LLM News and Articles
| Tuesday, 2024-10-22 | ||||
| 20:00 | Working With Gemini https://medium.com/@petermark/working-with-gemini-6daa0e3523f2 | |||
| 19:57 | Product Management and LLMs: A Personal Journey https://medium.com/@deveshrohan/product-management-and-llms-a-personal-journey-708f8213f0f5 | |||
| 19:15 | Unlocking Your Data: How LLMs Empower Businesses to Tap into Data Warehouses https://medium.com/@brian.kipp/unlocking-your-data-how-llms-empower-businesses-to-tap-into-data-warehouses-628e319c5e34 | |||
| 18:43 | Why Regression Testing LLMs is Essential: A Practical Guide with Promptfoo https://adel-muursepp.medium.com/why-regression-testing-llms-is-essential-a-practical-guide-with-promptfoo-7b39b636bf91 | |||
| 18:43 | Mastering the Art of AI: Essential Prompting Practices for Generative Models https://nadiawood.medium.com/mastering-the-art-of-ai-essential-prompting-practices-for-generative-models-b4a38f93672f | |||
| 18:40 | Understanding — “Generative Adversarial Networks” https://medium.com/@santoshpandey987/understanding-generative-adversarial-networks-21c2c557275e | |||
| 18:27 | Study : GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language… https://medium.com/@dbiswajitdatta/study-gsm-symbolic-understanding-the-limitations-of-mathematical-reasoning-in-large-language-7256e103a016 | |||
| 18:24 | Understanding — BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding https://medium.com/@santoshpandey987/understanding-bert-pre-training-of-deep-bidirectional-transformers-for-language-understanding-90655e542ec4 | |||
| 18:17 | Lida AI Explained: Hands-On Tutorials for Data Science Enthusiasts https://faun.pub/lida-ai-explained-hands-on-tutorials-for-data-science-enthusiasts-0c159fc7737b | |||
| 18:08 | Unlocking the Power of BM25: Why It’s Outshining TF-IDF in the World of Search https://medium.com/@kushagramisra10/unlocking-the-power-of-bm25-why-its-outshining-tf-idf-in-the-world-of-search-152413392790 | |||
| 17:58 | Think of labeled data as the director’s cut for AI — without it, you’re just watching a blooper… https://medium.com/@adari.girishkumar/think-of-labeled-data-as-the-directors-cut-for-ai-without-it-you-re-just-watching-a-blooper-ae8902f5434d | |||
| 17:53 | Understanding TF-IDF: The Secret Sauce Behind Text Analysis https://medium.com/@kushagramisra10/understanding-tf-idf-the-secret-sauce-behind-text-analysis-4f5325acc092 | |||
| 17:46 | Initial explorations of Anthropic's new Computer Use capability https://simonwillison.net/2024/Oct/22/computer-use/ | |||
| 17:12 | Creating an local LLM application with Golang https://zhimin-wen.medium.com/creating-an-local-llm-application-with-golang-6147a2418b41 | |||
| 16:27 | Show HN: LLM Deceptiveness and Gullibility Benchmark https://github.com/lechmazur/deception | |||
| 16:16 | How Does Machine Learning Work? https://medium.com/were-writers/how-does-machine-learning-work-448896902d81 | |||
| 16:07 | Show HN: Steiner – An open-source reasoning model inspired by OpenAI o1 https://medium.com/@peakji/a-small-step-towards-reproducing-openai-o1-b9a756a00855 | |||
| 15:42 | Stability AI Releases Stable Diffusion 3.5: Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo https://www.marktechpost.com/2024/10/22/stability-ai-releases-stable-diffusion-3-5-stable-diffusion-3-5-large-and-stable-diffusion-3-5-large-turbo/ | |||
| 15:37 | AI Dev Tips #10: GPT4ALL — AI Chat with Local Documents, Offline https://medium.com/ai-dev-tips/ai-dev-tips-10-gpt4all-ai-chat-with-local-documents-offline-318da3125ef8 | |||
