LLM News and Articles
Monday, 2024-10-14 | ||||
18:06 | From Feature Flags to Prompt Flags https://medium.com/@jenn-j-dev/from-feature-flags-to-prompt-flags-fd754ab7f7c3 | |||
17:59 | Building a ReAct Agent from Scratch: A Beginner’s Guide: https://generativeai.pub/building-a-react-agent-from-scratch-a-beginners-guide-4a7890b0667e | |||
16:52 | Chain of Thought and Tree of Thoughts: Solving the Shortest Path Problem Using Tree of Thoughts. https://medium.com/@naziyamahimkar13/chain-of-thought-and-tree-of-thoughts-solving-the-shortest-path-problem-using-tree-of-thoughts-de6a1d06250e | |||
16:02 | Reducing Hallucinations by 95% with Memory Tuning https://odsc.medium.com/reducing-hallucinations-by-95-with-memory-tuning-87031a979705 | |||
15:46 | Show HN: I made a macOS app to support Anthropic Claude https://www.wallestudio.com/ | |||
15:39 | How to Achieve Artificial Superintelligence https://michaellarionov.medium.com/how-to-achieve-artificial-superintelligence-91cfbc592fe0 | |||
15:36 | Fine-Tuning LLM with LoRA for Effective Tool Selection in AI Agents https://medium.com/@homayoun.srp/fine-tuning-llm-with-lora-for-effective-tool-selection-in-ai-agents-bfba687c6da3 | |||
15:31 | Agents Routines & Hand offs, How to build them Intuitively https://medium.com/@kamaljp/agents-routines-hand-offs-how-to-build-them-intuitively-a6f27d32bb64 | |||
15:21 | Differential Transformer Explained: What is it and How Does It Work? https://medium.com/@sahin.samia/differential-transformer-explained-what-is-it-and-how-does-it-work-437d91bd8724 | |||
15:20 | AlphaCodium outperforms direct prompting of OpenAI's o1 on coding problems https://www.qodo.ai/blog/system-2-thinking-alphacodium-outperforms-direct-prompting-of-openai-o1/ | |||
15:07 | Text Splitting in LangChain: A Component of the RAG System https://pub.towardsai.net/text-splitting-in-langchain-a-component-of-the-rag-system-dd4b7b61211a | |||
15:01 | What is RAG and RIG? Key Concepts of Recent Generative AI https://medium.com/@yutowachi52/what-is-rag-and-rig-key-concepts-of-recent-generative-ai-4fae4ea41a8a | |||
14:50 | Deploying your LLM Project with GPU Support Using Docker and Docker Compose https://medium.com/@skalaliya/deploying-your-llm-project-with-gpu-support-using-docker-and-docker-compose-00a049fc3727 | |||
14:49 | How To Run Ollama Models in Colab https://medium.com/@sumithearra/how-to-run-ollama-models-in-colab-cb33fd5b119c | |||
14:39 | Demystifying Generative AI: How Does It Actually Work? https://medium.com/@sanjaypatel91/demystifying-generative-ai-how-does-it-actually-work-9ffce2cfc910 | |||
14:32 | OpenAI DevDay 2024: What ChatGPT Users Want https://medium.com/@tarashekhar97/openai-devday-2024-what-chatgpt-users-want-ee2f50ab3afb | |||
14:09 | ToolGen: framework that unifies tool retrieval and execution in LLMs for scalable and efficient AI… https://medium.com/@techsachin/toolgen-framework-that-unifies-tool-retrieval-and-execution-in-llms-for-scalable-and-efficient-ai-6db733a980fd | |||
14:02 | Building ElevateCV: A Dynamic Resume Builder with React and Flask https://medium.com/@menon.ab/building-elevatecv-a-dynamic-resume-builder-with-react-and-flask-b19a3dd2ae65 | |||
13:57 | Areas of Research in the LLM Field https://medium.com/@aaribhaider2008/areas-of-research-in-the-llm-field-e2f6c3b7df78 | |||
13:55 | An Introduction to LLM Research https://medium.com/@aaribhaider2008/an-introduction-to-llm-research-464bde2d80ee | |||
