LLM News and Articles
Saturday, 2024-10-19 | ||||
13:05 | Bitnet.cpp an opensource LLM platform by Microsoft https://medium.com/@kldurga999/bitnet-cpp-an-opensource-llm-platform-by-microsoft-8cdeccf272c2 | |||
12:56 | Comparing 6 Frameworks for Rule-based PDF parsing https://medium.com/@AIBites/comparing-6-frameworks-for-rule-based-pdf-parsing-f9e7ca5b6cc9 | |||
12:40 | What is 1-bit LLM? — Bitnet.cpp may eliminate GPUs https://medium.com/@don-lim/what-is-1-bit-llm-bitnet-cpp-may-eliminate-gpus-54b6e0d7207b | |||
12:32 | Reverse Engineering Is Not Hard with LLM Powered Tools https://reflare.com/research/reverse-engineering-is-not-hard-with-llm-powered-tools | |||
12:22 | Understanding System and Normal Prompts in LLM: How They Work and Differ https://generativeai.pub/understanding-system-and-normal-prompts-in-llm-how-they-work-and-differ-df9ea490546c | |||
12:19 | Astute RAG in LLMs: The Key to Better, Trustworthy AI Responses https://medium.com/@sahin.samia/astute-rag-in-llms-the-key-to-better-trustworthy-ai-responses-354667e30450 | |||
12:16 | Revolutionizing Car Shopping with Generative AI https://alex-g.medium.com/revolutionizing-car-shopping-with-generative-ai-d3a8807e02dd | |||
12:09 | LLAMA Series https://ankittaxak5713.medium.com/llama-series-02f7786f39ec | |||
11:55 | Semantic Search: Enhancing Information Retrieval with Meaning and Context https://medium.com/@pyrosv/semantic-search-enhancing-information-retrieval-with-meaning-and-context-37d32adbd63b | |||
11:55 | Semantic Search: Enhancing Information Retrieval with Meaning and Context https://blog.stackademic.com/semantic-search-enhancing-information-retrieval-with-meaning-and-context-37d32adbd63b | |||
11:38 | Understanding the Modern LLM — Part 4: Using PyTorch Autoregressive Encoder-Decoder Architecture… https://medium.com/@ikim1994914/understanding-the-modern-llm-part-4-using-pytorch-autoregressive-encoder-decoder-architecture-abb36aa8a62f | |||
11:14 | Unlocking the Power of Alibaba Cloud Qwen: A Comparative Analysis with AWS and Google Cloud LLMs https://medium.com/@shaista.swati/unlocking-the-power-of-alibaba-cloud-qwen-a-comparative-analysis-with-aws-and-google-cloud-llms-6d9ec674defd | |||
11:11 | Credit Card Fraud Detection Using Snowflakes-Arctic https://usharengaraju.medium.com/credit-card-fraud-detection-using-snowflakes-arctic-6177f20bde71 | |||
10:31 | A Selective Survey of Efficient Speculative Decoding Techniques for LLM Inferen https://blog.codingconfessions.com/p/a-selective-survey-of-speculative-decoding | |||
10:19 | LLMs Finetuning https://ankittaxak5713.medium.com/llms-finetuning-f6eae45f08e4 | |||
10:08 | Retrieval Augmented Generation (RAG) with Ollama (llama3.2) and ChromaDB with Python Code https://medium.com/@jonathantan12/retrieval-augmented-generation-rag-with-ollama-llama3-2-and-chromadb-with-python-code-7a401335c069 | |||
09:56 | The Promise of Personal AI assistants: AgentQ’s Approach to Web Navigation https://medium.com/@iamarihantjha/the-promise-of-personal-ai-assistants-agentqs-approach-to-web-navigation-c169acc9f9e0 | |||
09:05 | Why do you want to use LLM? https://medium.com/@UbaidullahTanoli/why-do-you-want-to-use-llm-4aafabfde7f5 | |||
08:48 | Is Neurosymbolic AI the future Of Truth-Seeking AI? — part 1: LLM Meets Reasoning https://medium.com/@koby.choy/is-neurosymbolic-ai-the-future-of-truth-seeking-ai-part-1-llm-meets-reasoning-6f1c78179a64 | |||
08:37 | trustcall :: Simplifying JSON Data Extraction and Updates https://medium.com/@pankaj_pandey/trustcall-simplifying-json-data-extraction-and-updates-6537aca373a9 | |||