| 15:33 | Understanding Key AI Terms https://medium.com/@minimaldevops/understanding-key-ai-terms-6cd73534449e | |||
| 15:27 | Try Hybrid Search RAG with LangChain https://medium.com/@koki_noda/try-a-hybrid-search-rag-with-langchain-4488364316a7 | |||
| 15:22 | LLM Zero-to-Hero with Ollama https://robert-mcdermott.medium.com/llm-zero-to-hero-with-ollama-913e50d6b7f0 | |||
| 15:10 | Anthropic Claude 3.5 Sonnet and Haiku https://twitter.com/anthropicai/status/1848742740420341988 | |||
| 15:06 | Navigating the Complexities of Evaluating Retrieval-Augmented Generation Systems https://medium.com/@moudather.chelbi/navigating-the-complexities-of-evaluating-retrieval-augmented-generation-systems-e7dc6b9274a8 | |||
| 15:02 | RAG vs Fine-Tuning: A Complete Guide to AI Customization https://medium.com/@ahmadmukhtar2001/rag-vs-fine-tuning-a-complete-guide-to-ai-customization-d2ee8f063977 | |||
| 15:01 | AI for Science: How to turn your LLM into an Innovation Machine https://www.llmwatch.com/p/ai-for-science-how-to-turn-your-llm | |||
| 14:52 | Building a Greenwashing Detection System Using Retrieval-Augmented Generation (RAG) https://medium.com/@artur.sogomonyan/building-a-greenwashing-detection-system-using-retrieval-augmented-generation-rag-11ebb2cd4afc | |||
| 14:23 | Want to Dominate Crypto? Automate Your Research Like a Pro https://medium.com/the-crypto-kiosk/want-to-dominate-crypto-automate-your-research-like-a-pro-9fbed8cb4a79 | |||
| 14:12 | Datasets for Bias Evaluation in Language Models https://code.likeagirl.io/datasets-for-bias-evaluation-in-language-models-6205fea3bfc5 | |||
| 14:02 | TAI #122; LLMs for Enterprise Tasks; Agent Builders or Fully Custom Pipelines? https://pub.towardsai.net/tai-122-llms-for-enterprise-tasks-agent-builders-or-fully-custom-pipelines-a08e519ed527 | |||
| 14:02 | [Digital MATSUMOTO] “Is this the correct understanding of AI?” https://medium.com/@digitalmatsumoto/digital-matsumoto-is-this-the-correct-understanding-of-ai-2f0f569e35fa | |||
| 12:06 | Agent Zero: The Ultimate AI Command-Line Assistant with Gaia Integration https://medium.com/@zulfanbaswedan/agent-zero-the-ultimate-ai-command-line-assistant-with-gaia-integration-5b90b6e1a520 | |||
| 12:01 | Zamba2–7B: Setting New Standards in NLP Performance and Efficiency — 25% Faster Inference with… https://pub.towardsai.net/zamba2-7b-setting-new-standards-in-nlp-performance-and-efficiency-25-faster-inference-with-2d45de826b9b | |||
| 12:00 | The Role of RISC-V in Shaping the Future of AI and Computational Neurosciences with Multi-Agent… https://medium.com/@jsmith0475/the-role-of-risc-v-in-shaping-the-future-of-ai-and-computational-neurosciences-with-multi-agent-4ca2a90e2765 | |||
| 11:32 | Retrieval-Augmented Generation (RAG) for Document-Based Question Answering https://ai.gopubby.com/retrieval-augmented-generation-rag-for-document-based-question-answering-c3f5f939f886 | |||
| 10:54 | Using ChatGPT for research? https://medium.datadriveninvestor.com/using-chatgpt-for-research-bb570f3bee03 | |||
| 10:49 | Understanding How to Evaluate AI Language Models: A Simple Guide https://andreda-mind.medium.com/understanding-how-to-evaluate-ai-language-models-a-simple-guide-c5378f6d3072 | |||
| 10:09 | Prompt or Be Prompted: The Beginner’s Guide to Prompt Engineering https://medium.com/@mayomi1/prompt-or-be-prompted-the-beginners-guide-to-prompt-engineering-7c96e62bb3eb | |||
| 09:59 | Following LLM Manufacturer's Instructions https://www.armilla.ai/resources/following-llm-manufacturers-instructions | |||
