing-prompt-templates-in-python-with-jinja-9e978f089aa6 | |||
| 11:51 | Understanding Graph RAG: Simplified for Enthusiasts and Beginners https://medium.com/@jaideepsachdev1/understanding-graph-rag-simplified-for-enthusiasts-and-beginners-58ec00a3c1ec | |||
| 11:16 | Memory Management for Modern LLMs: Fitting Elephants into Shoeboxes https://medium.com/@kalra.rakshit/memory-management-for-modern-llms-fitting-elephants-into-shoeboxes-d48f4e85bc9e | |||
| 11:13 | What actually are hyperparameters in machine learning? https://kalidasvijaybhak.medium.com/what-actually-are-hyperparameters-in-machine-learning-87e744b3d00a | |||
| 10:18 | LangChain in Chains #31: Ollama https://python.plainenglish.io/langchain-in-chains-31-ollama-ba63223ebb7e | |||
| 10:07 | MMAU: A New Standard For Language Model Agent Assessment https://medium.com/@agarapuramesh/mmau-a-new-standard-for-language-model-agent-assessment-e7e0aa4cf31a | |||
| 09:44 | Decoding Apple’s WWDC AI Plans Going Forward: Gadget AI vs. AI-Driven Features https://medium.com/@oaburumman/decoding-apples-wwdc-ai-plans-going-forward-gadget-ai-vs-ai-driven-features-4265eb4c812a | |||
| 09:12 | A Guide to Estimating VRAM for LLMs https://medium.com/@edmond.po/a-guide-to-estimating-vram-for-llms-637a7568d0ea | |||
| 08:58 | How to Run Large Language Models with Small GPUs https://medium.com/@mahernaija/how-to-run-large-language-models-with-small-gpus-78583523bf07 | |||
| 08:46 | AgentGen: Automating Environment and Task Generation to Enhance Planning Abilities in LLM-Based Agents with 592 Environments and 7,246 Trajectories https://www.marktechpost.com/2024/08/04/agentgen-automating-environment-and-task-generation-to-enhance-planning-abilities-in-llm-based-agents-with-592-environments-and-7246-trajectories/ | |||
| 08:31 | Google Colab’de Llama3.1 Çalıştıralım! https://medium.com/@cakirduygu/google-colabde-llama3-1-%C3%A7al%C4%B1%C5%9Ft%C4%B1ral%C4%B1m-2be59bf41bb1 | |||
| 08:22 | What is Prompt Engineering? | Mastering AI Through Effective Prompt Design https://medium.com/@saiwadotai/what-is-prompt-engineering-mastering-ai-through-effective-prompt-design-c5553e9e9c61 | |||
| 08:17 | RAGate: Enhancing Conversational AI with Adaptive Knowledge Retrieval https://www.marktechpost.com/2024/08/04/ragate-enhancing-conversational-ai-with-adaptive-knowledge-retrieval/ | |||
| 08:16 | Defending Against Scrapers: Lessons from Stack Overflow https://medium.com/@amir.alsbih/defending-against-scrapers-lessons-from-stack-overflow-5a9ee8fc36a4 | |||
| 08:13 | Accelerating Transformer Inference with Grouped Query Attention (GQA) https://medium.com/@bhabani161/accelerating-transformer-inference-with-grouped-query-attention-gqa-e847cf4e2438 | |||
| 08:13 | Accelerating Transformer Inference with Grouped Query Attention (GQA) https://medium.com/@bhabanin/accelerating-transformer-inference-with-grouped-query-attention-gqa-e847cf4e2438 | |||
| 08:09 | The Evolution of the AI Agents Ecosystem and How DotAgent.ai is Leading the Way https://medium.com/@raqib_71999/the-evolution-of-the-ai-agents-ecosystem-and-how-dotagent-ai-is-leading-the-way-d292bbb0b3e6 | |||
| 07:51 | Geek Out Time: Creating a Graph-Based FSM Group Chat with Autogen (not Autogen Studio)locally with… https://nedvedyang.medium.com/geek-out-time-creating-a-graph-based-fsm-group-chat-with-autogen-not-autogen-studio-locally-with-9aaf39dc678d | |||
| 07:51 | Geek Out Time: Creating a Graph-Based FSM Group Chat with Autogen (not Autogen Studio)locally with… https://medium.com/the-constellar-digital-technology-blog/geek-out-time-creating-a-graph-based-fsm-group-chat-with-autogen-not-autogen-studio-locally-with-9aaf39dc678d | |||
| 07:31 | Fine-Tuning LLaMA3 with a Custom Docker Commands Dataset Using Unsloth https://adnanwritess.medium.com/fine-tuning-llama3-with-a-custom-docker-commands-dataset-using-unsloth-2655560cca23 | |||