08:37 | Introduction to OpenAI Swarms: Unlocking the Power of Agent Swarms https://medium.com/@kaviyadharishini21/introduction-to-openai-swarms-unlocking-the-power-of-agent-swarms-41e43c05ad74 | |||
08:24 | Unlock Custom Quantization for Hugging Face Models Locally with Ollama : https://pub.towardsai.net/unlock-custom-quantization-for-hugging-face-models-locally-with-ollama-eb34166ced6a | |||
08:18 | Unlock the Future of Hiring: Create an AI-Driven Engineer CV Review System with OpenAI in Just… https://medium.com/@takatsugu/unlock-the-future-of-hiring-create-an-ai-driven-engineer-cv-review-system-with-openai-in-just-9ea9b365b90e | |||
07:43 | Navigating the Challenges of Retrieval Augmented Generation (RAG) https://nizamudheenti.medium.com/navigating-the-challenges-of-retrieval-augmented-generation-rag-e790e69cf82e | |||
07:37 | How to run LLMs locally on your computer? https://jyoti03.medium.com/how-to-run-llms-locally-on-your-computer-268333ea6a3c | |||
07:02 | SimLayerKV: An Efficient Solution to KV Cache Challenges in Large Language Models https://www.marktechpost.com/2024/10/19/simlayerkv-an-efficient-solution-to-kv-cache-challenges-in-large-language-models/ | |||
06:48 | 10+ Best Large Language Model (LLM) Development Companies https://medium.com/ailogic/10-best-large-language-model-llm-development-companies-c9718b4ad8af | |||
06:43 | How Can Large Language Model Development Services Help You Gain a Competitive Edge in 2025? https://medium.com/tokentrends/how-can-large-language-model-development-services-help-you-gain-a-competitive-edge-in-2025-62fc775dca27 | |||
06:24 | Building Your Personal AI Companion: Llama 3.2 Chatbot with Ollama and Docker https://medium.com/accredian/building-your-personal-ai-companion-llama-3-2-chatbot-with-ollama-and-docker-7fa5f2b658f5 | |||
06:23 | Unlocking the Power of Zero-Shot and Few-Shot Learning with LLMs https://medium.com/accredian/unlocking-the-power-of-zero-shot-and-few-shot-learning-with-llms-74082889a7ea | |||
04:59 | Mixture-of-Head Attention (MoH) : alternative to multi-head attention that treats attention heads… https://medium.com/@techsachin/mixture-of-head-attention-moh-alternative-to-multi-head-attention-that-treats-attention-heads-6c82a5d80074 | |||
03:55 | SimLayerKV: framework for Layer-level KV Cache reduction to reduce memory consumption on… https://medium.com/@techsachin/simlayerkv-framework-for-layer-level-kv-cache-reduction-to-reduce-memory-consumption-on-30232f4eed22 | |||
03:36 | 365 Days of New Headlines — A Longitudinal Analysis Driven by Data Science https://medium.com/@kmaurinjones/365-days-of-new-headlines-a-longitudinal-analysis-driven-by-data-science-b39c9ac9d8e5 | |||
03:18 | Probing-RAG: RAG approach with efficient adaptive retrieval pipeline using LLM Hidden States for… https://medium.com/@techsachin/probing-rag-rag-approach-with-efficient-adaptive-retrieval-pipeline-using-llm-hidden-states-for-a97baa0774c5 | |||
01:52 | NVIDIA Nemotron 70B: Is it better for coding compared to GPT-4o https://ai.plainenglish.io/nvidia-nemotron-70b-is-it-better-for-coding-compared-to-gpt-4o-9c61ab21ccc5 | |||
01:39 | Cognitive Prompting in LLMs https://towardsdatascience.com/cognitive-prompting-in-llms-6234f6ab9a4b | |||
00:40 | Crazy Easy OpenAI Fine Tuning https://annacsmedeiros.medium.com/crazy-easy-openai-fine-tuning-88657bc9520f | |||
Friday, 2024-10-18 | ||||
23:58 | How I Studied LLMs in Two Weeks: A Comprehensive Roadmap https://towardsdatascience.com/how-i-studied-llms-in-two-weeks-a-comprehensive-roadmap-e8ac19667a31 | |||
