LLM News and Articles
Friday, 2024-08-23 | ||||
17:01 | Attention is all you need: How Transformer Architecture in NLP started. https://pub.towardsai.net/attention-is-all-you-need-how-transformer-architecture-in-nlp-started-16382dc2158c | |||
16:15 | Notes from the Edge: “Chain of Thoughtlessness?” https://gcmori.medium.com/notes-from-the-edge-chain-of-thoughtlessness-ece38ebdaf8f | |||
16:11 | How machine learning drives innovation https://medium.com/@hivemind_tech/how-machine-learning-drives-innovation-fd4d943358a6 | |||
16:06 | Unleashing the Power of Fully Automated Open-Ended Scientific Discovery: The “AI Scientist” https://medium.com/@chandana.sree145/unleashing-the-power-of-fully-automated-open-ended-scientific-discovery-the-ai-scientist-1ae2515b1cee | |||
15:53 | RAG Book Recommendation https://medium.com/@ju.rabikumarsingh/rag-book-recommendation-c59491782542 | |||
15:32 | Top 10 Best Large Language Model Development Companies of 2024 https://medium.com/coinmonks/top-10-best-large-language-model-development-companies-of-2024-8958609e5a39 | |||
15:29 | Top 12 Large Language Models (LLMs) for August 2024 https://medium.com/coinmonks/top-12-large-language-models-llms-for-august-2024-2f909f689e0a | |||
15:26 | A Lightweight Embeddings Solution for LangChain with Google AI https://medium.com/@markbochner1/a-lightweight-embeddings-solution-for-langchain-with-google-ai-e1522aa776e1 | |||
15:26 | How To Use LLMs To Create Automated Trading Strategies For NT8 https://celanbryant.medium.com/how-to-use-llms-to-create-automated-trading-strategies-for-nt8-e2ee4d5387cf | |||
15:05 | Confidentiality concerns over Public GenAI platforms https://lean-link.medium.com/confidentiality-concerns-over-public-genai-platforms-1011f78ac043 | |||
14:46 | Chat with WSJ articles https://medium.com/@timo.au.laine/chat-with-wsj-articles-d119f14fa5fc | |||
14:40 | Exploring RAG: Essential Steps to Implementing AI Agents and Deep Learning Strategies https://medium.com/@pratikabnave97/exploring-rag-essential-steps-to-implementing-ai-agents-and-deep-learning-strategies-f41ceda143c4 | |||
14:39 | Components of a Neural Network: A Detailed Overview with Use Cases https://medium.com/@punya8147_26846/components-of-a-neural-network-a-detailed-overview-with-use-cases-aeff2e3e576f | |||
14:37 | Why Blindly Applying Prompt Engineering Techniques to RAG Systems a bad idea https://aarontay.medium.com/why-blindly-applying-prompt-engineering-techniques-to-rag-systems-a-bad-idea-9ca7f893f6f3 | |||
14:34 | Generating consistent images of characters using AI https://ai.gopubby.com/generating-consistent-images-of-characters-using-ai-130ac50761e2 | |||
14:04 | Figuring Out How Much Memory Your Giant Language Model Needs https://medium.com/@sumit2sk/figuring-out-how-much-memory-your-giant-language-model-needs-2acab515265d | |||
12:50 | Generative AI vs. Large Language Models (LLMs) Complete Guide https://richellejohn89.medium.com/generative-ai-vs-large-language-models-llms-complete-guide-fedf5a24af03 | |||
12:49 | The Buzz about ChatGPT — To infinity and beyond! (Part 2) https://medium.com/@benoitgarbinato/the-buzz-about-chatgpt-to-infinity-and-beyond-part-2-bdb8f889f4e1 | |||
12:47 | LLMs for Chatbots and Conversational AI: Building Engaging User Experiences https://blog.chatbotslife.com/llms-for-chatbots-and-conversational-ai-building-engaging-user-experiences-5b656835fc8b | |||
12:39 | Unraveling the Nature of Emergent Abilities in Large Language Models: The Role of In-Context Learning and Model Memory https://www.marktechpost.com/2024/08/23/unraveling-the-nature-of-emergent-abilities-in-large-language-models-the-role-of-in-context-learning-and-model-memory/ | |||