| 09:22 | Using LLMs on Your Phone Locally in Three Easy Steps https://medium.com/@frank.t.f.ye/using-llms-on-your-phone-locally-in-three-easy-steps-30367c3a60a3 | |||
| 08:57 | How to Train Your Own LLM Using Existing Models Hosted by Providers https://medium.com/@r00tb33r/how-to-train-your-own-llm-using-existing-models-hosted-by-providers-1f72e485d1e5 | |||
| 08:45 | Top 10 LLM Development Companies in UAE https://medium.com/coinmonks/top-10-llm-development-companies-in-uae-f67535da8983 | |||
| 08:40 | Top 20 LLM Development Companies In US https://medium.com/coinmonks/top-20-llm-development-companies-in-us-cc87eb01e8fa | |||
| 08:40 | LLM Benchmark: An Ultimate Guide For 2025 https://medium.com/coinmonks/llm-benchmark-an-ultimate-guide-for-2025-ad4d40db9238 | |||
| 08:30 | How to Build an LLM from Scratch? An Overview https://medium.com/coinmonks/how-to-build-an-llm-from-scratch-an-overview-59b34f9659e4 | |||
| 08:26 | How to Train Your Llama: The Trilogy https://taswhe.medium.com/how-to-train-your-llama-the-trilogy-79fec761978f | |||
| 08:09 | How to Train Your Llama: Hyper Parameters (Part 3) https://taswhe.medium.com/how-to-train-your-llama-hyper-parameters-part-3-8c0ee7f9e1da | |||
| 08:01 | How to Train Your Llama: Go Wide, Go Deep (Part 2) https://taswhe.medium.com/how-to-train-your-llama-go-wide-go-deep-part-2-9336a83f5f09 | |||
| 07:57 | How to Train Your Llama: For Fun & Profit (Part 1) https://taswhe.medium.com/how-to-train-your-llama-for-fun-profit-part-1-bada51c5eda2 | |||
| 07:31 | Harnessing the Power of LLaMA-3: Effective Hyperparameter Tuning and Advanced Optimization… https://medium.com/@abhilashkrish/harnessing-the-power-of-llama-3-effective-hyperparameter-tuning-and-advanced-optimization-8d7b72647f33 | |||
| 06:55 | Why Scaling Works: Inductive Biases vs The Bitter Lesson https://towardsdatascience.com/why-scaling-works-inductive-biases-vs-the-bitter-lesson-9c2782f99b18 | |||
| 06:53 | Building a Natural Language to SQL Query Generator Using Large Language Models (LLMs) https://medium.com/@abhilashkrish/building-a-natural-language-to-sql-query-generator-using-large-language-models-llms-8653f654c7b6 | |||
| 06:51 | Building Industry-Specific LLMs https://medium.com/@bragadeeshs/building-industry-specific-llms-481874585018 | |||
| 06:51 | Stitching Prompts using LangChain Expression Language https://medium.com/@anshuk.pal_17235/stitching-prompts-using-langchain-expression-language-b944c0329e6f | |||
| 06:50 | 10x Your Local LLM: Create a RAG with Local LLM + DuckDuckGo API! https://medium.com/@AIMom/10x-your-local-llm-create-a-rag-with-local-llm-duckduckgo-api-860cb46aa9dc | |||
| 06:39 | Breaking Down Key Concepts in LLMs and LLaMA-2 Architecture https://medium.com/@abhilashkrish/breaking-down-key-concepts-in-llms-and-llama-2-architecture-d902e7f2603f | |||
| 06:32 | Understanding Large Language Models (LLMs): A Game-Changer in AI https://medium.com/@LearnersGalaxy/understanding-large-language-models-llms-a-game-changer-in-ai-5e97e2822183 | |||
| 05:53 | Exploring the Latest Advances in AI: From Healthcare to Finance and Beyond https://medium.com/@vivekkalyanarangan/exploring-the-latest-advances-in-ai-from-healthcare-to-finance-and-beyond-3fc566b7ecc7 | |||
| 05:39 | Decoding an LLM’s Thoughts: Logit Lens in Just 25 Lines of Code https://ai.plainenglish.io/decoding-an-llms-thoughts-logit-lens-in-just-25-lines-of-code-100c1dbf2ac0 | |||
