LLM News and Articles
| Sunday, 2024-05-12 | ||||
| 08:47 | Build a Usefulness-Based Chatbot https://medium.com/@waywardverities/build-a-usefulness-based-chatbot-6aeca393454c | |||
| 08:45 | Unveiling the Giants: An Introduction to Large Language Models https://medium.com/@gagcoders/unveiling-the-giants-an-introduction-to-large-language-models-57af0f5f7692 | |||
| 08:33 | Prompt Engineering https://medium.com/@ankittaxak5713/prompt-engineering-e89caa958afc | |||
| 08:10 | So You Want to Get Into This Whole LLM Thing? https://medium.com/@kuwarkapur/so-you-want-to-get-into-this-whole-llm-thing-bc3c324af02e | |||
| 08:09 | Using AI to Analyse file and Database. https://medium.com/@tripathinaman.1014/using-ai-to-analyse-file-and-database-e9b05b7f8b64 | |||
| 07:52 | LLMOps Introduction https://aliissa99.medium.com/llmops-introduction-11c8f47755aa | |||
| 07:46 | How much LLM training data is there from all sources in Trillions of Tokens? https://www.educatingsilicon.com/2024/05/09/how-much-llm-training-data-is-there-in-the-limit/ | |||
| 07:33 | Building a Retrieval Augmented Generation (RAG) Application with LangChain and Cohere https://medium.com/@lalit.k.pal/building-a-retrieval-augmented-generation-rag-application-with-langchain-and-cohere-13ad54c9a361 | |||
| 07:30 | This AI Paper by the University of Michigan Introduces MIDGARD: Advancing AI Reasoning with Minimum Description Length https://www.marktechpost.com/2024/05/12/this-ai-paper-by-the-university-of-michigan-introduces-midgard-advancing-ai-reasoning-with-minimum-description-length/ | |||
| 07:05 | What You Say Is What You Get https://medium.com/@0xc22b/what-you-say-is-what-you-get-ad88f898061e | |||
| 06:20 | Tsinghua University Researchers Propose ADELIE: Enhancing Information Extraction with Aligned Large Language Models Around Human-Centric Tasks https://www.marktechpost.com/2024/05/11/tsinghua-university-researchers-propose-adelie-enhancing-information-extraction-with-aligned-large-language-models-around-human-centric-tasks/ | |||
| 06:06 | Mistral AI is looking to raise 0M — B in valuation https://medium.com/@saisuhasiniramalingam/mistral-ai-is-looking-to-raise-600m-6b-in-valuation-f8d94c588d17 | |||
| 05:51 | LangChain: Document Loading https://medium.com/@rutambhagat/langchain-document-loading-b252e781dc49 | |||
| 05:43 | UC Berkeley Researchers Introduce Learnable Latent Codes as Bridges (LCB): A Novel AI Approach that Combines the Abstract Reasoning Capabilities of Large Language Models with Low-Level Action Policies https://www.marktechpost.com/2024/05/11/uc-berkeley-researchers-introduce-learnable-latent-codes-as-bridges-lcb-a-novel-ai-approach-that-combines-the-abstract-reasoning-capabilities-of-large-language-models-with-low-level-action-policies/ | |||
| 05:29 | Building Intuition on Log Probabilities in Language Models https://medium.com/ai-assimilating-intelligence/building-intuition-on-log-probabilities-in-language-models-8fd00f34c03c | |||
| 05:26 | LLMs: Large Language Models https://medium.com/@ankittaxak5713/llms-large-language-models-d976a26ecaed | |||
| 04:35 | Evaluate Your RAG System Using NDCG https://medium.com/@Stan_DS/evaluate-your-rag-system-using-ndcg-4d45fac1bf0d | |||
| 04:31 | Maximizing Efficiency: Parameter Sharing https://medium.com/@tharunsivamani/maximizing-efficiency-parameter-sharing-0c285c8602c7 | |||
| 04:21 | OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs https://medium.com/@techsachin/openfactcheck-a-unified-framework-for-factuality-evaluation-of-llms-d88f2946ca94 | |||
| 04:14 | What are large language models? https://randomresearchai.medium.com/what-are-large-language-models-7dd032afbbba | |||
