LLM News and Articles
Friday, 2024-10-11 | ||||
21:58 | Approach to Routing in a Multi-Agent Platform https://medium.com/@yhoso/approach-to-routing-in-a-multi-agent-platform-1ea4d50b8da0 | |||
21:47 | Why did LLMs stand out among the many AI fields, and what will be the next? https://medium.com/@Woni0427/why-did-llms-stand-out-among-the-many-ai-fields-and-what-will-be-the-next-8029c0ffb04a | |||
21:34 | 11-Oct-2024: Unstructured Data Podcast Report https://medium.com/@tspann/computer11-oct-2024-unstructured-data-podcast-report-6d836a5f28ba | |||
21:32 | Enhance Your Projects with Llama 3.1 API Integration https://medium.com/@marketing_novita.ai/enhance-your-projects-with-llama-3-1-api-integration-18b0bfa6a766 | |||
21:02 | An Introduction to Asynchronous Programming: The Key to Efficient Generative AI Applications https://vinayak-arannil.medium.com/an-introduction-to-asynchronous-programming-the-key-to-efficient-generative-ai-applications-871e76d1d02c | |||
21:01 | Understanding the Math Behind LLM Models and Fine-Tuning Them https://medium.com/@anjalitanikella/understanding-the-math-behind-llm-models-and-fine-tuning-them-ee4ca222823f | |||
20:51 | Optima: framework for optimizing Multi-Agents LLMs via Iterative Training https://medium.com/@techsachin/optima-framework-for-optimizing-multi-agents-llms-via-iterative-training-c4308b71343f | |||
20:32 | A Mixed-Methods Approach to Offline Evaluation of News Recommender Systems https://towardsdatascience.com/a-mixed-methods-approach-to-offline-evaluation-of-news-recommender-systems-7dc7e9f0b501 | |||
20:28 | Topic Alignment for NLP Recommender Systems https://towardsdatascience.com/topic-alignment-for-nlp-recommender-systems-b35ef2902c1a | |||
19:47 | Utilizando ResponseSchema e StructuredOutputParser no LangChain para Obter Resultados Estruturados https://medium.com/@joaogabriel1995/utilizando-responseschema-e-structuredoutputparser-no-langchain-para-obter-resultados-estruturados-43d68e5d0f0e | |||
19:34 | Securing FastAPI Applications: Protecting LLM and OpenAI Endpoints with JWT Authentication https://pub.aimind.so/securing-fastapi-applications-protecting-llm-and-openai-endpoints-with-jwt-authentication-257ea27f60a1 | |||
19:13 | Why Metadata is so Crucial for Text-to-SQL Applications https://medium.com/basejump-ai/why-metadata-is-so-crucial-for-text-to-sql-applications-09c5b2563483 | |||
18:51 | Limitations of Basic RAG and the Need for More Advanced Approaches https://medium.com/@adarshb3/limitations-of-basic-rag-and-the-need-for-more-advanced-approaches-448cc4b6b598 | |||
18:42 | LLM Agent SOS: Best Practices and Considerations for Implementation https://rajatnigam89.medium.com/llm-agent-sos-best-practices-and-considerations-for-implementation-90bda9583cba | |||
18:37 | Creating A Cold Outreach AI Agent using Python, AWS SES, Google Search & Claude AI — Part 2 https://python.plainenglish.io/creating-a-cold-outreach-ai-agent-using-python-aws-ses-google-search-claude-ai-part-2-8932f7555f54 | |||
18:35 | WizMuse: Your Powerful AI Assistant for Web Browsing https://medium.com/chinkan-ai/wizmuse-your-powerful-ai-assistant-for-web-browsing-3427e95aabf5 | |||
18:31 | LLM-powered Social Robots for Mediating Health Information https://medium.com/acm-cscw/llm-powered-social-robots-for-mediating-health-information-6251f2a309b5 | |||
18:24 | Building AI-Powered Applications with AWS Bedrock: A Step-by-Step Guide https://medium.com/@athergenius777/building-ai-powered-applications-with-aws-bedrock-a-step-by-step-guide-a1c60960220a | |||
18:21 | Basic Information from codellama:13b https://medium.com/@angelo.jusay/basic-information-from-codellama-13b-541e2c046192 | |||
17:57 | From BERT to BART: A Simplified Introduction to Transformer-Based NLP Models https://python.plainenglish.io/from-bert-to-bart-a-simplified-introduction-to-transformer-based-nlp-models-97072bff57f2 | |||
17:23 | 🔋 Fixing AI's Energy Consumption https://www.llmwatch.com/p/fixing-ais-energy-consumption | |||
17:12 | Emergent Abilities in Large Language Models (LLMs) https://medium.com/@bragadeeshs/emergent-abilities-in-large-language-models-llms-53bd140ae4cf | |||
17:10 | Reinforcement Learning Fine-Tuning : The Future of Adapting Language Models https://medium.com/@anjalitanikella/reinforcement-learning-fine-tuning-the-future-of-adapting-language-models-b26406934ce6 | |||
17:09 | AI inshorts 3 — Pixtral https://medium.com/@akshithakumbam1/ai-inshorts-3-pixtral-c7b02867066e | |||
17:01 | Evaluating and tracing your AI App with Prompt Flow https://medium.com/microsoftazure/evaluating-and-tracing-your-ai-app-with-prompt-flow-9d8bc181ad87 | |||
16:46 | Lm.rs: Minimal CPU LLM inference in Rust with no dependency https://github.com/samuel-vitorino/lm.rs | |||