| 05:28 | OpenRAG: An Open-Source GenAI Application to Supercharge Data Queries with Large Language Models https://abdulla-ansari.medium.com/openrag-an-open-source-genai-application-to-supercharge-data-queries-with-large-language-models-0579ade119de | |||
| 04:39 | From N-grams to GPT-4: The Evolution of Predictive Text Modeling https://medium.com/@mukul.mschauhan/from-n-grams-to-gpt-4-the-evolution-of-predictive-text-modeling-38f2427da225 | |||
| 04:32 | Efficient Model Tuning: Exploring PEFT, LoRA, and Other Techniques https://medium.com/@kshitijdarwhekar/parameter-efficient-fine-tuning-peft-268dd8c99692 | |||
| 04:07 | Multi-Agent LLM in Banking https://medium.com/@bragadeeshs/multi-agent-llm-in-banking-2562f4a055ba | |||
| 03:47 | Unlock the right foundational model for Your AI with Amazon Bedrock https://devopslearning.medium.com/unlock-the-right-foundational-model-for-your-ai-with-amazon-bedrock-3fafbb0db039 | |||
| 02:49 | Self-Attention in NLP: From Static to Dynamic Contextual Embeddings https://medium.com/@d.isham.ai93/self-attention-in-nlp-from-static-to-dynamic-contextual-embeddings-4e26d8c49427 | |||
| 02:46 | RAG vs. Fine-Tuning vs. Prompting: Methods to Reduce AI Hallucinations https://blog.algesoft.com/rag-vs-fine-tuning-vs-prompting-methods-to-reduce-ai-hallucinations-a60bb9221f47 | |||
| 01:58 | LLM-as-a-Judge: A Technique for Evaluation Using LLMs https://medium.com/gaudiy-web3-and-ai-lab/032a47b0b017 | |||
| 01:38 | Using Google’s NotebookLM for Data Science: A Comprehensive Guide https://medium.com/@sarayavalasaravikiran/using-googles-notebooklm-for-data-science-a-comprehensive-guide-0ef4f1fc1e41 | |||
| 01:38 | Using Google’s NotebookLM for Data Science: A Comprehensive Guide https://ai.plainenglish.io/using-googles-notebooklm-for-data-science-a-comprehensive-guide-0ef4f1fc1e41 | |||
| 01:34 | Abstraction in AI https://medium.com/think-ai/abstraction-in-ai-04f09d7171cd | |||
| 00:57 | Using Vector Steering to Improve Model Guidance https://towardsdatascience.com/using-vector-steering-to-improve-model-guidance-9cca64635510 | |||
| 00:42 | Streamlining Diverse Document Handling and LLM Analysis with Prompt Flow https://medium.com/@karthikrao183/streamlining-diverse-document-handling-and-llm-analysis-with-prompt-flow-6f4ae78894e5 | |||
| 00:00 | Releasing Outlines-core 0.1.0: structured generation in Rust and Python https://huggingface.co/blog/outlines-core | |||
| 00:00 | 🧨 Diffusers welcomes Stable Diffusion 3.5 Large https://huggingface.co/blog/sd3-5 | |||
| 00:00 | Transformers.js v3: WebGPU support, new models & tasks, and more… https://huggingface.co/blog/transformersjs-v3 | |||
| Monday, 2024-10-21 | ||||
| 23:22 | Fine-Tuning Mistral 7B with Hugging Face AutoTrain to Generate Better Midjourney Prompts https://levelup.gitconnected.com/fine-tuning-mistral-7b-with-hugging-face-autotrain-to-generate-better-midjourney-prompts-fb96057c138a | |||
| 23:21 | RAG- Hybrid Search with Ensemble Retriever vs. https://levelup.gitconnected.com/rag-hybrid-search-with-ensemble-retriever-vs-de6625d4ba63 | |||
| 23:21 | Building Porter: Your Personal AI Assistant with Memory Using Ollama’s Llama3.1, https://levelup.gitconnected.com/building-porter-your-personal-ai-assistant-with-memory-using-ollamas-llama3-1-efb32b80c129 | |||
| 22:01 | Generative AI’s Growing Tech Debt: Managing the Ripple Effect https://pub.towardsai.net/generative-ais-growing-tech-debt-managing-the-ripple-effect-e7f4b11dbb2f | |||
| 22:01 | Why Memory Matters https://medium.com/@dr.i.watson/why-memory-matters-b48b10bad845 | |||