| 03:42 | An Introduction to Typicality and Fan Effects in LLMs Research https://medium.com/@thaopham03/an-introduction-to-typicality-and-fan-effects-in-llms-research-d960520fc177 | |||
| 03:19 | Let’s RAG some financial reports with LLMware and ChromaDB https://blog.gopenai.com/lets-rag-some-financial-reports-with-llmware-and-chromadb-c02f9712c867 | |||
| 03:09 | Aloe: A Family of Fine-tuned Open Healthcare LLMs that Achieves State-of-the-Art Results through Model Merging and Prompting Strategies https://www.marktechpost.com/2024/05/11/aloe-a-family-of-fine-tuned-open-healthcare-llms-that-achieves-state-of-the-art-results-through-model-merging-and-prompting-strategies/ | |||
| 01:52 | Show NH: "data-to-paper" - autonomous stepwise LLM-driven research https://github.com/Technion-Kishony-lab/data-to-paper | |||
| 00:51 | Llama 3 in 30 Minutes or Less: A Quick and Easy Local Setup https://medium.com/@jayasb/llama-3-in-30-minutes-or-less-a-quick-and-easy-local-setup-efb2647e441b | |||
| 00:12 | DeepSeek-V2: An Efficient and Economical Mixture-of-Experts LLM https://ai.gopubby.com/deepseek-v2-an-efficient-and-economical-mixture-of-experts-llm-ed9690ad1552 | |||
| 00:11 | A Discussion on Chain-of-Verification https://medium.com/@ashnicsto/a-discussion-on-chain-of-verification-b5495e4c0d2b | |||
| 00:10 | ChuXin: A Fully Open-Sourced Language Model with a Size of 1.6 Billion Parameters https://www.marktechpost.com/2024/05/11/chuxin-a-fully-open-sourced-language-model-with-a-size-of-1-6-billion-parameters/ | |||
| Saturday, 2024-05-11 | ||||
| 23:58 | Sci-fi writer JG Ballard's computer poems predicted ChatGPT https://www.bbc.com/future/article/20240510-how-sci-fi-writer-jg-ballards-computer-poems-predicted-chatgpt | |||
| 21:55 | Why AI Language Models Are Making Old Chatbot Building Methods Obsolete (And Maybe Costing Some… https://kiranbeethoju.medium.com/why-ai-language-models-are-making-old-chatbot-building-methods-obsolete-and-maybe-costing-some-acba88ee7b4f | |||
| 21:54 | Análisando Empresas do Mercado Financeiro com RAG: Uma Abordagem Baseada em IA Generativa e Dados… https://franckepeixoto.medium.com/an%C3%A1lisando-empresas-do-mercado-financeiro-com-rag-uma-abordagem-baseada-em-ia-generativa-e-dados-6ea973c9234c | |||
| 21:53 | The Power and Peril of Large Language Models: Challenges and Considerations https://vtiya.medium.com/the-power-and-peril-of-large-language-models-challenges-and-considerations-5694e2ccee9b | |||
| 21:12 | Citation Needed – Wikimedia Foundation's Experimental LLM/RAG Chrome Extension https://chromewebstore.google.com/detail/wikipedia-citation-needed/kecnjhdipdihkibljeicopdcoinghmhj | |||
| 21:08 | Advanced RAG 11: Query Classification and Refinement https://ai.gopubby.com/advanced-rag-11-query-classification-and-refinement-2aec79f4140b | |||
| 21:02 | GSoC’24 with C2SI Org https://medium.com/@hardikdlf/gsoc24-with-c2si-org-43c0f03edfbd | |||
| 20:50 | How to Deploy and Experiment with Ollama Models on Your Local Machine (Windows) https://medium.com/@dpn.majumder/how-to-deploy-and-experiment-with-ollama-models-on-your-local-machine-windows-34c967a7ab0e | |||
| 20:38 | Chat with local Llama3 Model via Ollama in KNIME Analytics Platform — Also extract Logs into… https://medium.com/@mlxl/chat-with-local-llama3-model-via-ollama-in-knime-analytics-platform-also-extract-logs-into-aca61e4a690a | |||
| 20:29 | ChatQA-1.5: A Breakthrough in Conversational AI https://medium.com/@omkamal/chatqa-1-5-a-breakthrough-in-conversational-ai-43bef5ff62db | |||
| 20:07 | ChatGPT: Kurumsal Dönüşüm içinYeni Bir Kapı https://medium.com/@seliskacmaz1/chatgpt-kurumsal-d%C3%B6n%C3%BC%C5%9F%C3%BCm-i%C3%A7inyeni-bir-kap%C4%B1-7a63bf3d5238 | |||
