LLM News and Articles
| Tuesday, 2024-10-08 | ||||
| 06:44 | New Research on Transformer Architecture part4 https://medium.com/@thekingventer99/new-research-on-transformer-architecture-part4-ad56b91993f4 | |||
| 06:25 | The Emerging Economy of LLMs https://medium.com/wix-engineering/the-emerging-economy-of-llms-883f2ab13067 | |||
| 06:22 | ChromaDB vs PGVector: The Epic Battle of Vector Databases https://dev523.medium.com/chromadb-vs-pgvector-the-epic-battle-of-vector-databases-a43216772b34 | |||
| 06:16 | How to Use a File Storage API for Efficient Data Management https://medium.com/@tayloroakley/how-to-use-a-file-storage-api-for-efficient-data-management-6a1d37955227 | |||
| 06:13 | Episode 10: LLM09 — Over-reliance https://medium.com/@anandpawar26/episode-10-llm09-over-reliance-5ac5dce1acb1 | |||
| 06:02 | Large Language Models (LLMs) https://medium.com/@hayleygohxn/large-language-models-llms-78446bf95f64 | |||
| 05:45 | Open AI Model Pricing: Large Language Models Review and Use https://medium.com/@getanakin/open-ai-model-pricing-large-language-models-review-and-use-0f369576673c | |||
| 04:44 | Road to AGI: Is it even possible? https://akiranin.medium.com/road-to-agi-is-it-even-possible-6bd1dc73c54b | |||
| 04:34 | Open Sourcing Venator https://medium.com/@0x4d31/open-sourcing-venator-b94374e30a55 | |||
| 04:18 | The Role of Retrieval-Augmented Generation (RAG) in Content Marketing: Revolutionizing Personalized… https://palarkaprabha.medium.com/the-role-of-retrieval-augmented-generation-rag-in-content-marketing-revolutionizing-personalized-a2db9627c292 | |||
| 04:08 | Simplifying Meta’s Movie Gen Paper for You https://medium.com/@esmatibrahim/simplifying-metas-movie-gen-paper-for-you-09f02cacc061 | |||
| 04:02 | [Digital MATSUMOTO] How much can we trust benchmark tests? https://medium.com/@digitalmatsumoto/digital-matsumoto-how-much-can-we-trust-benchmark-tests-2b3a044910cc | |||
| 04:02 | [Paper] LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations https://medium.com/@louis19980927/paper-llms-know-more-than-they-show-on-the-intrinsic-representation-of-llm-hallucinations-2389f8f01066 | |||
| 03:58 | Generating documents through LLMs: A hands-on guide to model fine-tuning https://medium.com/@arunabh223/generating-documents-through-llms-a-hands-on-guide-to-model-fine-tuning-5e3031b72ce2 | |||
| 03:56 | Taking an AI approach to digital marketing https://actbrilliant.medium.com/taking-an-ai-approach-to-digital-marketing-6edceab3c34a | |||
| 03:56 | Taking an AI approach to digital marketing https://digitizingpolaris.com/taking-an-ai-approach-to-digital-marketing-6edceab3c34a | |||
| 03:53 | Llama 3.2 vs The World: The Tiny AI That Stomps, Spits, and Slays the Competition! https://medium.com/@teendifferent/llama-3-2-vs-the-world-the-tiny-ai-that-stomps-spits-and-slays-the-competition-bb9f204f02a3 | |||
| 03:15 | The Future of LLMs in Medicine https://medium.com/@henilsinhrajraj/the-future-of-llms-in-medicine-c706427ad4b8 | |||
| 03:07 | A Tale of Three Models: How Transformers, BERT, and ULMFiT Took NLP by Storm https://medium.com/@mukul.mschauhan/a-tale-of-three-models-how-transformers-bert-and-ulmfit-took-nlp-by-storm-58080f1459b6 | |||
| 03:02 | SLMs (Small Language Models) and the 7 key scenarios where they surpass LLMs https://medium.com/@armankamran/slms-small-language-models-and-the-7-key-scenarios-where-they-surpass-llms-b548d73de85e | |||