12:36 | The Buzz about ChatGPT — To infinity and beyond! (Part 1) https://medium.com/@benoitgarbinato/the-buzz-about-chatgpt-to-infinity-and-beyond-part-1-88862a775364 | |||
12:31 | - https://medium.com/@shreyakhandelwalofficial/-39f7e512e221 | |||
12:19 | Unlocking the Potential of Indic Languages: The Rise of Indic LLMs https://medium.com/@SatyaSruthiPakalapati/unlocking-the-potential-of-indic-languages-the-rise-of-indic-llms-1426463c01e4 | |||
11:47 | How does agent use tools? CAMEL can tell you! https://medium.com/camel-al/how-does-agent-use-tools-camel-can-tell-you-c8ff51acd09a | |||
11:33 | Battle of AI Models: Claude vs ChatGPT https://levelup.gitconnected.com/battle-of-ai-models-claude-vs-chatgpt-5084e3044aca | |||
11:23 | TF-IDF In NLP https://medium.com/@ayanawan33/tf-idf-in-nlp-270ddfcb8fee | |||
11:22 | Difference Between LLM and LLMChain in LangChain https://medium.com/@narenderbeniwal1234/difference-between-llm-and-llmchain-in-langchain-6a7e51b7dec1 | |||
11:06 | Deep Dive into LLM-evaluators aka “LLM-as-a-Judge” https://medium.com/@yugank.aman/deep-dive-into-llm-evaluators-aka-llm-as-a-judge-c34f497edca9 | |||
11:00 | LangChain Explained the Easiest Way https://medium.com/@arknoah3/langchain-explained-the-easiest-way-0cc14721a132 | |||
10:23 | The Evolution of Understanding: How LLMs Develop Their Own Reality https://medium.com/@gavandiroshan/the-evolution-of-understanding-how-llms-develop-their-own-reality-84bd399baa55 | |||
09:31 | Build Drawing Prompt Generator: Spark Your Imagination https://medium.com/@marketing_novita.ai/build-drawing-prompt-generator-spark-your-imagination-443db1a706a2 | |||
08:51 | Show HN: I made a GPT based Dungeon Crawler game https://github.com/oxy-k/gpt-dungeon-crawler | |||
08:35 | Walmart’s AI Revolution: Transforming Retail with 850 Million Product Data Points https://medium.com/@gavandiroshan/walmarts-ai-revolution-transforming-retail-with-850-million-product-data-points-6eec81d54a4c | |||
08:02 | Top AI Projects in Python — August 2024 https://augmentedstartups.medium.com/top-ai-projects-in-python-august-2024-64a5b23ab638 | |||
07:52 | The AI Bubble: Is It the Next Internet Bubble? https://medium.com/@valuelize/the-ai-bubble-is-it-the-next-internet-bubble-e1fe6fcedb4f | |||
07:31 | Introducing Projects: Revolutionizing Document-Based Conversations https://medium.com/@modelfusion/introducing-projects-revolutionizing-document-based-conversations-2dbe504c6c96 | |||
06:54 | Customizing LLM Evaluation: Using LangChain to Assess Responses Against Custom Criteria https://medium.com/@rudraadityanaveen/customizing-llm-evaluation-using-langchain-to-assess-responses-against-custom-criteria-7cdb8468f512 | |||
06:43 | Vector Databases vs. Knowledge Graphs: A Comparative Approach to Boosting LLM Accuracy https://medium.com/@orengr4/vector-databases-vs-knowledge-graphs-a-comparative-approach-to-boosting-llm-accuracy-3ebab9393df4 | |||
06:31 | Understanding the Architecture Behind DO-Solution: A Dive into RAG and LLM Integration https://medium.com/@alicejeanchoi/understanding-the-architecture-behind-do-solution-a-dive-into-rag-and-llm-integration-d65a72d14a97 | |||
05:37 | Learn how to use your own llm locally with ollama https://medium.com/@srinipotnuru/learn-how-to-use-your-own-llm-locally-with-ollama-f181e6ba07d3 | |||
04:53 | Building a Smart Chatbot Using Qdrant Cloud and LangChain for Customer Support Tickets https://ai.gopubby.com/building-a-smart-chatbot-using-qdrant-cloud-and-langchain-for-customer-support-tickets-504a3e17ac83 | |||