23:37 | Some good work prompts https://medium.com/@randyleonard99/some-good-work-prompts-447972e34999 | |||
23:17 | If you cannot see the world in 3D, you cannot learn from it, interact with it, create in it, or… https://medium.com/@xwggsphc/if-you-cannot-see-the-world-in-3d-you-cannot-learn-from-it-interact-with-it-create-in-it-or-19601b8f156c | |||
23:13 | Main 3 Types of Caching in LLMs with Codes https://medium.com/@mlubbad/main-3-types-of-caching-in-llms-with-codes-d1c067f394b9 | |||
22:25 | Understanding the Algorithms Behind Large Language Models https://medium.com/@gealleh/understanding-the-algorithms-behind-large-language-models-a6d26b938c44 | |||
22:21 | BERT vs Llama: The Battle Against Jailbreaking Eval in AI ️ https://medium.com/@prasoongarg_62435/bert-vs-llama-the-battle-against-jailbreaking-eval-in-ai-%EF%B8%8F-c57aa1f19fdc | |||
22:08 | Building LLMs: Key Insights from Stanford’s CS229 Lecture https://medium.com/@kshitijvj98/building-llms-key-insights-from-stanfords-cs229-lecture-a409e2717a50 | |||
22:03 | LLuffman: LLM-Based Steganography https://botnoise.org/~pokes/lluffman/ | |||
22:01 | 5 Smart Ways to Use Retrieval-Augmented Generation (RAG) to Elevate Your NLP Projects https://pub.towardsai.net/5-smart-ways-to-use-retrieval-augmented-generation-rag-to-elevate-your-nlp-projects-e1c583d0577f | |||
21:34 | Day 6 of — 7 Days of agent framework anatomy from first principles https://medium.com/@mrsirsh/day-6-of-7-days-of-agent-framework-anatomy-from-first-principles-bae7ae187748 | |||
21:32 | Explore Llama 3.1 Paper: An In-Depth Manual https://medium.com/@marketing_novita.ai/explore-llama-3-1-paper-an-in-depth-manual-f6a2a23bbbaf | |||
21:28 | Meta Spirit LM: Open multimodal language model that freely mixes text and speech https://twitter.com/AIatMeta/status/1847383580269510670 | |||
21:07 | Agentic Workflows in AI: A Deep Dive into Multi-Agent Collaboration https://medium.com/@aisquarecommunity/agentic-workflows-in-ai-a-deep-dive-into-multi-agent-collaboration-617d978676fa | |||
20:28 | Microsoft Open-Sources bitnet.cpp: A Super-Efficient 1-bit LLM Inference Framework that Runs Directly on CPUs https://www.marktechpost.com/2024/10/18/microsoft-open-sources-bitnet-cpp-a-super-efficient-1-bit-llm-inference-framework-that-runs-directly-on-cpus/ | |||
20:21 | Sam Altman's eyeball-scanning crypto project has a new Orb and a new name https://www.theverge.com/2024/10/18/24273691/world-orb-sam-altman-iris-scan-crypto-token | |||
20:19 | 12 Top Performing LLMs In 2024 https://medium.com/@kshitijsharma730/12-top-performing-llms-in-2024-26c8638da192 | |||
20:11 | Unlock Claude AI API’s Potential: Effective Usage Tips https://medium.com/@tomskiecke/unlock-claude-ai-apis-potential-effective-usage-tips-ecd40727aa77 | |||
20:08 | Build your own Healthcare Chatbot using a local LLM, Haystack, and PubMed https://medium.com/@AIMom/build-your-own-healthcare-chatbot-using-a-local-llm-haystack-and-pubmed-2c2195e7dfa8 | |||
19:31 | Navigating Audience Engagement https://medium.com/admiring-multipotentiality/navigating-audience-engagement-008fc3616647 | |||
19:29 | Will this LLM-race destroy the environment ? https://medium.com/@junaidsayani03/will-this-llm-race-destroy-the-environment-256e7213cbbe | |||
19:17 | How to Build a Scalable In-Document Search Engine in Just a Few Lines of Code https://medium.com/@AIMom/how-to-build-a-scalable-in-document-search-engine-in-just-a-few-lines-of-code-ecb95a5da674 | |||
19:16 | How Google is changing to compete with ChatGPT https://www.theverge.com/2024/10/18/24273748/google-deepmind-gemini-search-chaptgpt-meta-ai-interview | |||