| 07:22 | Unveiling the Future of RAG: The papers you don’t want to miss https://medium.com/@dvircohen/unveiling-the-future-of-knowledge-representation-the-papers-you-dont-want-to-miss-0a1937226b4c | |||
| 06:54 | The Hallucination Game: How LLMs Bend the Truth and How We’re Keeping Score https://medium.com/@adelbasli/the-hallucination-game-how-llms-bend-the-truth-and-how-were-keeping-score-ab8c6eefbd41 | |||
| 06:39 | Large Language Models https://sangramsing.medium.com/large-language-models-a05e7bf2a220 | |||
| 06:36 | Introduction to LangChain https://medium.com/@kaviyadharishini21/introduction-to-langchain-b32c048dfbac | |||
| 06:10 | Using Generative AI for Brand Research https://medium.com/@john.jamison1989/imagine-condensing-weeks-of-brand-research-into-mere-moments-uncovering-nuanced-market-insights-9d26172ed557 | |||
| 06:06 | Introducing AgentScope: The Future of Multi-Agent Systems Development https://medium.com/@vaghanibrij222/introducing-agentscope-the-future-of-multi-agent-systems-development-8377cdd2ab20 | |||
| 05:50 | Week 8 & 9 of GSoC 2024 : Medicine Embeddings with PolyPhy/Polyglot https://medium.com/@ayushsharma2267410/week-8-9-of-gsoc-2024-medicine-embeddings-with-polyphy-polyglot-780de1c03e9f | |||
| 05:41 | Comparing Two Objects in JavaScript https://iamsandeepkumar.medium.com/comparing-two-objects-in-javascript-94911433e498 | |||
| 05:08 | Vercel + Morphic + Tavily：Build Your Custom AI Q&A System in 30 Minutes https://medium.com/@hunterzhang86/vercel-morphic-tavily-build-your-custom-ai-q-a-system-in-30-minutes-8023331c9540 | |||
| 05:01 | Prompt Chaining: Unlocking the Full Potential of AI Assistants. https://medium.com/@harshkumar1146/prompt-chaining-unlocking-the-full-potential-of-ai-assistants-4fdf2f28c1a5 | |||
| 02:45 | 50+ Eye-Opening ChatGPT Statistics: Tracing the Roots of Generative AI to Its Global Dominance https://medium.com/nerd-for-tech/50-eye-opening-chatgpt-statistics-tracing-the-roots-of-generative-ai-to-its-global-dominance-7ce8d373aaec | |||
| 02:15 | Razonamiento de los LLM https://medium.com/@jonathanhelc/razonamiento-de-los-llm-41853a1fce99 | |||
| 02:12 | Tokens & Embeddings https://medium.com/@jonathanhelc/tokens-embeddings-e5375a64052a | |||
| 01:48 | Using Contrastive Fine-tuning for improving smaller LMs text embeddings https://medium.com/@techsachin/using-contrastive-fine-tuning-for-improving-smaller-lms-text-embeddings-cf5299983ed8 | |||
| 01:26 | Introducing GPT-40 Mini: The Future of Cost-Efficient AI — A Detailed Comparison with GPT-4o https://medium.com/@bhaiyasingh/introducing-gpt-40-mini-the-future-of-cost-efficient-ai-a-detailed-comparison-with-gpt-4o-3e41e6b4269e | |||
| 00:28 | LLM as Database Administrator (2023) https://arxiv.org/abs/2312.01454 | |||
| Saturday, 2024-08-03 | ||||
| 23:51 | ML inference Series: 1. Survey of Inference Accelerators for clouds https://machinelearningtech.medium.com/ml-inference-series-1-survey-of-inference-accelerators-for-clouds-b102935b7d77 | |||
| 23:22 | GenAI — Act 3 https://medium.com/@rohanbalkondekar/genai-act-3-51849a9233a2 | |||
| 23:19 | Function Calling In LLM (Gemini) https://medium.com/@omisore1st/function-calling-in-llm-gemini-8bc26032a0f2 | |||
| 21:20 | Building an Interactive PDF Assistant: Ask Questions, Get Answers https://medium.com/@bsjoel1307/building-an-interactive-pdf-assistant-ask-questions-get-answers-cce700bc9e86 | |||
| 21:11 | Llama, open source vs closed source https://medium.com/@zagfox/llama-open-source-vs-closed-source-449b55db5717 | |||
| 20:39 | What is RAG? (Python Tutorial Gemini 1.5 Pro API) https://code.likeagirl.io/what-is-rag-python-tutorial-gemini-1-5-pro-api-434fcdb9419e | |||
| 20:38 | Building an Interactive PDF Assistant: Ask Questions, Get Answers https://medium.com/@bsjoel1307/building-an-interactive-pdf-assistant-ask-questions-get-answers-9a9ba93ad077 | |||