04:51 | Create your Avatar Using Diffusers and Dreambooth on Azure Machine Learning https://medium.com/@manoranjan.rajguru/create-your-avatar-using-diffusers-and-dreambooth-on-azure-machine-learning-9366224c4586 | |||
04:25 | Why Large Language Models Struggle with Simple Math https://medium.com/@mohammednabi2007/why-large-language-models-struggle-with-simple-math-fbfdbcea47e3 | |||
03:16 | Claude 3.5 Sonnet vs GPT-4o vs Google Gemini Pro API: Pricing Comparison https://towards-agi.medium.com/claude-3-5-sonnet-vs-gpt-4o-vs-google-gemini-pro-api-pricing-comparison-2bb415d65b8c | |||
03:16 | GPT Tokenizer with Andrej Karpathy: Part 1 https://medium.com/@kdwa2404/gpt-tokenizer-with-andrej-karpathy-part-1-bffd6d6173ff | |||
03:01 | AI Code Generation with Visual Copilot https://ai.gopubby.com/ai-code-generation-with-visual-copilot-b6a53fd3bc2c | |||
02:54 | AI Persuasion: How Machines Shape Our Decisions Without Us Knowing https://generativeai.pub/ai-persuasion-how-machines-shape-our-decisions-without-us-knowing-8a6bd648a4a2 | |||
02:52 | Where to Use Llama 3.1 405B Base Model via API https://towards-agi.medium.com/where-to-use-llama-3-1-405b-base-model-via-api-3c93556e84a2 | |||
02:43 | Expanding Gemini API’s Capabilities: A Practical Solution for Web Content Summarization https://medium.com/google-cloud/expanding-gemini-apis-capabilities-a-practical-solution-for-web-content-summarization-5617474b2ad1 | |||
02:30 | dora, a robot development framework that integrates multiple models:bringing robot programming to… https://medium.com/@gosimfoundation/dora-a-robot-development-framework-that-integrates-multiple-models-bringing-robot-programming-to-4494eec8f053 | |||
02:12 | Jamba 1.5: the New RAG King is Here? https://towards-agi.medium.com/jamba-1-5-the-new-rag-king-is-here-ee2f0ce21202 | |||
00:53 | The Rapid Rise of AI Sales Development: Sustainable Growth or Short-Lived Trend? https://reiserx.medium.com/the-rapid-rise-of-ai-sales-development-sustainable-growth-or-short-lived-trend-a092793a259a | |||
00:10 | Snowflake’s Arctic-TILT: Matching the Power of Models 1,000x Larger in Document Understanding https://medium.com/syncedreview/snowflakes-arctic-tilt-matching-the-power-of-models-1-000x-larger-in-document-understanding-9f944cd0e286 | |||
Thursday, 2024-08-22 | ||||
23:44 | The Four Levels of Language AI https://margaliot.medium.com/the-four-levels-of-language-ai-01bf4fe15219 | |||
23:00 | Types of AI Agents https://medium.com/mindsdb/types-of-ai-agents-9f683235d636 | |||
22:39 | Pretrained language models for Arabic language https://medium.com/@khenchouchmohamed32/pretrained-language-models-for-arabic-language-46212c72bbfe | |||
22:19 | Internship at AWS as an Applied Scientist https://medium.com/@shahriarsadat71_26111/internship-at-aws-as-an-applied-scientist-1105204726a2 | |||
21:43 | Let CodeQwen1.5–7B-Chat generate your GraphQL types https://medium.com/@mariusmuntean/let-codeqwen1-5-7b-chat-generate-your-graphql-types-e8044e5f00ed | |||
21:33 | Demystifying TVM: A Deep Dive into Machine Learning Model Optimization on Mobile Hardware https://medium.com/@_jeremy_/demystifying-tvm-a-deep-dive-into-machine-learning-model-optimization-on-mobile-hardware-9a9ea64596ee | |||
21:18 | Code walkthrough: Bootstrapping demonstrations for LLM game recommendations in DSPy https://chip-hennig.medium.com/code-walkthrough-bootstrapping-demonstrations-for-llm-game-recommendations-in-dspy-82ef5682fac7 | |||
21:05 | Ideogram V2 released https://ai.gopubby.com/ideogram-v2-released-625cf4ed4316 | |||