13:53 | Understanding TF-IDF and c-TF-IDF in Topic Modeling https://medium.com/@shashankag14/understanding-tf-idf-and-c-tf-idf-in-topic-modeling-071eb82fa858 | |||
13:39 | Entropix: Sampling Techniques for Maximizing Inference Performance https://medium.com/@m_sea_bass/entropix-sampling-techniques-for-maximizing-inference-performance-a422d65b6c65 | |||
13:32 | Authorship Attribution: Why Identifying Who Wrote What is More Important Than Ever in the Age of… https://thishuang.medium.com/authorship-attribution-why-identifying-who-wrote-what-is-more-important-than-ever-in-the-age-of-91fb8cf98096 | |||
13:31 | Building Multi AI Agent Systems: A Comprehensive Guide! https://ai.plainenglish.io/building-multi-ai-agent-systems-a-comprehensive-guide-58bf21f84f6e | |||
13:13 | Show HN: Microagent, a fork of OpenAI Swarm that supports Groq and Anthropic https://github.com/chrislatimer/microagent | |||
12:50 | Language Model Categorisation https://cobusgreyling.medium.com/language-model-categorisation-95ad2865566e | |||
12:43 | How Do Businesses Successfully Scale LLM Solutions from Development to Deployment? https://medium.com/coinmonks/how-do-businesses-successfully-scale-llm-solutions-from-development-to-deployment-7fe806b75478 | |||
12:25 | Introduction to Power BI Front-End and Back-End: A Deep Dive https://medium.com/@punya8147_26846/introduction-to-power-bi-front-end-and-back-end-a-deep-dive-67fcfb5953ea | |||
11:43 | Chat GPT is Bad at Math | Philip Okoampah Kwaning https://medium.com/@philipokoampah/chat-gpt-is-bad-at-math-philip-okoampah-kwaning-f21de893eca2 | |||
11:21 | Building Production-Ready AI Agents with LangGraph: A Real-Life Use Case https://medium.com/cyberark-engineering/building-production-ready-ai-agents-with-langgraph-a-real-life-use-case-7bda34c7f4e4 | |||
11:06 | LightRAG the Cross breed of NavieRag and GraghRAG https://medium.com/@sumithearra/lightrag-the-cross-breed-of-navierag-and-graghrag-a1548df81fa7 | |||
10:11 | How to Create an Agriculture Chatbot Using Gemini API https://medium.com/@ja_hagani/how-to-create-an-agriculture-chatbot-using-gemini-api-b7220d9429f8 | |||
09:57 | Top Open-Source AI Chatbot Tools for 2024–2025 https://medium.com/@marrouchi.mohamed/top-open-source-ai-chatbot-tools-for-2024-2025-255a95c82493 | |||
09:47 | Simple RAG with Langchain, Google Gemini, and FAISS Vector Database https://medium.com/@michwirja/simple-rag-with-langchain-google-gemini-and-faiss-vector-database-67e4cd6cb66f | |||
09:35 | How Do Customized Large Language Models Enhance Business Performance? https://medium.com/coinmonks/how-do-customized-large-language-models-enhance-business-performance-403e7fb589da | |||
09:29 | How to Test the Phi-3.5 Model from Hugging Face on Google Colab https://medium.com/@cd_24/how-to-test-the-phi-3-5-model-from-hugging-face-on-google-colab-611cf18d7124 | |||
08:44 | How to Improve Search with LLMs https://medium.com/@dmitrijs.rutko/how-to-improve-search-with-llms-64caa7acc950 | |||
08:41 | How Google Missed the AI Boom and Let OpenAI Dominate https://medium.com/@fathahka/how-google-missed-the-ai-boom-and-let-openai-dominate-620de42bc04e | |||
08:39 | Building a Multi-Agent AI System with Temporal.io: https://generativeai.pub/building-a-multi-agent-ai-system-with-temporal-io-0c3e8f928f6d | |||
08:39 | Unleashing LLM’s Self-Awareness: How SEAKR Enhances Knowledge Retrieval in RA https://generativeai.pub/unleashing-llms-self-awareness-how-seakr-enhances-knowledge-retrieval-in-ra-7a0d6603c8ee | |||
