LLM News and Articles
Thursday, 2024-09-19 | ||||
05:44 | Deploy LLMs in Your Own Infrastructure vs. API Consumption https://atul-yadav7717.medium.com/deploy-llms-in-your-own-infrastructure-vs-api-consumption-cf9603190191 | |||
05:33 | Ban warnings fly as users dare to probe the "thoughts" of OpenAI's latest model https://arstechnica.com/information-technology/2024/09/openai-threatens-bans-for-probing-new-ai-models-reasoning-process/ | |||
05:16 | The History of Poison Making from Household Materials https://medium.com/@andy1729/the-history-of-poison-making-from-household-materials-4e8590be97d9 | |||
04:46 | Qwen 2.5 Models Released: Featuring Qwen2.5, Qwen2.5-Coder, and Qwen2.5-Math with 72B Parameters and 128K Context Support https://www.marktechpost.com/2024/09/18/qwen-2-5-models-released-featuring-qwen2-5-qwen2-5-coder-and-qwen2-5-math-with-72b-parameters-and-128k-context-support/ | |||
04:25 | How to Create a Langchain Tutorial for Beginners in 2023 https://medium.com/@garysvenson09/how-to-create-a-langchain-tutorial-for-beginners-in-2023-d8844ab0a681 | |||
04:02 | I Made a Weekly Newsletter that’s Completely AI Generated https://ryankemmer.medium.com/i-made-a-weekly-newsletter-thats-completely-ai-generated-0234fbaa4715 | |||
04:00 | Prompting, RAG, and Fine Tunning https://medium.com/@850049535/prompting-rag-and-fine-tunning-a8b03416c023 | |||
03:31 | RAG 2.0 by Contextual ai https://medium.com/@850049535/rag-2-0-by-contextual-ai-5c61af1ba7f7 | |||
03:18 | How to Open Assistant Settings for Optimal Use https://medium.com/@asakisakamoto02/how-to-open-assistant-settings-for-optimal-use-59fe39acfa7d | |||
03:07 | Mastering Document Preprocessing for NER with BERT https://medium.com/@mleinbayarea/mastering-document-preprocessing-for-ner-with-bert-a9f54d9a2c72 | |||
03:01 | Üretken Yapay Zeka Rehberi https://medium.com/@anil.guleroglu/%C3%BCretken-yapay-zeka-rehberi-da29eaedca42 | |||
02:20 | Qwen2.5: A Party of Foundation Models! https://medium.com/@jenray1986/qwen2-5-a-party-of-foundation-models-e3921e08c00f | |||
02:16 | How to Add a Subscriber Using the Mailchimp API https://medium.com/@tayloroakley/how-to-add-a-subscriber-using-the-mailchimp-api-b9005f9d5b46 | |||
02:06 | Decoding AI: A Practical Guide to Understanding Token Usage https://medium.com/@vaibhavdubey_74802/decoding-ai-a-practical-guide-to-understanding-token-usage-63ab005ff925 | |||
01:58 | AI Models Can Get It Wrong: Why Comparing Them Could Save Your Business — or Even Lives https://medium.com/@vncmvn/ai-models-can-get-it-wrong-why-comparing-them-could-save-your-business-or-even-lives-b991f41f7fcc | |||
01:45 | Azure GPT-4o Pricing, Benchmarks, and Usage Guide https://medium.com/@getanakin/azure-gpt-4o-pricing-benchmarks-and-usage-guide-e68b9cd805f8 | |||
01:04 | Are Larger Language Models Always Better? The rise of Small Language Models https://medium.com/@fahimabrar0/are-larger-language-models-always-better-the-rise-of-small-language-models-1fa53adcc98a | |||
00:58 | Promptriever: first Zero-Shot Promptable Instruction-Trained Retriever Model https://medium.com/@techsachin/promptriever-first-zero-shot-promptable-instruction-trained-retriever-model-72e9f2eecbb2 | |||
00:34 | Decoding the Encoder, Decoder of Transformers https://medium.com/@karteekmenda93/decoding-the-encoder-decoder-in-transformers-94d2fc98e6c7 | |||
00:25 | How to Use LangChain Tools Effectively for Your Projects https://medium.com/@garysvenson09/how-to-use-langchain-tools-effectively-for-your-projects-8fb2861b1078 | |||
00:08 | Anthropic Claude Golang SDK https://github.com/aitrailblazer/anthropic-claude-golang-sdk | |||