20:30 | Participant Checklist: Streamlining Virtual Standups with a Custom MacOS Application https://medium.com/@shinfinity/participant-checklist-streamlining-virtual-standups-with-a-custom-macos-application-efbf280f9470 | |||
20:28 | Why you should let LLM’s write your Commit Messages. https://medium.com/@raiyashpramod16/why-you-should-let-llms-write-your-commit-messages-b231906e8ed5 | |||
20:24 | Exploring Multi-Agent Systems as a Pathway to Artificial General Intelligence https://medium.com/@zouheir.tricha/exploring-multi-agent-systems-as-a-pathway-to-artificial-general-intelligence-3b7a33db0166 | |||
20:22 | Introducing the Swagger Query Engine using LlamaIndex https://satishkumarandey.medium.com/introducing-the-swagger-query-engine-using-llamaindex-44fa8bbda139 | |||
20:17 | Snowflake Text-to-SQL magic https://medium.com/snowflake/snowflake-text-to-sql-magic-dcae2ebc5a82 | |||
20:16 | Graph RAG — A conceptual introduction https://towardsdatascience.com/graph-rag-a-conceptual-introduction-41cd0d431375 | |||
19:53 | Unlocking Efficiency: A Deep Dive into Quantization Strategies for Large Language Models https://adarshsahu27.medium.com/unlocking-efficiency-a-deep-dive-into-quantization-strategies-for-large-language-models-95ed0fc40544 | |||
19:11 | Anthropic AI Claude’s Memory Function Explained https://medium.com/@tomskiecke/anthropic-ai-claudes-memory-function-explained-4c8ed5b36949 | |||
18:58 | Unlock the Future of AI with OpenAI’s Fine-Tuning for GPT-4o https://medium.com/@Jamesabryant/unlock-the-future-of-ai-with-openais-fine-tuning-for-gpt-4o-e29cb1ef9f21 | |||
18:50 | Speculative Retrieval Augmented Generation (Speculative RAG): A Novel Framework Enhancing Accuracy and Efficiency in Knowledge-intensive Query Processing with LLMs https://www.marktechpost.com/2024/08/22/speculative-retrieval-augmented-generation-speculative-rag-a-novel-framework-enhancing-accuracy-and-efficiency-in-knowledge-intensive-query-processing-with-llms/ | |||
18:49 | Large Language Models (LLMs) in the Context of Multi-Agent Systems (MAS) https://medium.com/@gulernilay088/large-language-models-llms-in-the-context-of-multi-agent-systems-mas-472cfd330faf | |||
18:40 | Part 1 : ReACT AI Agents: A Guide to Smarter AI Through Reasoning and Action. https://medium.com/@gauritr01/part-1-react-ai-agents-a-guide-to-smarter-ai-through-reasoning-and-action-d5841db39530 | |||
18:18 | What is Proof of Training(PoT)? Can it helps to store LLM model on the blockchain? https://medium.com/@gopichandwriting/what-is-proof-of-training-pot-can-it-helps-to-store-llm-model-on-the-blockchain-4371f0ffc0bc | |||
18:04 | Code as a Catalyst: Improving LLM Capabilities Across Diverse Tasks https://www.marktechpost.com/2024/08/22/code-as-a-catalyst-improving-llm-capabilities-across-diverse-tasks/ | |||
17:51 | Understanding the Differences Between ChatGPT and LangGraph: A Simple Guide https://medium.com/@kts.ramamoorthy07/understanding-the-differences-between-chatgpt-and-langgraph-a-simple-guide-40a897c40c8d | |||
17:44 | Are Large Language Models Politically Biased? A Deep Dive into the Latest Research https://medium.com/@samaneh_shn/are-large-language-models-politically-biased-a-deep-dive-into-the-latest-research-dc889ca31b9e | |||
17:42 | How to integrate AI into webpages with ONE line of JavaScript https://medium.com/@thomas_82964/how-to-integrate-ai-into-webpages-with-one-line-of-javascript-1e6c6d3f6819 | |||
17:41 | LLMs 101: Intro to Large Language Models https://medium.com/@zelkovavc/llms-101-intro-to-large-language-models-391e453c2050 | |||