| 02:16 | How to Use Flat File Integration vs API for Your Projects https://medium.com/@tayloroakley/how-to-use-flat-file-integration-vs-api-for-your-projects-ce38435af4a1 | |||
| 01:45 | Mistral Pricing and Use Cases: A Comprehensive Review of LLMs https://medium.com/@getanakin/mistral-pricing-and-use-cases-a-comprehensive-review-of-llms-4d999ed406be | |||
| 00:44 | FTI Architecture for ML Success-From Features to Inference https://medium.com/@bijit211987/fti-architecture-for-ml-success-from-features-to-inference-9f7005a1c4ae | |||
| 00:05 | Memory https://paigekim29.medium.com/memory-7267f4b23b57 | |||
| 00:00 | Faster Assisted Generation with Dynamic Speculation https://huggingface.co/blog/dynamic_speculation_lookahead | |||
| Monday, 2024-10-07 | ||||
| 23:55 | Close Encounters of the LLM Kind https://vanhoucke.medium.com/close-encounters-of-the-llm-kind-61323cef25d3 | |||
| 23:26 | Training LLMs to Interact and Infer user profiles and personalities for Alignment with individual… https://medium.com/@techsachin/training-llms-to-interact-and-infer-user-profiles-and-personalities-for-alignment-with-individual-e41ac869a05e | |||
| 23:05 | How to become an instant expert on anything — Part 1 https://medium.com/@treadwell.joseph/how-to-become-an-instant-expert-on-anything-part-1-eeab6d6628ea | |||
| 22:37 | A Glimpse at GPT: A Quick and Simple Introduction https://medium.com/@lorenamelo.engr/understanding-gpt-making-sense-of-the-language-of-ai-d64dbab38efd | |||
| 22:17 | How to Use API Integration Steps for Seamless Connectivity https://medium.com/@tayloroakley/how-to-use-api-integration-steps-for-seamless-connectivity-b0629b8ed5b8 | |||
| 21:56 | Privacy Risks of Large Language Models (LLMs) https://ai.gopubby.com/privacy-risks-of-large-language-models-llms-5c0f96dccc56 | |||
| 21:46 | NotebookLM https://medium.com/@lmoise2022/notebooklm-b0104b1515c8 | |||
| 21:45 | Mistral Large Language Model Review: Pricing, Use Cases, and Benchmarks https://medium.com/@getanakin/mistral-large-language-model-review-pricing-use-cases-and-benchmarks-62196422b464 | |||
| 21:32 | Mistake-Aware Peer-Review Distillation: instruction tuning Student LM by peer-review among multiple… https://medium.com/@techsachin/mistake-aware-peer-review-distillation-instruction-tuning-student-lm-by-peer-review-among-multiple-fd4742ae8498 | |||
| 20:55 | Mastering LoRA and QLoRA: Efficient Techniques for Fine-Tuning Large Language Models https://medium.com/@phaneendraganji3/mastering-lora-and-qlora-efficient-techniques-for-fine-tuning-large-language-models-ee76af92267a | |||
| 20:54 | The Future of AI is Here: Zero-Shot Reasoning https://medium.com/thedeephub/zero-shot-a7778b45e7c8 | |||
| 20:31 | Token Efficiency and Compression Techniques in Large Language Models: Navigating Context-Length… https://medium.com/@anicomanesh/token-efficiency-and-compression-techniques-in-large-language-models-navigating-context-length-05a61283412b | |||
| 20:11 | Prompting Made Easy: Basics of Prompting. https://medium.com/@bhanuprakash5507/prompting-made-easy-basics-of-prompting-95c89198e173 | |||
| 20:08 | Llama 3: An Open-Source Game-Changer for AI Applications https://blog.whiteprompt.com/llama-3-an-open-source-game-changer-for-ai-applications-7ed08659968b | |||