18:57 | CPU based LLM for GPU-Poor (115.72 https://medium.com/@AyushmanPranav/cpu-based-llm-for-gpu-poor-115-72-909d9c9e6539 | |||
18:34 | How AI-Powered Product Description Enhancements Drive Conversion in E-Commerce https://medium.com/@ysfckmk/how-ai-powered-product-description-enhancements-drive-conversion-in-e-commerce-7998c7da7af1 | |||
18:01 | 🗃️ GraphRAG Evolves into StructRAG https://www.llmwatch.com/p/graphrag-evolves-into-structrag | |||
17:55 | Introduction to Reasoning with Chain of Thought https://pratikbarjatya.medium.com/introduction-to-reasoning-with-chain-of-thought-4f662d48b017 | |||
17:53 | Beyond Traditional Rules, Agentic AI Reshapes Banking Compliance https://medium.com/@j.m.olivera08/beyond-traditional-rules-agentic-ai-reshapes-banking-compliance-dae3d70b6e0b | |||
17:51 | How Transformers Work https://medium.com/@RobuRishabh/how-transformers-work-b08627a300cb | |||
17:42 | Leveraging Smaller LLMs for Enhanced Retrieval-Augmented Generation (RAG) https://towardsdatascience.com/leveraging-smaller-llms-for-enhanced-retrieval-augmented-generation-rag-bc320e71223d | |||
17:31 | LLMO School Part 3: Building an AI-Driven Content Strategy https://medium.com/@johnnydiggz/llmo-school-part-3-building-an-ai-driven-content-strategy-86aec39ba99f | |||
16:38 | Exploring NVIDIA’s Latest Buzz-Worthy AI Model: Hands-On Test https://medium.com/@remidenoyer/exploring-nvidias-latest-buzz-worthy-ai-model-hands-on-test-7c0688aa3bb0 | |||
16:35 | The Competition Between LLMs and Software Products: A Paradigm Shift in AI https://medium.com/illumination/the-competition-between-llms-and-software-products-a-paradigm-shift-in-ai-12f5b0da89c0 | |||
16:11 | Drop GPT o1, try this alternative. https://medium.com/thoughts-on-machine-learning/drop-gpt-o1-try-this-alternative-f22b3d2d54b2 | |||
16:07 | Assessing Large Language Models on Hot Aisle’s AMD MI300X https://medium.com/@semantichasm/assessing-large-language-models-on-hot-aisles-amd-mi300x-11763e5dadb1 | |||
16:03 | Discover the Hidden Power of AI Learning in Creative Workflow! https://medium.com/@AI_Explore/discover-the-hidden-power-of-ai-learning-in-creative-workflow-b7bf47ee425e | |||
16:00 | OpenAI releases ChatGPT app for Windows https://arstechnica.com/ai/2024/10/openai-releases-chatgpt-app-for-windows/ | |||
15:58 | Low-Rank Adaptation (LoRA): Boosting LLMs Without Breaking the Bank https://medium.com/@S.Shakir/low-rank-adaptation-lora-boosting-llms-without-breaking-the-bank-de455974b09a | |||
15:40 | Introduction to Transformers https://medium.com/@RobuRishabh/introduction-to-transformers-ebe87787f7d3 | |||
15:37 | Large Language Models in Machine Learning https://medium.com/@vamsithu2/large-language-models-in-machine-learning-af16fcc9aa4b | |||
15:03 | The AI future will require change what Middle Managmemt needs https://medium.com/@jones.steveg/the-ai-future-will-require-change-what-middle-managmemt-needs-c5dd6dfa3073 | |||
14:54 | UI-Focused AI Agent https://cobusgreyling.medium.com/ui-focused-ai-agent-72b0a2e17646 | |||
14:52 | Power of AI Agents: The Future is Multi-Modal! https://pub.towardsai.net/power-of-ai-agents-the-future-is-multi-modal-c6ecb43431fa | |||
14:39 | AGI Is Not Coming Soon https://nicholas-mitsakos.medium.com/agi-is-not-coming-soon-36fc56e71a91 | |||
14:16 | Don’t Do this to Chatgpt, You’ll Regret! https://medium.com/@peerzadafayzan/dont-do-this-to-chatgpt-you-ll-regret-450e139e414f | |||
14:02 | [Digital MATSUMOTO] “Is this the correct understanding of AI?” https://medium.com/@digitalmatsumoto/digital-matsumoto-is-this-the-correct-understanding-of-ai-e74cfc55f1a3 | |||