17:29 | Extending context length with Hugging Face’s transformers https://medium.com/@leannetan/extending-context-length-with-hugging-faces-transformers-6b04db05b39a | |||
17:22 | Improving RAG using Self Rag + Gemma 2 https://medium.com/@sridevi.gogusetty/improving-rag-using-self-rag-gemma-2-fd984e58162b | |||
17:05 | The NLP Handbook: Rules for Solving Business Problems Effectively https://kshitijkutumbe.medium.com/the-nlp-handbook-essential-rules-for-solving-business-problems-effectively-c1b13c7036c3 | |||
16:27 | Flows Are So Back https://cobusgreyling.medium.com/flows-are-so-back-5a4d0ee95661 | |||
16:04 | Fine-Tuning OpenAI's Small Language Model https://cobusgreyling.medium.com/fine-tuning-openai-gpt-4o-mini-da064d464946 | |||
15:51 | Rethinking innovation funding in the age of AI https://medium.com/caribou-digital/rethinking-innovation-funding-in-the-age-of-ai-ef51a81a57db | |||
15:39 | AI-Assisted Arduino Programming https://medium.com/@edmond.po/ai-assisted-arduino-programming-dcc256f34846 | |||
15:23 | Offline AI: Build Ollama on Android Mobiles/Waydroid from Source with Termux https://medium.com/free-or-open-source-android-apps/offline-ai-build-ollama-on-android-mobiles-waydroid-from-source-with-termux-a882db71e09d | |||
15:00 | Quantization Demystified: GGUF, GPTQ, AWQ https://python.plainenglish.io/quantization-demystified-gguf-gptq-awq-94796bd0ae27 | |||
14:45 | LLMs: A Code-Changing Revolution in Machine Learning and Deep Learning https://medium.com/@sreedharnali/llms-a-code-changing-revolution-in-machine-learning-and-deep-learning-47295f2510b6 | |||
14:38 | AI Uncensored: a fine tune of Llama 405B – no more PC nonsense https://www.aiuncensored.info/uncensor1 | |||
14:31 | NO, Prompt Engineering Is Not Dying, It Was Never Alive https://medium.com/@ignacioperezzv/no-prompt-engineering-is-not-dying-it-was-never-alive-052651753fa3 | |||
14:12 | Unveiling the Power of RAG: Beyond Traditional Large Language Models https://medium.com/@sreedharnali/unveiling-the-power-of-rag-beyond-traditional-large-language-models-9827b312e921 | |||
13:45 | 130 Machine Learning Words that Everyone Must Know! https://blog.stackademic.com/130-machine-learning-words-that-everyone-must-know-f3170f07b05d | |||
13:41 | Creating a Local Search Engine with TF-IDF and Cosine Similarity: A Hands-On Guide. https://medium.com/@jayantnehra18/creating-a-local-search-engine-with-tf-idf-and-cosine-similarity-a-hands-on-guide-21af2fba6416 | |||
13:31 | How AI’s Western Bias is Homogenizing Written Content on Social Media and Digital Platforms https://medium.com/@shushghandilyan/how-ais-western-bias-is-homogenizing-written-content-on-social-media-and-digital-platforms-24f1156cddf7 | |||
13:24 | Community Governance Opportunities in the ML Pipeline https://jending.medium.com/community-governance-opportunities-in-the-ml-pipeline-45466ca7c947 | |||
13:08 | LongWriter: enables LLMs to generate coherent, high-quality texts of more than 10,000 or even… https://braintitan.medium.com/longwriter-enables-llms-to-generate-coherent-high-quality-texts-of-more-than-10-000-or-even-c72f087ad9ff | |||
12:41 | What is RAG | Retrieval-Augmented Generation? https://emaddehnavi.medium.com/what-is-rag-retrieval-augmented-generation-b5dad32764f9 | |||
12:26 | How Does a Neural Network Work? https://medium.com/@punya8147_26846/how-does-a-neural-network-work-116634edd8fe | |||
11:24 | Basic RAG is not so basic for Enterprise Data https://medium.com/@greger_ottosson/basic-rag-is-not-so-basic-for-enterprise-data-3ce2aa9a8c04 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803