| 19:47 | Unveiling the Transformer: A Paradigm Shift in Natural Language Processing(PART-3): https://medium.com/@mauryaanoop3/unveiling-the-transformer-a-paradigm-shift-in-natural-language-processing-part-3-c74fd60fca95 | |||
| 19:00 | How to Start Using ChatGPT and Become Fluent in Prompting https://medium.com/@villejohannespajala/how-to-start-using-chatgpt-and-become-fluent-in-prompting-2061d7ce23ac | |||
| 18:54 | Leveraging Linguistic Expertise in NLP: A Deep Dive into RELIES and Its Impact on Large Language Models https://www.marktechpost.com/2024/05/11/leveraging-linguistic-expertise-in-nlp-a-deep-dive-into-relies-and-its-impact-on-large-language-models/ | |||
| 18:29 | Unbridling the Power of LangChain framework with LCEL https://medium.com/@itsmybestview/unbridling-the-power-of-langchain-framework-with-lcel-9e5f7bf8af74 | |||
| 18:27 | Redash chat-bot add-on: LLM based chatbot for Advanced Data Analytics, Visualisation, and Automated… https://medium.com/@koomistoussaintamoussouvi/redash-chat-bot-add-on-llm-based-chatbot-for-advanced-data-analytics-visualisation-and-automated-fe689f1c9b7f | |||
| 18:24 | Vamos falar sobre o Llama e Meta AI? https://medium.com/@mdbaraujo/vamos-falar-sobre-o-llama-72ff33bec136 | |||
| 18:17 | [ML] compiling llama.cpp with conda installed cuda env https://id2thomas.medium.com/ml-compiling-llama-cpp-with-conda-installed-cuda-env-6653a824b120 | |||
| 17:49 | Is Google Scared? OpenAI Prepares to Launch AI-Powered Search Engine and Champion Transparency! https://medium.com/@k.pranav_22/is-google-scared-openai-prepares-to-launch-ai-powered-search-engine-and-champion-transparency-f5afd35b6e21 | |||
| 17:06 | xLSTM better than Transformer models? https://medium.com/magic-ai/xlstm-better-than-transformer-models-fea3fb933340 | |||
| 16:38 | Build your first AI assistant using RAG https://medium.com/@dhirajkumarsahu.999/build-your-first-ai-assistant-using-rag-5f7b7ec0f39a | |||
| 16:31 | Chapter 3: Now You Know: Can it Think Like Me? https://medium.com/@vikrambj/chapter-3-now-you-know-can-it-think-like-me-01f0eb134d86 | |||
| 15:49 | GraphRag and more https://medium.com/@emrahtanyildizi/graphrag-and-more-5d1fa032dd1e | |||
| 15:14 | Red Teaming of LLM Application using Giskard https://medium.com/@jainashish.079/red-teaming-of-llm-application-using-giskard-32132bc6d4f1 | |||
| 14:53 | 75Hard Generative AI & LLM Challenge -Day 22 to 28 https://medium.com/@simranjeetsingh1497/75hard-generative-ai-llm-challenge-day-22-to-28-c2238fee3cb0 | |||
| 14:50 | Finetuning an LLM-Based Spam Classifier with LoRA from Scratch https://github.com/rasbt/LLMs-from-scratch/blob/main/appendix-E/01_main-chapter-code/appendix-E.ipynb | |||
| 14:50 | Words in Space: An Astronaut’s Guide to Embeddings in Language Models https://medium.com/@finomeno/words-in-space-an-astronauts-guide-to-embeddings-in-language-models-41726796ffb1 | |||
| 14:37 | Japan team uses Fugaku supercomputer to develop language model for AI https://www.japantimes.co.jp/news/2024/05/11/japan/ai-fugaku-language-model-japanese/ | |||
| 14:16 | Unlocking the potential of LLMs: Fine-tuning https://medium.com/@souhailguennouni/unlocking-the-potential-of-llms-fine-tuning-1467d4b13fcc | |||
| 13:48 | Mixture-of-Experts (MoE) Evolution https://medium.com/@m_chak/mixture-of-experts-moe-evolution-c6acacf17167 | |||
| 13:27 | The Night I Asked ChatGPT How to Build a Bomb https://reason.com/2024/05/11/the-night-i-asked-chatgpt-how-to-build-a-bomb/ | |||
| 13:14 | Is AI Really Intelligent? The Generative AI Paradox https://medium.com/@mkdev/is-ai-really-intelligent-the-generative-ai-paradox-9af433fd7767 | |||