| 20:02 | Q&A Bot Using Gen-AI https://pub.towardsai.net/q-a-bot-using-gen-ai-2ab934b180af | |||
| 19:54 | Sam Altman Goes Full Emperor https://nonzero.substack.com/p/sam-altman-goes-full-emperor | |||
| 19:41 | Generated Checklists Improve LLM Evaluation and Generation https://arxiv.org/abs/2410.03608 | |||
| 19:24 | Should the world have uncensored LLMs? https://medium.com/@groups.rampy1/should-the-world-have-uncensored-llms-3d6d77cd3db5 | |||
| 19:14 | L’Adaptation des Centres de Données à l’ère de l’IA : Un Défi et une Opportunité pour l’Écologie https://jeremyjouvance.medium.com/ladaptation-des-centres-de-donn%C3%A9es-%C3%A0-l-%C3%A8re-de-l-ia-un-d%C3%A9fi-et-une-opportunit%C3%A9-pour-l-%C3%A9cologie-85a22920da79 | |||
| 19:12 | Supercharge Your LLM Apps using DSPy and Langfuse https://towardsdatascience.com/supercharge-your-llm-apps-using-dspy-and-langfuse-f83c02ba96a1 | |||
| 18:55 | Why 30% of Devs Go Framework-Free for LLMs https://medium.com/@alejandro7899871776/why-30-of-devs-go-framework-free-for-llms-07ed4f89fa98 | |||
| 18:40 | Scaling RAG from POC to Production https://towardsdatascience.com/scaling-rag-from-poc-to-production-31bd45d195c8 | |||
| 18:36 | A Beginner’s Guide to Fine-Tuning an Embedding Model: https://medium.com/@mauryaanoop3/a-beginners-guide-to-fine-tuning-an-embedding-model-38bb4b4ae664 | |||
| 18:30 | Using Linear Equations + LLM to Solve LinkedIn Queens Game https://towardsdatascience.com/using-linear-equations-llm-to-solve-linkedin-queens-game-fe9802d997e9 | |||
| 18:17 | How to Add Users with the Okta SCIM API Tutorial https://medium.com/@tayloroakley/how-to-add-users-with-the-okta-scim-api-tutorial-2ca54e9d0d78 | |||
| 18:09 | “Exploring the Future of AI: Machine Learning, Large Language Models, and Retrieval-Augmented… https://medium.com/@srivanivinnakotamadhava/exploring-the-future-of-ai-machine-learning-large-language-models-and-retrieval-augmented-3cd442bc4b71 | |||
| 17:55 | How LLMs Works https://towardsdev.com/how-llms-works-3723fa05c9e9 | |||
| 17:45 | Mistral API Pricing and Benchmark Review of Language Models https://medium.com/@getanakin/mistral-api-pricing-and-benchmark-review-of-language-models-c8a36d0a4abd | |||
| 17:43 | Show HN: GPT Circuits – Mapping the inner workings of simple LLMs https://peterlai.github.io/gpt-mri/ | |||
| 17:38 | A RAG based intelligent Chatbot https://chiradip94.medium.com/a-rag-based-intelligent-chatbot-39fc2223d546 | |||
| 17:32 | GemmaTokenizer: A Simple Course on Tokenization https://medium.com/@kuipasta1121/gemmatokenizer-a-simple-course-on-tokenization-3b1eb4559503 | |||
| 16:46 | AIM Weekly for 07 Oct 2024 https://medium.com/@tspann/aim-weekly-for-07-oct-2024-cfdde27cd38e | |||
| 16:23 | Text Classification in Large Language Models (LLMs) https://medium.com/@shashankag14/text-classification-in-large-language-models-llms-7fcaebeae0d4 | |||
| 16:17 | Large Language Models (LLM) ile Dönüşen Dünya https://medium.com/@yarenfenci/large-language-models-llm-ile-d%C3%B6n%C3%BC%C5%9Fen-d%C3%BCnya-8776dbef50ba | |||
| 16:01 | [Research Paper Summary]ReFT: Representation Finetuning for Language Models https://medium.com/athina-ai/research-paper-summary-reft-representation-finetuning-for-language-models-1063e137bda1 | |||
| 15:56 | OpenAI Realtime Console in Streamlit https://github.com/mdagost/openai-realtime-streamlit | |||