08:26 | Implementing a Retrieval-Augmented Generation (RAG) Model with OpenAI LLM https://medium.com/@bragadeeshs/implementing-a-retrieval-augmented-generation-rag-model-with-openai-llm-c06f0e793f07 | |||
08:20 | Talk @ AWS Telco hackathon, Dallas, TX (09/2024) https://julsimon.medium.com/talk-aws-telco-hackathon-dallas-tx-09-2024-a08ead18ff43 | |||
08:12 | Fast Llama inference in pure, modern Java https://www.youtube.com/watch | |||
08:11 | Attention Mechanism in LLMs: An Intuitive Explanation https://medium.com/@girimanaskumar1998/attention-mechanism-in-llms-an-intuitive-explanation-41a133a1541e | |||
08:01 | Build Your Own Private PDF Search Tool https://medium.com/@hopsworks_ai/build-your-own-private-pdf-search-tool-3d3d0fa333c0 | |||
08:01 | 5 Machine Learning Myths https://medium.com/@carolin.svenberg/5-machine-learning-myths-0d63abdb6d29 | |||
07:56 | How to Run Your Own Local LLM: Updated for 2024 — Version 2 https://thomascherickal.medium.com/how-to-run-your-own-local-llm-updated-for-2024-version-2-78a64000b47a | |||
07:55 | Proof of current (LLMs) SOTA models fails to do general reasoning which isn’t on the internet. https://tharunaithink.medium.com/proof-of-current-llms-sota-models-fails-to-do-general-reasoning-which-isnt-on-the-internet-461c2962c6e0 | |||
07:51 | Multi-Headed Attention in BERT https://medium.com/@nibeditad07/multi-headed-attention-in-bert-3b8affe5e2c4 | |||
07:40 | How Transformers Work: A Detailed Exploration of Transformer Architecture https://medium.com/@girimanaskumar1998/how-transformers-work-a-detailed-exploration-of-transformer-architecture-180e02e4570f | |||
07:30 | Fine Tuning Google Gemma: Enhancing LLMs with Customized Instructions https://medium.com/@girimanaskumar1998/fine-tuning-google-gemma-enhancing-llms-with-customized-instructions-c40483819e6d | |||
07:25 | The Road to AGI: Why Abstraction, Not Just Scaling Models, Is the Key https://medium.com/@sahin.samia/the-road-to-agi-why-abstraction-not-just-scaling-models-is-the-key-03744dbb1d0d | |||
07:16 | AGI — homosapienslərin əlçat(an?)maz arzusu https://medium.com/@v.resad.89/agi-homosapiensl%C9%99rin-%C9%99l%C3%A7at-an-maz-arzusu-4348c7737281 | |||
07:13 | Fine-Tuning SAM 2 on a Custom Dataset https://medium.com/@girimanaskumar1998/fine-tuning-sam-2-on-a-custom-dataset-44e4714e7b03 | |||
07:05 | Speculative RAG Implementation With Transformers https://medium.com/@girimanaskumar1998/speculative-rag-implementation-with-transformers-93320e8a51c0 | |||
06:50 | Phi-3 Tutorial: Hands-On With Microsoft’s Smallest AI Model https://medium.com/@girimanaskumar1998/phi-3-tutorial-hands-on-with-microsofts-smallest-ai-model-a0291561886a | |||
06:35 | Fine-Tuning Phi-3.5 on E-Commerce Classification Dataset https://medium.com/@girimanaskumar1998/fine-tuning-phi-3-5-on-e-commerce-classification-dataset-00b8cd24fec6 | |||
06:30 | Exploring Chat Models with LangChain https://medium.com/donato-story/exploring-chat-models-with-langchain-bfaa363f8edc | |||
06:16 | NVIDIA se lance dans les LLMs https://guillaume-besson.medium.com/nvidia-se-lance-dans-les-llms-c16b5857bcdc | |||
04:32 | OpenR: An Open-Source AI Framework Enhancing Reasoning in Large Language Models https://www.marktechpost.com/2024/10/13/openr-an-open-source-ai-framework-enhancing-reasoning-in-large-language-models/ | |||
04:12 | Power BI: The Gateway to Advanced Analytics and Machine Learning https://medium.com/@punya8147_26846/power-bi-the-gateway-to-advanced-analytics-and-machine-learning-cbb1bec1db63 | |||