| 12:54 | ZeRO: Breaking Down the Revolutionary Approach to Optimizing Deep Learning Models https://medium.com/@punya8147_26846/zero-breaking-down-the-revolutionary-approach-to-optimizing-deep-learning-models-1cc0a403d591 | |||
| 12:38 | How DDP Helps Train LLM https://medium.com/@punya8147_26846/how-ddp-helps-train-llm-38899c0472ac | |||
| 12:28 | LLMs in Action: Text Compression and Decompression Techniques https://mawgoud.medium.com/llms-in-action-text-compression-and-decompression-techniques-171a31985803 | |||
| 11:58 | Run Ollama Llama3 LLM on Google Colab using colab-xterm https://medium.com/@varsha.rainer/run-ollama-llama3-llm-on-google-colab-9b56b7254be9 | |||
| 10:43 | Hanooman: A Generative AI and Large Language Model Chatbot Inspired From Lord Hanuman https://medium.com/@vavekbharwani/hanooman-a-generative-ai-and-large-language-model-chatbot-inspired-from-lord-hanuman-90da57f900a5 | |||
| 10:40 | Building Your Own Gemini Pro Chatbot with Python https://medium.com/@obotnt/unleashing-the-power-of-gemini-llm-api-crafting-your-own-ai-chatbot-75aa9ae7e2df | |||
| 09:13 | ChatGPT FAQ: Everything you need to know in 16 questions. https://medium.com/@gcentulani/chatgpt-faq-everything-you-need-to-know-in-16-questions-61ff0cf454f3 | |||
| 08:59 | BERT - Bidirectional Encoder Representations from Transformers https://medium.com/@varunsivamani/bert-bidirectional-encoder-representations-from-transformers-4897ec2e9a06 | |||
| 08:53 | Introduction to LLMs: An Overview of Prompts https://medium.com/donato-story/introduction-to-llms-an-overview-of-prompts-281040aa5ff9 | |||
| 08:53 | Show HN: Building a Jarvis-Like AI Program with ZeroLM and ChatGPT https://blog.civai.co/2023/09/building-jarvis-like-ai-program-with.html | |||
| 07:38 | Demystifying the Hype: A Deep Dive into Large Language Models https://medium.com/@guptaaaisha/demystifying-the-hype-a-deep-dive-into-large-language-models-d98d713fbd33 | |||
| 07:17 | How Field AI plans to take AI to next level using Field Foundation Models(FFM) https://adithyathatipalli.medium.com/how-field-ai-plans-to-take-ai-to-next-level-using-field-foundation-models-ffm-895e1542ed7c | |||
| 07:02 | AI Basics: Lesson 06 https://medium.com/kinomoto-mag/ai-basics-lesson-06-26949d5fa2e5 | |||
| 06:34 | Unlocking the Power of Language Models through Fine-Tuning and Efficient Transfer Learning https://blog.gopenai.com/unlocking-the-power-of-language-models-through-fine-tuning-and-efficient-transfer-learning-04ae957af040 | |||
| 06:30 | Unveiling Microsoft’s MAI-1: A New AI-Language Challenger https://medium.com/@shayan-ali/unveiling-microsofts-mai-1-a-new-ai-language-challenger-64c8a90ebfa0 | |||
| 06:00 | This AI Paper by Microsoft and Tsinghua University Introduces YOCO: A Decoder-Decoder Architectures for Language Models https://www.marktechpost.com/2024/05/10/this-ai-paper-by-microsoft-and-tsinghua-university-introduces-yoco-a-decoder-decoder-architectures-for-language-models/ | |||
| 05:30 | LangChain: Agents https://medium.com/@rutambhagat/langchain-agents-64e0010d9972 | |||
| 04:41 | Optimizing Latency: Strategies for Efficient LLM Inference in Task Execution https://medium.com/@manojkotary/optimizing-latency-strategies-for-efficient-llm-inference-in-task-execution-5a31de0a0d85 | |||
| 04:03 | Apple finalizing deal with OpenAI to bring ChatGPT features to iOS 18 https://9to5mac.com/2024/05/10/ios-18-chatgpt-features-apple-openai/ | |||
| 03:49 | Show HN: MinimalChat – A Simple and Customizable LLM Chat Application https://github.com/fingerthief/minimal-chat | |||