| 15:47 | Private LLMs Scaling Made Easy https://medium.com/@original2547/private-llms-scaling-made-easy-95cdc93e381b | |||
| 15:24 | TF-IDF and BM25 for RAG— a complete guide https://levelup.gitconnected.com/tf-idf-and-bm25-for-rag-a-complete-guide-4ec2f0ad7d25 | |||
| 15:02 | How to Implement AI in a DevOps Pipeline? https://medium.com/@hakeemsyd/how-to-implement-ai-in-a-devops-pipeline-5b54297b19ff | |||
| 14:50 | Aiming for Adaptability: Three Valuable Lessons from JournaPilot’s Product Launch https://medium.com/patrick-j-mcgovern-foundation/aiming-for-adaptability-three-valuable-lessons-from-journapilots-product-launch-7d1baa38ccc2 | |||
| 14:49 | Traditional ML and Its New Friend, LLM — Forming “ scikit-llm” https://generativeai.pub/traditional-ml-and-its-new-friend-llm-forming-scikit-llm-69f479ee1dea | |||
| 14:37 | Introducing Wiggle: The Modular, Multi-Node Framework for Large Language Model Workflows https://dshills.medium.com/introducing-wiggle-the-modular-multi-node-framework-for-large-language-model-workflows-e169bcbae233 | |||
| 14:36 | 5 Ways LLMs Are Revolutionizing Academic Research https://chochanmyei.medium.com/5-ways-llms-are-revolutionizing-academic-research-8e974cfb61f2 | |||
| 14:28 | Inovasi AI apa saja yang menarik? https://yogayudhatama.medium.com/inovasi-ai-apa-saja-yang-menarik-7a7ceac34bf2 | |||
| 14:18 | How to Use Unified API: Pros and Cons Explained https://medium.com/@tayloroakley/how-to-use-unified-api-pros-and-cons-explained-2fde93bcca58 | |||
| 14:17 | Testing LLM Apps with Trace-based Tests https://medium.com/kubeshop-i/testing-llm-apps-with-trace-based-tests-0544e359f627 | |||
| 14:08 | A Guide to Quantisation in LLMs https://pvsravanth.medium.com/a-guide-to-quantisation-in-llms-2c400c756fb5 | |||
| 13:58 | DeepSeek V2 — The Most Economical Choice, yet still SOTA LLM — Deeply explain with code (part 1) https://generativeai.pub/deepseek-v2-the-most-economical-choice-yet-still-sota-llm-deeply-explain-with-code-part-1-60f32c1ba792 | |||
| 13:54 | Run LLMs Locally: 7 Simple Methods https://generativeai.pub/run-llms-locally-7-simple-methods-32ed44ba73d6 | |||
| 13:46 | Mistral AI Pricing Review: Benchmarks and Usage Options https://medium.com/@getanakin/mistral-ai-pricing-review-benchmarks-and-usage-options-b2c11f78f48e | |||
| 13:10 | Game UI Database slowdown caused by relentless OpenAI scraping https://www.gamedeveloper.com/business/-this-was-essentially-a-two-week-long-ddos-attack-game-ui-database-slowdown-caused-by-openai-scraping | |||
| 13:02 | Evaluating a RAG Solution with Giskard https://pub.towardsai.net/evaluating-a-rag-solution-with-giskard-1bc138fa44af | |||
| 13:01 | Chain of Thought in Llama 3 from scratch https://medium.com/@alejandro7899871776/chain-of-thought-in-llama-3-from-scratch-6e39d4df699e | |||
| 12:46 | Inside the Minds of AI Transformers: Unpacking Their Types, Powers, and Real-World Impact https://medium.com/@vidhyashree.v/inside-the-minds-of-ai-transformers-unpacking-their-types-powers-and-real-world-impact-375d6c57e59e | |||
| 12:40 | Top 15 LLM Development Companies In US https://medium.com/coinmonks/top-15-llm-development-companies-in-us-a387716d7159 | |||
| 12:27 | Were RNNs All We Needed? Exploring MiniGRU and MiniLSTM Models for Sequence Modeling https://medium.com/@sahin.samia/were-rnns-all-we-needed-exploring-minigru-and-minilstm-models-for-sequence-modeling-664e4675c339 | |||