00:05 | FreshLLMs and Dappier: Real-Time Data for Accurate AI Responses https://maddy-a.medium.com/freshllms-and-dappier-real-time-data-for-accurate-ai-responses-9922ffc604cc | |||
00:05 | How to add real-time data to a GPT: FreshLLMs & Dappier https://medium.com/dappier/freshllms-and-dappier-real-time-data-for-accurate-ai-responses-9922ffc604cc | |||
Wednesday, 2024-09-18 | ||||
23:18 | How to Implement One-vs-Rest in Zhihu for Better Results https://medium.com/@asakisakamoto02/how-to-implement-one-vs-rest-in-zhihu-for-better-results-dfc670521471 | |||
22:54 | JavaScript Library to Bypass CORS for LLM APIs Without a Back End https://amanpriyanshu.github.io/API-LLM-Hub/unified-llm-api.js | |||
22:49 | API-LLM-Hub: In-Browser LLM Integration for Static Websites https://amanpriyanshu.github.io/API-LLM-Hub/ | |||
22:17 | Unleashing the Power of LLMs in Your GitHub Pages: Meet API-LLM-Hub https://medium.com/@amanpriyanshusms2001/unleashing-the-power-of-llms-in-your-github-pages-meet-api-llm-hub-e7e0b51bab1f | |||
22:17 | How to Use Application Integration Examples for Success https://medium.com/@tayloroakley/how-to-use-application-integration-examples-for-success-8e0478a7fa07 | |||
22:10 | The Game-Changer in Machine Learning: How Autostopping Saved My Sanity https://medium.com/mr-plan-publication/the-game-changer-in-machine-learning-how-autostopping-saved-my-sanity-28accc44b5ec | |||
21:49 | Copyright Laundering: A New AI Legal Strategy https://medium.com/the-generator/copyright-laundering-a-new-ai-legal-strategy-c9b0bdcbf773 | |||
21:45 | Azure GPT-4 Pricing and Benchmark Review for Large Language Models https://medium.com/@getanakin/azure-gpt-4-pricing-and-benchmark-review-for-large-language-models-7baeb6b5c375 | |||
21:40 | AIs collaborate and get better results via ‘Co-LLM’ developed by MIT researchers https://medium.com/@ravikashbakolia/ais-collaborate-and-get-better-results-via-co-llm-developed-by-mit-researchers-68af9e462505 | |||
21:39 | TAG vs Text2SQL https://medium.com/@visrow/tag-vs-text2sql-96542742e401 | |||
21:23 | Building a Voice-Enabled AI Agent for Text-to-SQL Queries with LangGraph https://medium.com/@mohammed97ashraf/building-a-voice-enabled-ai-agent-for-text-to-sql-queries-with-langgraph-b8d3c32d717e | |||
21:19 | 2024 Independent Study — Week 2 https://medium.com/@lukehenriquez/2024-independent-study-week-2-2e917d5e1efc | |||
21:16 | Why Re-rankers Are So Powerful: A Dive into Bi-encoders, Cross-encoders, and Late Interaction https://medium.com/@rajendharmendra/why-re-rankers-are-so-powerful-a-dive-into-bi-encoders-cross-encoders-and-late-interaction-bfcb6051f2e4 | |||
21:08 | New OpenAI models o1-preview and o1-mini https://medium.com/@thomas.latterner/new-openai-models-o1-preview-and-o1-mini-b1f8b1f2a066 | |||
21:03 | I Explored Retrieval-Augmented Generation — Here’s What I Discovered About Turning Data into… https://pub.aimind.so/i-explored-retrieval-augmented-generation-heres-what-i-discovered-about-turning-data-into-d58966e872b9 | |||
20:25 | How to Implement RAG with LangChain in Simple Steps https://medium.com/@garysvenson09/how-to-implement-rag-with-langchain-in-simple-steps-8067cbaadf8d | |||
19:46 | AI Bites: OpenAI Releases New GPT-4o1 and o1-mini Models https://gcmori.medium.com/ai-bites-openai-releases-new-gpt-4o1-and-o1-mini-models-652607c2829e | |||
19:46 | CDS Researcher Develops Method for Targeted Language Model Updates https://nyudatascience.medium.com/cds-researcher-develops-method-for-targeted-language-model-updates-93d5f5cfa0b7 | |||