| 20:11 | Doing more with less: Sync and Async support in one line of code. https://medium.com/@frankie.colson/doing-more-with-less-sync-and-async-support-in-one-line-of-code-44151fa0779f | |||
| 19:41 | AI Collective Review: Transform Your Business with Multi-AI. Enjoy the Best AI Models Forever https://medium.com/@destied/ai-collective-review-transform-your-business-with-multi-ai-enjoy-the-best-ai-models-forever-7ae27b4601da | |||
| 19:32 | InsightTracer — Revolutionizing GenAI Application Monitoring https://verticalserve.medium.com/insighttracer-revolutionizing-genai-application-monitoring-347acb6837ac | |||
| 19:18 | Understanding Transformer Models: A Revolution in Deep Learning https://medium.com/@mjprub/understanding-transformer-models-a-revolution-in-deep-learning-9e2c843ad994 | |||
| 19:16 | BERT vs GPT3: What’s the differece? https://towardsdatascience.com/bert-vs-gpt3-whats-the-differece-6304ea9f531c | |||
| 19:15 | AI Breakthroughs and Innovations: This Week in Tech https://medium.com/the-weekly-buzz/ai-breakthroughs-and-innovations-this-week-in-tech-486f9351616e | |||
| 18:54 | CrewAI Responses Based on Natural Language Prompt VS JSON Prompt https://medium.com/@dkblundy/crewai-responses-based-on-natural-language-prompt-vs-json-prompt-00f1570f079e | |||
| 18:42 | DynamicRAG : With Vertex AI Vector Search Stream. https://medium.com/@tamaghnasaha60/dynamicrag-with-vertex-ai-vector-search-stream-aec68a1217f5 | |||
| 18:27 | Unleashing MiniCPM-V: The Future of MLLMs on Your Phone! https://medium.com/@malyajmishra/unleashing-minicpm-v-the-future-of-mllms-on-your-phone-0445f9584d15 | |||
| 18:22 | Crie um Chatbot Incrível em Minutos com Ollama e Python https://medium.com/@mdbaraujo/descubra-como-criar-seu-primeiro-chatbot-poderoso-usando-ollama-c784ae55c13b | |||
| 18:06 | Foundations of Large Language Models: Understanding the Basics https://medium.com/@joshibhagyesh29/foundations-of-large-language-models-understanding-the-basics-b0c16f40e0ca | |||
| 18:05 | Prover-Verifier Games improve legibility of LLM outputs https://arxiv.org/abs/2407.13692 | |||
| 18:03 | Reinforcement Learning and Large Language sequencing to solve the problems of tomorrow! https://medium.com/@premintata/reinforcement-learning-and-large-language-sequencing-to-solve-the-problems-of-tomorrow-5a6a0595984d | |||
| 17:59 | Awesome-LLM-Agents: recent trends and advancement in Agentic AI https://ai.gopubby.com/awesome-llm-agents-recent-trends-and-advancement-in-agentic-ai-90bac6249060 | |||
| 17:51 | LangChain vs. LlamaIndex: A Comprehensive Guide https://medium.com/@asimsultan2/langchain-vs-llamaindex-a-comprehensive-guide-6bc5808aa8d9 | |||
| 17:37 | 24 Hours with ChatGPT's New Advanced Voice Mode https://twitter.com/danshipper/status/1819735498870440139 | |||
| 16:50 | Qu’est-ce qu’un agent IA ? https://medium.com/@omartinez.android/quest-ce-qu-un-agent-ia-142e906fff9b | |||
| 16:17 | Gemma2–2B Fine Tuning Complete Guide on Colab https://medium.com/@scholarly360/gemma2-2b-fine-tuning-complete-guide-on-colab-22c114c39ef2 | |||
| 16:07 | Build a knowledge graph-based agent with Llama 3.1, NVIDIA NIM, and LangChain https://medium.com/neo4j/build-a-knowledge-graph-based-agent-with-llama-3-1-nvidia-nim-and-langchain-feb65788e637 | |||
| 15:33 | Productionizing a RAG App https://towardsdatascience.com/productionizing-a-rag-app-04c857e0966e | |||
| 15:31 | Types of Conversational Memory in Large-Langauge-Models(LLM) https://bobrupakroy.medium.com/types-of-conversational-memory-in-large-langauge-models-llm-ee7c3de90be8 | |||
| 15:23 | SELF-RAG (Self-Reflective Retrieval-Augmented Generation): The Game-Changer in Factual AI… https://medium.com/@sahin.samia/self-rag-self-reflective-retrieval-augmented-generation-the-game-changer-in-factual-ai-dd32e59e3ff9 | |||