| 12:17 | Beehive – LLM Agentic Framework https://github.com/BeehiveHQ/beehive-ai | |||
| 12:02 | SEOs Can Escape Internal Link Hell With Automation https://bettermarketing.pub/seos-can-escape-internal-link-hell-with-automation-ac0ef87bb9ad | |||
| 11:28 | Another OpenAI founder moves to arch-rival Anthropic https://www.theregister.com/2024/10/02/anthropic_hires_openai_founder_durk_kingma/ | |||
| 11:26 | ChatGPT’s o1 Breaks So Many Benchmarks, It’s Infuriating! My Review for 2025 https://ai.plainenglish.io/chatgpts-o1-breaks-so-many-benchmarks-it-s-infuriating-my-review-for-2025-1fd161639a02 | |||
| 11:17 | How to Provide Custom Remote LLM as GPU-Inference by Defining an LLM Wrapper https://medium.com/@harshharsha360/how-to-provide-custom-remote-llm-as-gpu-inference-by-defining-an-llm-wrapper-9c175ca9fb85 | |||
| 10:58 | Introducing LML-DAP: A New Way to Combine Language Models with Data for Better Predictions https://medium.com/@praneeth.v/introducing-lml-dap-a-new-way-to-combine-language-models-with-data-for-better-predictions-b9385566f747 | |||
| 10:57 | CEO’s Guide to AI Integration: Turning Barriers Into Business Opportunities https://medium.com/@helloshorthills/ceos-guide-to-ai-integration-turning-barriers-into-business-opportunities-a4147e809fe7 | |||
| 10:43 | TikTok parent launched a scraper gobbling up world's data 25x faster than OpenAI https://fortune.com/2024/10/03/bytedance-tiktok-bytespider-scraper-bot/ | |||
| 10:35 | Retrievers: The Backbone of Retrieval-Augmented Generation https://medium.com/@kaviyadharishini21/retrievers-the-backbone-of-retrieval-augmented-generation-1544f34dd459 | |||
| 10:34 | FAISS, vector database. Building block of GenAI. https://medium.com/@sunnykumar1516/faiss-vector-database-building-block-of-genai-9f198d795dc7 | |||
| 10:32 | Takeaways From the Llama 3 Release Paper https://medium.com/axinc-ai/takeaways-from-the-llama-3-release-paper-90428875b2d4 | |||
| 10:31 | Prompting and Prompt Engineering https://saurabhharak.medium.com/prompting-and-prompt-engineering-c8657c93c436 | |||
| 10:13 | Rapid Application Development with Large Language Models https://medium.com/@nimritakoul01/rapid-application-development-with-large-language-models-97fd3c9544c2 | |||
| 10:10 | The AI Hack That Boosted My Learning Speed by 10x — and Revolutionized My Business https://augmentedstartups.medium.com/the-ai-hack-that-boosted-my-learning-speed-by-10x-and-revolutionized-my-business-5eb696d28134 | |||
| 09:42 | How to Master OpenAI Function Calling in NestJS: Automate Your Backend with AI Integration https://medium.com/@amarg3891/how-to-master-openai-function-calling-in-nestjs-automate-your-backend-with-ai-integration-2c73096536a1 | |||
| 09:37 | Show HN: LLM fine-tuning SDK and would love your feedback https://docs.luminolabs.ai/introduction | |||
| 09:18 | Zod: TypeScript-first schema validation with static type inference https://zod.dev/ | |||
| 08:57 | A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT https://medium.com/@programmerraja/a-prompt-pattern-catalog-to-enhance-prompt-engineering-with-chatgpt-e06e4325455f | |||
| 08:47 | How LLMs Improve Scenario Planning in Supply Chain Network Design https://medium.com/@lambdascs/how-llms-improve-scenario-planning-in-supply-chain-network-design-a34b28ad4a7c | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803