19:18 | How to Build a Node.js Server with Supabase Tutorial https://medium.com/@asakisakamoto02/how-to-build-a-node-js-server-with-supabase-tutorial-166f9f98f20e | |||
18:58 | Whitespace Tokenization vs. BPE: A Comparison of TF-IDF and Word2Vec Embeddings https://medium.com/@mobeentariq65/whitespace-tokenization-vs-bpe-a-comparison-of-tf-idf-and-word2vec-embeddings-45e996c70880 | |||
18:58 | T-Mobile to Supply OpenAI with Customer Data to Boost User Experience https://www.wsj.com/tech/ai/t-mobile-to-supply-openai-with-customer-data-to-boost-user-experience-763d0525 | |||
18:49 | Building Q&A LLM Applications Using Retrieval-Augmented Generation (RAG) for Local Document… https://medium.com/@senol.isci/building-q-a-llm-applications-using-retrieval-augmented-generation-rag-for-local-document-7e51203c01ff | |||
18:27 | AI-Enhanced Data Pipelines: A New Era of Efficiency and Insight https://hmix13.medium.com/ai-enhanced-data-pipelines-a-new-era-of-efficiency-and-insight-c7157a6632ac | |||
18:26 | CrewAI: um framework voltado para a integração e automação de agentes de inteligência artificial… https://medium.com/@michel.macario/crewai-um-framework-voltado-para-a-integra%C3%A7%C3%A3o-e-automa%C3%A7%C3%A3o-de-agentes-de-intelig%C3%AAncia-artificial-3bff452cb450 | |||
18:26 | Exploring White-Space + TF-IDF vs. https://medium.com/@mfarooq5066/exploring-white-space-tf-idf-vs-e181a34f7929 | |||
18:22 | OpenAI Threatening to Ban Users for Asking Strawberry About Its Reasoning https://futurism.com/the-byte/openai-ban-strawberry-reasoning | |||
18:19 | Understanding LLMOps - Efficiently Deploying Large Language Models in Production https://medium.com/@srivastava.anubhav/understanding-llmops-efficiently-deploying-large-language-models-in-production-e246ad9b44d2 | |||
18:17 | How to Use Automated Provisioning for Efficient Workflows https://medium.com/@tayloroakley/how-to-use-automated-provisioning-for-efficient-workflows-060e9456db2a | |||
17:46 | AWS Transcribe Pricing: Benchmarks, Use Cases, and Review https://medium.com/@getanakin/aws-transcribe-pricing-benchmarks-use-cases-and-review-825cc4aca19c | |||
17:04 | OpenAI-o1 and the Long Chain-of-Thought https://blog.gopenai.com/openai-o1-the-future-of-ai-that-thinks-before-it-speaks-40644c611c40 | |||
17:02 | Best Practices for Scalable GenAI Solutions https://medium.com/the-business-of-ai/best-practices-for-scalable-genai-solutions-b8cddd79f260 | |||
16:55 | Why I’m Betting on Hybrid Search Over RAG and Vector Search for the Future of Information Retrieval https://ai.plainenglish.io/why-im-betting-on-hybrid-search-over-rag-and-vector-search-for-the-future-of-information-retrieval-daa6763c1260 | |||
16:42 | Llama 3.1 Omni Model https://github.com/ictnlp/LLaMA-Omni | |||
16:25 | How to Get Started with LangChain in Python: A Tutorial https://medium.com/@garysvenson09/how-to-get-started-with-langchain-in-python-a-tutorial-9dfedff45bda | |||
16:01 | Writer Researchers Introduce Writing in the Margins (WiM): A New Inference Pattern for Large Language Models Designed to Optimize the Handling of Long Input Sequences in Retrieval-Oriented Tasks https://www.marktechpost.com/2024/09/18/writer-researchers-introduce-writing-in-the-margins-wim-a-new-inference-pattern-for-large-language-models-designed-to-optimize-the-handling-of-long-input-sequences-in-retrieval-oriented-tasks/ | |||
15:44 | Optimizing LLM Performance: The Impact of Data Quality and Model Size https://medium.com/@souhailguennouni/optimizing-llm-performance-the-impact-of-data-quality-and-model-size-95b988cdd4ae | |||