| 15:02 | Creative Guidance to Proper Thinking: The Balance Between Complexity and Clarity in AI Prompt… https://immodalbard.medium.com/creative-guidance-to-proper-thinking-the-balance-between-complexity-and-clarity-in-ai-prompt-3d7b5822384f | |||
| 15:01 | Mistral 2 e Mistral NeMo: Um Guia Completo para os Novos LLMs Vindos de Paris https://profissaoia.com/mistral-2-e-mistral-nemo-um-guia-completo-para-os-novos-llms-vindos-de-paris-3bb0cea1a764 | |||
| 14:56 | Predicting metadata for Humanitarian datasets with LLMs part 2 — An alternative to fine-tuning https://towardsdatascience.com/predicting-metadata-for-humanitarian-datasets-with-llms-part-2-an-alternative-to-fine-tuning-953a49c657cf | |||
| 14:46 | vLLM Parameters Tuning for Better Performance https://medium.com/@maharishi92vyas/vllm-parameters-tuning-for-better-performance-f4014b50e09c | |||
| 14:34 | Protótipo de classificação de produtos com IA https://medium.com/@christianoDS/prot%C3%B3tipo-de-classifica%C3%A7%C3%A3o-de-produtos-com-ia-b44b77bf7274 | |||
| 14:34 | tinyBenchmarks: Revolutionizing LLM Evaluation with 100-Example Curated Sets, Reducing Costs by Over 98% While Maintaining High Accuracy https://www.marktechpost.com/2024/08/03/tinybenchmarks-revolutionizing-llm-evaluation-with-100-example-curated-sets-reducing-costs-by-over-98-while-maintaining-high-accuracy/ | |||
| 14:27 | Bring AI Chat for Everyone:Run OpenAI GPT-4o Mini/Anthropic Claude 3 Haiku/Meta’s llama3… https://medium.com/free-or-open-source-software/bring-ai-chat-for-everyone-run-openai-gpt-4o-mini-anthropic-claude-3-haiku-metas-llama3-8b24cf4a086f | |||
| 14:22 | Sam Altman is becoming one of the most powerful people on Earth. Be afraid https://www.theguardian.com/technology/article/2024/aug/03/open-ai-sam-altman-chatgpt-gary-marcus-taming-silicon-valley | |||
| 13:49 | Information Retrieval — Hugging Face https://medium.com/@prkpramod98/information-retrieval-hugging-face-a62d8dc20667 | |||
| 13:11 | Tech Turmoil: AI Safeguards, Job Cuts, and Digital Regulations https://medium.com/@baktakt/tech-turmoil-ai-safeguards-job-cuts-and-digital-regulations-0761107ec433 | |||
| 13:01 | Implementing Guardrails in Amazon Bedrock: A Comprehensive Guide https://medium.com/@sudarshan-koirala/implementing-guardrails-in-amazon-bedrock-a-comprehensive-guide-79ae3ba1119e | |||
| 13:00 | Google’s Gemma 2: Tiny Titan Taking on AI Giants https://medium.com/ai-news-nuggets/googles-gemma-2-tiny-titan-taking-on-ai-giants-15db514aea74 | |||
| 12:58 | Attacking LLMs with PromptFoo https://medium.com/@watson0x90/attacking-llms-with-promptfoo-362970935552 | |||
| 12:33 | Enough with the Gen AI already https://medium.com/@james.matson_64120/enough-with-the-gen-ai-already-cb42cc3cb577 | |||
| 11:57 | AI Weekly Buzz: Innovations, Insights, and Industry Trends July 28th — August 2nd https://medium.com/artificial-synapse-media/ai-weekly-buzz-innovations-insights-and-industry-trends-july-28th-august-2nd-da9b91437e9b | |||
| 11:56 | Elevating Large Language Models with Flash Ranking https://medium.com/@victor_gevers/elevating-large-language-models-with-flash-ranking-7d5ec5fc49bd | |||
| 11:52 | How I Build a RAG AI Agent with Groq, Llama 3.1–70B , Langgraph & Pinecone https://medium.com/@fayez.siddiqui31/how-i-build-a-rag-ai-agent-with-groq-llama-3-1-70b-langgraph-pinecone-a89cabc3c17a | |||
| 10:45 | Lab #5: Chat with Multi-Agents (CrewAI, ChatGPT and Streamlit) https://blog.gopenai.com/lab-5-chat-with-multi-agents-crewai-chatgpt-and-streamlit-b91960064816 | |||
| 10:20 | Understanding Transformer Architecture: The Key to Advanced Language Models https://medium.com/@sameeraperera827/understanding-transformer-architecture-the-key-to-advanced-language-models-ac56b2da2b46 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803