| 03:42 | Tech giants are changing their views on AI NSFW content | Noah Z. NsfwGPT.ai https://medium.com/@nsfwgpt.ai/tech-giants-are-changing-their-views-on-ai-nsfw-content-03f3d5935b6c | |||
| 02:59 | A Survey Report on New Strategies to Mitigate Hallucination in Multimodal Large Language Models https://www.marktechpost.com/2024/05/10/a-survey-report-on-new-strategies-to-mitigate-hallucination-in-multimodal-large-language-models/ | |||
| 01:55 | Measuring the Cultural Adaptability of Large Language Models https://medium.com/@abhinav.797c/measuring-the-cultural-adaptability-of-large-language-models-4e86729e5122 | |||
| 01:40 | Apple Nears Deal with OpenAI to Put ChatGPT on iPhone https://www.bloomberg.com/news/articles/2024-05-11/apple-closes-in-on-deal-with-openai-to-put-chatgpt-on-iphone | |||
| 01:17 | The Evolution and Future of Cloud Security Posture Management (CSPM): Transforming Cloud Security https://medium.datadriveninvestor.com/the-evolution-and-future-of-cloud-security-posture-management-cspm-transforming-cloud-security-79b326010bb8 | |||
| 00:50 | Do Enormous LLM Context Windows Spell the End of RAG? https://thenewstack.io/do-enormous-llm-context-windows-spell-the-end-of-rag/ | |||
| Friday, 2024-05-10 | ||||
| 23:39 | Meet StyleMamba: A State Space Model for Efficient Text-Driven Image Style Transfer https://www.marktechpost.com/2024/05/10/meet-stylemamba-a-state-space-model-for-efficient-text-driven-image-style-transfer/ | |||
| 23:04 | Join the DEKUBE Genesis Points Campaign and Shape the Future of AI! https://medium.com/@dekube/join-the-dekube-genesis-points-campaign-and-shape-the-future-of-ai-66346fe5d96e | |||
| 22:47 | Not all tokens are created equal https://medium.com/@disparate-ai/not-all-tokens-are-created-equal-7347d549af4d | |||
| 22:44 | Pengcognito: You don’t want to be in that category. https://jenbeaven.medium.com/pengcognito-you-dont-want-to-be-in-that-category-67b50d3803e9 | |||
| 22:17 | Griffin: New LLM Architecture Conquer Long Contexts https://angelina-yang.medium.com/griffin-new-llm-architecture-conquer-long-contexts-9c767a2d4489 | |||
| 21:57 | Sam Altman's nuclear energy company Oklo plunges 54% in NYSE debut https://www.cnbc.com/2024/05/10/sam-altman-takes-nuclear-startup-oklo-public-to-power-ai-ambitions.html | |||
| 21:56 | The Art of LLM Selection https://medium.com/@chrisvitalos/the-art-of-llm-selection-46959e7f064e | |||
| 21:37 | Get rid of your digital clutter with watsonx.ai and CLI for GenAI https://medium.com/@rafal.bigaj/get-rid-of-your-digital-clutter-with-watsonx-ai-and-cli-for-genai-a762e092a6a8 | |||
| 21:08 | Tuning the Symphony of AI: A Beginner’s Guide to LLM Hyperparameters https://medium.com/@anish.gillella/tuning-the-symphony-of-ai-a-beginners-guide-to-llm-hyperparameters-b3159042b2af | |||
| 20:33 | RAG: A Simple DIY Approach https://medium.com/@helmanofer/search-with-rag-a-simple-diy-approach-a38074109260 | |||
| 20:31 | Unveiling the Decoder: A Deep Dive into Transforming Encoded Representations into Human… https://medium.com/@mauryaanoop3/unveiling-the-decoder-a-deep-dive-into-transforming-encoded-representations-into-human-18cb06e12e3a | |||
| 20:28 | Understanding Mathematics behind floating-point precisions https://medium.com/decisionforce/understanding-mathematics-behind-floating-point-precisions-24c7aac535e3 | |||
| 19:55 | Who’s replacing Whom? Unpacking LLM’s and Labor Myths https://medium.com/@vanshika02/whos-replacing-whom-unpacking-llm-s-and-labor-myths-bca1eff58a72 | |||
| 19:46 | Fine-tuning Mistral-7B-v02: A Step-by-Step Guide https://medium.com/@markorlando45/fine-tuning-mistral-7b-v02-a-step-by-step-guide-6b6262d2b4a0 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801