15:27 | Introduzione a LangChain: Un Nuovo Approccio alla Gestione dei Modelli Linguistici https://medium.com/@pasquale.verta/introduzione-a-langchain-un-nuovo-approccio-alla-gestione-dei-modelli-linguistici-4980e7601cd1 | |||
15:27 | The Holy Grail of AI: When Machines Crack the P vs NP Enigma https://medium.com/@mourad.ghafiri/the-holy-grail-of-ai-when-machines-crack-the-p-vs-np-enigma-ae8018a5143e | |||
15:23 | Show HN: Everyday's ArXiv Papers Explained at Your Level https://www.everydayacademic.com/ | |||
15:20 | LLM Apps in Minutes with Langchain! https://medium.com/@pashamsathwikreddy/llm-apps-in-minutes-with-langchain-4fd2c4bd831a | |||
15:18 | How to Use useParams in Next.js for Dynamic Routing https://medium.com/@asakisakamoto02/how-to-use-useparams-in-next-js-for-dynamic-routing-1b26ddde128c | |||
15:17 | ML: Bias and Variance tradeoff (explained) https://medium.com/@thomas.zilliox/ml-bias-and-variance-explained-e43f92cdb2a3 | |||
15:12 | The Evolution of Large Language Models: From GPT to Multimodal Mastery https://medium.com/@avijitsur_8327/the-evolution-of-large-language-models-from-gpt-to-multimodal-mastery-2e38b23cf1a3 | |||
15:07 | Over Refuse? Identifying Exaggerated Safety Behaviours in LLMs with XSTest https://medium.com/@tsunhanchiang/over-refuse-identifying-exaggerated-safety-behaviours-in-llms-with-xstest-51e0244abc8f | |||
15:01 | Unleashing Enterprise Productivity: How to Revolutionize Your Workflow with Copilot for M365 https://medium.com/@georgije.stanisic00/unleashing-enterprise-productivity-how-to-revolutionize-your-workflow-with-copilot-for-m365-796affce132d | |||
14:52 | Why I Chose Open-Source LLMs Over Proprietary Models — A Deep Dive Into the Best Options https://ai.gopubby.com/why-i-chose-open-source-llms-over-proprietary-models-a-deep-dive-into-the-best-options-6673fe5a73b0 | |||
14:49 | OpenAI Eleva a IA: Raciocínio Próximo ao Humano https://medium.com/@canal.iaeeu/openai-eleva-a-ia-racioc%C3%ADnio-pr%C3%B3ximo-ao-humano-98c08e7870d7 | |||
14:17 | How to Set Up a Redis Cluster in Docker Easily https://medium.com/@tayloroakley/how-to-set-up-a-redis-cluster-in-docker-easily-7b5c240d9446 | |||
14:05 | The Phenomenology of Machine: A Route for the Sentience of OpenAI-O1 [pdf] https://mypapers.nyc3.cdn.digitaloceanspaces.com/the_phenomenology_of_machine.pdf | |||
13:46 | AWS Speech to Text Pricing: A Comprehensive Review and Benchmark https://medium.com/@getanakin/aws-speech-to-text-pricing-a-comprehensive-review-and-benchmark-d24c2608a855 | |||
13:39 | Saving a Million Dollars on AWS with ChatGPT O1 https://pinata.cloud/blog/saving-a-million-dollars-on-aws-with-chatgpt-o1/ | |||
13:21 | Evaluating LLMs : All about LLM Benchmarks , Part 2-Years 2022–24 https://medium.com/@saurad44/evaluating-llms-all-about-llm-benchmarks-part-2-years-2022-24-cf11c448b544 | |||
12:40 | Which Ops is Right for Your AI? AIOps, MLOps, and LLMOps Compared https://generativeai.pub/which-ops-is-right-for-your-ai-aiops-mlops-and-llmops-compared-80f5044f050c | |||
12:32 | Small Language Models (SLMs) — Why Going Small is the Big Thing for AI https://arthirajendran.medium.com/small-language-models-slms-why-going-small-is-the-big-thing-for-ai-026e42b690b9 | |||
12:25 | How to Install LangChain Using PyPI: A Step-by-Step Guide https://medium.com/@garysvenson09/how-to-install-langchain-using-pypi-a-step-by-step-guide-c75f343e2b0e | |||
12:22 | Small Models, Big Dreams: A Novice’s Misadventures in Tree of Thoughts Implementation https://medium.com/mr-plan-publication/small-models-big-dreams-a-novices-misadventures-in-tree-of-thoughts-implementation-3988cac202e3 | |||