| 21:44 | Exploring AI Agents with Lamini https://medium.com/@dirakx/exploring-ai-agents-with-lamini-ce3ee1ad0f59 | |||
| 21:34 | Car game. https://medium.com/@sila_22801/car-game-081ffcd0bbed | |||
| 21:29 | The Power of Language: Exploring the Impact of Large Language Models (LLMs) https://medium.com/@rifaferzana/the-power-of-language-exploring-the-impact-of-large-language-models-llms-2a4a70bab25e | |||
| 21:23 | China’s STAR1 Humanoid Robot Breaks Speed Record with AI and High-Torque Innovation https://medium.com/@mariem.jabloun/the-fastest-humanoid-robot-star1-22293446c56a | |||
| 21:12 | Murdoch's news sue Perplexity AI for allegedly engaging in 'massive freeriding' https://www.cnn.com/2024/10/21/media/rupert-murdoch-dow-jones-perplexity-lawsuit/index.html | |||
| 21:06 | Review: Learning In-context Learning for Named Entity Recognition https://medium.com/@farihaanjum.24csedu.022/review-learning-in-context-learning-for-named-entity-recognition-7c31d326d22c | |||
| 21:00 | Thinking Fast and Slow: Google DeepMind’s Dual-Agent Architecture for Smarter AI https://medium.com/syncedreview/thinking-fast-and-slow-google-deepminds-dual-agent-architecture-for-smarter-ai-d49a0285473f | |||
| 20:54 | Let’s Verify Step by Step, ORM vs PRM https://medium.com/@yananchen1116/lets-verify-step-by-step-orm-vs-prm-613ecffb59ab | |||
| 20:43 | 6 Kaggle Notebooks to Build a Strong Foundation in LangChain https://levelup.gitconnected.com/6-kaggle-notebooks-to-build-a-strong-foundation-in-langchain-063751b0f184 | |||
| 20:42 | How to Measure Performance & Quality of LLMs powered Systems with the Right Metrics https://medium.com/@joana.c.mesquita.f/how-to-measure-performance-quality-of-llms-powered-systems-with-the-right-metrics-edf07ea02cf0 | |||
| 20:28 | How I turn research papers into an engaging podcasts on Spotify using NotebookLM https://dswharshit.medium.com/how-i-turn-research-papers-into-an-engaging-podcasts-on-spotify-using-notebooklm-bdb1d980c3c6 | |||
| 20:15 | From Data to Creativity: The Power of LLMs (-2-) https://medium.com/@anilcogalan/from-data-to-creativity-the-power-of-llms-2-0a5e9d6b260a | |||
| 20:01 | A Taxonomy of Retrieval Augmented Generation https://pub.towardsai.net/a-taxonomy-of-retrieval-augmented-generation-a39eb2c4e2ab | |||
| 19:57 | Experiments with RAGAs : For testing and evaluating LLM application https://medium.com/@kirankumar_61999/experiments-with-ragas-for-testing-and-evaluating-llm-application-cdfdb448a245 | |||
| 19:40 | Guiding Students in Using LLMs: Beyond the Default Approach https://medium.com/acm-cscw/guiding-students-in-using-llms-beyond-the-default-approach-2cb2d6fd7a2d | |||
| 19:23 | THIS COLLEGE STUDENT TURNED #63$ INTO MILLION IN 1.5 YEARS WITH ZER0 MARKETING COST…. https://medium.com/@haiderjhn55/this-college-student-turned-63-into-4-million-in-1-5-years-with-zer0-marketing-cost-f6380b5fedf5 | |||
| 18:54 | Who Owns OpenAI? https://www.bloomberg.com/opinion/articles/2024-10-21/who-owns-openai | |||
| 18:52 | Brincando com os parâmetros no playground da OpenAI https://medium.com/@michel.macario/brincando-com-os-par%C3%A2metros-no-playground-da-openai-b110613da23b | |||
| 18:32 | Coding Llama2 Inference from scratch https://abishek21.medium.com/coding-llama2-inference-from-scratch-96f5b8f29633 | |||
| 18:30 | Perplexity AI's new tool for researching the stock market https://www.zdnet.com/article/perplexity-ais-new-tool-makes-researching-the-stock-market-delightful-heres-how/ | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803