04:03 | NVIDIA AI Researchers Explore Upcycling Large Language Models into Sparse Mixture-of-Experts https://www.marktechpost.com/2024/10/13/nvidia-ai-researchers-explore-upcycling-large-language-models-into-sparse-mixture-of-experts/ | |||
04:02 | Beyond “Hello World” — A Race to The Future of Generative AI https://andisama.medium.com/beyond-hello-world-a-race-to-the-future-of-generative-ai-342f784fdebc | |||
03:56 | How LangChain and LlamaIndex Maintain Context https://medium.com/@abhilashkrish/how-langchain-and-llamaindex-maintain-context-be3326ed8ec6 | |||
03:50 | Don’t Ever Drop the First Token. Here’s Why. https://medium.com/@crclq2018/dont-ever-drop-the-first-token-here-s-why-cf86a5013800 | |||
03:31 | What will happen if a big tech-based company hires a senior software developer using LLM and AI in… https://medium.datadriveninvestor.com/what-will-happen-if-a-big-tech-based-company-hires-a-senior-software-developer-using-llm-and-ai-in-0e10e42d0229 | |||
03:04 | Unleashing the Power of Large Language Models: My Journey with LLMs https://heyubaidullah.medium.com/unleashing-the-power-of-large-language-models-my-journey-with-llms-0b03091f62f5 | |||
02:13 | “Large language models (LLMs) are beginning to revolutionize the way we work.” https://medium.com/@yasirhamidkapco/large-language-models-llms-are-beginning-to-revolutionize-the-way-we-work-75c3160d6982 | |||
01:54 | Liquid Foundation Models (LFMs): A Simple Explanation https://ashington.medium.com/liquid-foundation-models-lfms-a-simple-explanation-cf833dbaf3dc | |||
01:27 | Trio: A browser-based LLM that runs locally to create a 3-step task workflow https://github.com/sudoghut/trio | |||
01:21 | Llama 405B 506 tokens/second on an H200 https://developer.nvidia.com/blog/boosting-llama-3-1-405b-throughput-by-another-1-5x-on-nvidia-h200-tensor-core-gpus-and-nvlink-switch/ | |||
00:51 | A Comprehensive Guide to Effective Methods for Fine-Tuning Large Language Models https://medium.com/@gunkurnia/a-comprehensive-guide-to-effective-methods-for-fine-tuning-large-language-models-f0a1c613dc51 | |||
00:37 | Satisfaction Scores of Generative AI Apps Based on Real-Life Questions https://medium.com/@wanglikai/satisfaction-scores-of-generative-ai-apps-based-on-real-life-questions-18a5f5a34de8 | |||
00:32 | Unlocking the Power of Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) https://gagan-mehta.medium.com/unlocking-the-power-of-retrieval-augmented-generation-rag-with-large-language-models-llms-f82f61f49996 | |||
00:32 | The Multimodal Generative AI Revolution https://medium.com/@afshinkhadangi/the-multimodal-generative-ai-revolution-0a21f8029cfe | |||
00:04 | 1000 Days of Learning AI & ML Challenge https://medium.com/@sanderink.ursina95/1000-days-of-learning-ai-ml-challenge-874821107d90 | |||
Sunday, 2024-10-13 | ||||
23:39 | Understanding the Limitations of
Mathematical Reasoning in Large Language Models https://medium.com/@qvwnky9d/understanding-the-limitations-of-mathematical-reasoning-in-large-language-models-093b1808ac37 | |||
23:26 | OpenAI's AI-adjusted earnings numbers have echoes of Groupon and WeWork https://www.msn.com/en-in/news/world/openais-ai-adjusted-earnings-numbers-have-echoes-of-groupon-and-wework/ar-AA1s5VRM | |||
23:10 | Can Editing LLMs Inject Harm? A Deep Dive into New Safety Threats https://thishuang.medium.com/can-editing-llms-inject-harm-a-deep-dive-into-new-safety-threats-dc84d24dcc06 | |||
22:15 | Generative AI On Android — Gemini Nano | Part I https://medium.com/@omeraksu/generative-ai-on-android-gemini-nano-part-i-7a2feb71f321 | |||