12:14 | Gilbane Advisor: o1 paradigm?, abductive reasoning, ARC-AGI https://fgilbane.medium.com/gilbane-advisor-o1-paradigm-abductive-reasoning-arc-agi-a067ee2ae0c9 | |||
11:42 | Yapay Zeka Bülteni : 1. Büyük Dil Modellerinin Tarihi https://medium.com/@alperaydyn/yapay-zeka-b%C3%BClteni-1-b%C3%BCy%C3%BCk-dil-modellerinin-tarihi-02cbd296a489 | |||
11:18 | How to Use Next.js Performance Analyzer Library for NPM https://medium.com/@asakisakamoto02/how-to-use-next-js-performance-analyzer-library-for-npm-fb0213a4abef | |||
11:14 | How to convert a PDF into JSON (Properly) https://medium.com/@tinyidp/how-to-convert-a-pdf-into-json-properly-c1274bd59da1 | |||
11:13 | How To Enhance LLM Evaluation For Responsible AI https://medium.com/toloka/how-to-enhance-llm-evaluation-for-responsible-ai-461efb603c1f | |||
11:00 | Advanced RAG: RAPTOR — Recursive Abstractive Processing for Tree-Organized Retrieval https://medium.com/disassembly/advanced-rag-raptor-recursive-abstractive-processing-for-tree-organized-retrieval-308e1ca5a82f | |||
10:16 | How to Find the Best Workato Alternatives for Automation https://medium.com/@tayloroakley/how-to-find-the-best-workato-alternatives-for-automation-acfd451152cb | |||
09:45 | AWS Bedrock Pricing Review: Large Language Models & Usage https://medium.com/@getanakin/aws-bedrock-pricing-review-large-language-models-usage-628d01f2dda3 | |||
09:44 | 10 Ways to Lower LLM Inference Costs https://medium.com/@narenderbeniwal1234/10-ways-to-lower-llm-inference-costs-0579feb219ce | |||
09:26 | Enhanced Contextual Insights: RAG-Based GPT Integration for Question Answering with BBC News Data https://medium.com/@ayesha.rafiq229/enhanced-contextual-insights-rag-based-gpt-integration-for-question-answering-with-bbc-news-data-9c52c339962b | |||
08:52 | 1Hub.ai: The Future of AI Services on One Platform https://medium.com/@1HubAI/1hub-ai-the-future-of-ai-services-on-one-platform-c1980c5f46d4 | |||
08:41 | The Art of Prompting. https://medium.com/@aadityakumar26082004/the-art-of-prompting-f68acb2724d3 | |||
08:40 | Comparing AI Model Performance in Genetic Diagnosis: A Case Study https://medium.com/@muwenbo.prc/comparing-ai-model-performance-in-genetic-diagnosis-a-case-study-25d114635a08 | |||
08:29 | Top 10 LLM Interview Questions https://medium.com/@narenderbeniwal1234/top-10-llm-interview-questions-72d0ab495829 | |||
08:25 | How to Provide Effective Examples in LangChain Prompts https://medium.com/@garysvenson09/how-to-provide-effective-examples-in-langchain-prompts-59b708e4cf70 | |||
07:58 | Hackers Find Ways to “Jailbreak” Powerful AI LLMs, Raising Security Concerns https://medium.com/@mir.global.academy/hackers-find-ways-to-jailbreak-powerful-ai-llms-raising-security-concerns-f23d58f6d3f1 | |||
07:32 | Business Salesforce CEO Marc Benioff says he uses ChatGPT as a therapist https://sfstandard.com/2024/09/17/marc-benioff-jensen-huang-dreamforce/ | |||
07:28 | How Large Language Models are Configured? https://medium.com/@aadityakumar26082004/how-large-language-models-are-configured-de4a9ddb7fb6 | |||
07:20 | Comparing Different Large Language Models (LLM) https://medium.com/@jaggarwal.ritika/comparing-different-large-language-models-llm-6ee90384de85 | |||
07:18 | How to Use SVG Images in Next.js for Enhanced Performance https://medium.com/@asakisakamoto02/how-to-use-svg-images-in-next-js-for-enhanced-performance-58f49cd0eb28 | |||
06:54 | RAG: Unleashing the Future of AI-Powered Recommendation Systems. https://medium.com/@ai-mayurpatil/rag-unleashing-the-future-of-ai-powered-recommendation-systems-5d36b667023f |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803