13:59 | A Two-Step Test that will help you select the right AI approach https://medium.com/the-ai-strategist/a-two-step-test-that-will-help-you-select-the-right-ai-approach-477fe0371284 | |||
13:43 | How to Use Ollama with GGUF Models from Hugging Face Hub: A Step-by-Step Guide https://medium.com/@monsuralirana/how-to-use-ollama-with-gguf-models-from-hugging-face-hub-a-step-by-step-guide-9aab740eaac3 | |||
13:29 | How to Run Ministral 3B and 8B Model Using Ollama, Huggingface GGUF, and LangChain: A Step-by-Step… https://medium.com/@monsuralirana/how-to-run-ministral-3b-and-8b-model-using-ollama-huggingface-gguf-and-langchain-a-step-by-step-1a750af6a00e | |||
13:08 | Mastering LangChain: A Comprehensive Guide to Key Concepts and Components https://medium.com/@arpit.singhal57/mastering-langchain-a-comprehensive-guide-to-key-concepts-and-components-b97ffdca4a71 | |||
12:58 | The ChatGPT Jailbreak Experience: A Journey Through AI Limitations https://medium.com/@SecResearcher/the-chatgpt-jailbreak-experience-a-journey-through-ai-limitations-132ae682560e | |||
12:51 | LLMD: A Large Language Model for Interpreting Longitudinal Medical Records https://arxiv.org/abs/2410.12860 | |||
12:15 | Salesforce AI Introduces ReGenesis: A Novel AI Approach to Improving Large Language Model Reasoning Capabilities https://www.marktechpost.com/2024/10/18/salesforce-ai-introduces-regenesis-a-novel-ai-approach-to-improving-large-language-model-reasoning-capabilities/ | |||
12:02 | Navigating the Vector Database Landscape: Choosing the Right One for Your Project https://pub.towardsai.net/navigating-the-vector-database-landscape-choosing-the-right-one-for-your-project-38cc21ae15af | |||
12:00 | Model Kinship: The Degree of Similarity or Relatedness between LLMs, Analogous to Biological Evolution https://www.marktechpost.com/2024/10/18/model-kinship-the-degree-of-similarity-or-relatedness-between-llms-analogous-to-biological-evolution/ | |||
11:56 | LLM Agents: Their Past, Present, and Future https://saurabhharak.medium.com/llm-agents-their-past-present-and-future-22988c29a5f8 | |||
11:11 | Microsoft and OpenAI's close partnership shows signs of fraying https://www.nytimes.com/2024/10/17/technology/microsoft-openai-partnership-deal.html | |||
11:08 | AI-Powered Code Review: Is It Worth Paying For? https://medium.com/@API4AI/ai-powered-code-review-is-it-worth-paying-for-157993309f55 | |||
11:03 | About Green AI, Green-in-AI, and Green-by-AI https://medium.com/how-to-realize-ai-projects-in-organizations-a/about-green-ai-green-in-ai-and-green-by-ai-fa2eb5efb53c | |||
10:59 | LLM Consulting Service: Key Features to Look for When Choosing a Provider https://medium.com/@samprasoftyourcloudpartner/llm-consulting-service-key-features-to-look-for-when-choosing-a-provider-816dae233bed | |||
10:49 | Generative AI: Shaping the Future of Creativity and Innovation https://medium.com/@chawlapc.619/generative-ai-shaping-the-future-of-creativity-and-innovation-c018a41a6b08 | |||
10:48 | LLM API Showdown – compare the cheapest and fastest LLM API providers https://llmshowdown.vercel.app/ | |||
10:47 | Revolutionizing Technology: The Power of Generative AI Development Services https://medium.com/@samprasoftyourcloudpartner/revolutionizing-technology-the-power-of-generative-ai-development-services-12f76126aaef | |||
10:44 | 7 Advanced Prompting Techniques for Better Chatbots https://prasadsawant27.medium.com/7-advanced-prompting-techniques-for-better-chatbots-fde8b5a6e23c |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110