22:13 | Generative AI On Android — Gemini Nano | Part II https://medium.com/@omeraksu/generative-ai-on-android-gemini-nano-part-ii-85049304b193 | |||
22:13 | Beauty, the Last Bastion https://medium.com/@yongebai/beauty-the-last-bastion-85a66ee2c0da | |||
21:36 | EligereAI — Technical Breakdown, Background https://medium.com/@hayden-williams-uk/eligereai-technical-breakdown-background-a67a5ce2c31c | |||
21:22 | Use Prolog to improve LLM's reasoning https://shchegrikovich.substack.com/p/use-prolog-to-improve-llms-reasoning | |||
21:05 | Building, Customizing, Training, and Deploying LLMs with Ollama https://medium.com/@a_farag/building-customizing-training-and-deploying-llms-with-ollama-1d4a6b893c11 | |||
20:50 | [Weekend Read] KnowPhish: LLMs Meet Multimodal KGs for Enhancing RBPDs https://nabeelxy.medium.com/weekend-read-knowphish-llms-meet-multimodal-kgs-for-enhancing-rbpds-19b84fb0f1ff | |||
20:43 | Building Next-Gen Apps with LLMs: A Practical Guide with LangChain https://medium.com/@vikashkhandelwal273/building-next-gen-apps-with-llms-a-practical-guide-with-langchain-8af454e1db67 | |||
20:36 | Mathematical Foundations of Large Language Models https://medium.com/@korirkiplangat22/mathematical-foundations-of-large-language-models-541b196ccf84 | |||
20:16 | Understanding Causal Model Induction in Neural Networks for Interpretability https://medium.com/@sharears4077/understanding-causal-model-induction-in-neural-networks-for-interpretability-480daa76c446 | |||
20:04 | A Note on Supercharging Your RAG System https://medium.com/@rohithvr3/a-note-on-supercharging-your-rag-system-5ba392a8e3b1 | |||
19:58 | OpenAI Swarm: A Lightweight Framework for Multi-Agent Orchestration https://levelup.gitconnected.com/openai-swarm-a-lightweight-framework-for-multi-agent-orchestration-b4a83a1a1e37 | |||
19:58 | AgentKit, A Lightweight Multi-Agent Framework for Creating Complex Apps https://levelup.gitconnected.com/agentkit-a-lightweight-multi-agent-framework-for-creating-complex-apps-eeb5f66945e0 | |||
19:57 | AI-Agent Consensus Framework: Reducing Bias and Improving Accuracy in Generative AI https://levelup.gitconnected.com/ai-agent-consensus-framework-reducing-bias-and-improving-accuracy-in-generative-ai-14f0764098fb | |||
19:47 | An Introduction to NLP and LLMs in the Age of AI https://medium.com/@angelamarieteng/an-introduction-to-nlp-and-llms-in-the-age-of-ai-773fe649ecc8 | |||
19:20 | Small Language Models: Innovations, Applications, and Challenges https://medium.com/@miguelangel.kjh/small-language-models-innovations-applications-and-challenges-23ccf400bdd7 | |||
19:17 | An LLM TDD Loop https://codeinthehole.com/tips/llm-tdd-loop-script/ | |||
19:11 | Understanding Causal and Masked Language Models: How Scaling Laws Impact Their Power https://medium.com/@sajidc707/understanding-causal-and-masked-language-models-how-scaling-laws-impact-their-power-7768d8a86a68 | |||
18:48 | Building an AI-Powered Retrieval System for Alphabet’s Earnings Reports and Conference Call… https://medium.com/@vishnurajs10/building-an-ai-powered-retrieval-system-for-alphabets-earnings-reports-and-conference-call-40a9752d0b2c | |||
18:40 | Fine Tuning Llama 3.2 11B for Question Answering https://medium.com/@coldstart_coder/fine-tuning-llama-3-2-11b-for-question-answering-435c28bb57c1 | |||
18:33 | Breaking Down AI Agentic Patterns in AutoGen https://blog.gopenai.com/breaking-down-ai-agentic-patterns-in-autogen-c2997829e065 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803