16:43 | Revolutionizing Mental Health Support: Building WellBot with AI, RAG, and Langchain https://medium.com/@athergenius777/revolutionizing-mental-health-support-building-wellbot-with-ai-rag-and-langchain-047caca5981f | |||
16:37 | Test https://medium.com/@stevesajanjacobkallunkal04/test-a8ac99dbccb9 | |||
15:57 | Snowflake Cortex AI: Smart activity planning https://medium.com/snowflake/snowflake-cortex-ai-smart-activity-planning-d6e5acf5b672 | |||
15:44 | Introducing GAP: A paradigm shift in decentralized AI development. https://medium.com/@fractionai/introducing-gap-a-paradigm-shift-in-decentralized-ai-development-1a706afe5d1f | |||
15:43 | CoverMe: Your Ultimate Tool for Personalized Cover Letters and LinkedIn Messages https://nkumarvishnu5.medium.com/coverme-your-ultimate-tool-for-personalized-cover-letters-and-linkedin-messages-f9edcdfaf219 | |||
15:18 | Machine Unlearning - An Overview https://medium.com/@bourichahichem/machine-unlearning-an-overview-a548071f86e1 | |||
15:05 | Trying the waters before jumping deep … Actionable steps on how to validate and test your GenAI… https://medium.com/@lucia.larise.stavarache/trying-the-waters-before-jumping-deep-actionable-steps-on-how-to-validate-and-test-your-genai-ff950eea1c6d | |||
14:56 | Our Evolutionary Journey of Building the LLM-powered Data Agent https://medium.com/@meghasaini/our-evolutionary-journey-of-building-the-llm-powered-data-agent-e6109b943923 | |||
14:51 | Pioneers of AI spreading misinformation: A race to become the leading doomsday prophet of AI https://medium.com/@don-lim/pioneers-of-ai-spreading-misinformation-a-race-to-become-the-leading-doomsday-prophet-of-ai-b067eb7d87ef | |||
14:25 | Build custom OCRs with this No-Code tool https://medium.com/@tinyidp/build-custom-ocrs-with-this-no-code-tool-23c4ea27ef84 | |||
14:06 | Don’t feed meat to the model https://medium.com/@longolius/dont-feed-meat-to-the-model-570bdd859159 | |||
13:01 | The Rise of Vertical LLMs: Revolutionizing Industry-Specific AI https://medium.com/@varun4guitar/the-rise-of-vertical-llms-revolutionizing-industry-specific-ai-eb48ebf23d4f | |||
12:45 | Is selling LangGraph templates the new meta? https://medium.com/@filipkny/is-selling-langgraph-templates-the-new-meta-744798c93848 | |||
12:41 | Unlock the Power of RAG Pipelines: Cloud-Based PDF Storage and Vector Search Made Simple https://tarunaga.medium.com/unlock-the-power-of-rag-pipelines-cloud-based-pdf-storage-and-vector-search-made-simple-e4428591720e | |||
12:20 | Fast api cookbook for llms and embedding model! https://medium.com/@krishnaaryaveer/fast-api-cookbook-for-llms-and-embedding-model-1862f0ec58e4 | |||
12:16 | Day 3 of — 7 Days of agent framework anatomy from first-principles https://medium.com/@mrsirsh/day-3-of-7-days-of-agent-framework-anatomy-from-first-principles-3252222ac025 | |||
12:16 | How to Run Your Own Local LLM (Updated for 2024) https://thomascherickal.medium.com/how-to-run-your-own-local-llm-updated-for-2024-ca841ae4e564 | |||
11:43 | ArXiv Data Map: a map of papers on ArXiv https://lmcinnes.github.io/datamapplot_examples/arXiv/ | |||
11:41 | Moderation Classifier: LLamaGuard Zero-Shot Learning https://medium.com/neural-engineer/moderation-classifier-llamaguard-zero-shot-learning-dddabbbcb00c | |||
11:11 | Debunking the Myths of Artificial Intelligence (AI) https://medium.com/@don-lim/debunking-the-myths-of-artificial-intelligence-ai-20d870b78e76 | |||
11:07 | Simplifying Neural Networks: Batch and Layer Normalization for NLP, Quantization, and Pruning for… https://python.plainenglish.io/simplifying-neural-networks-batch-and-layer-normalization-for-nlp-quantization-and-pruning-for-37fd71c4cfdb | |||
10:38 | RAG on steroids: Self-RAG https://ai.gopubby.com/rag-on-steroids-self-rag-69505f9d8238 | |||
10:34 | OpenAI vs. Claude: Comparison of Prompt Caching in GPT-4o and Claude 3.5 https://medium.com/@sandeepkumar998855/openai-vs-claude-comparison-of-prompt-caching-in-gpt-4o-and-claude-3-5-2e37a85e0c42 | |||
10:21 | SQLite Queue for LLM Calls https://twitter.com/HamelHusain/status/1844527172293362070 | |||
09:58 | Accelerating Language Model Inference with Mixture of Attentions: Speculative Decoding 2.0 https://medium.com/@haitham.bouammar71/accelerating-language-model-inference-with-mixture-of-attentions-speculative-decoding-2-0-126afbbed728 | |||
09:38 | Unsupervised Fine-Tuning of Large Language Models: A Step-by-Step Guide https://medium.com/@pdrudra.121/unsupervised-fine-tuning-of-large-language-models-a-step-by-step-guide-494916225d8e | |||
09:34 | Contextual Search Engine for Molecular Drug Discover using Snowflakes https://usharengaraju.medium.com/contextual-search-engine-for-molecular-drug-discover-using-snowflakes-a3dafa41ae85 | |||
09:33 | Ensuring Safety in Large Language Models: Approaches and Challenges https://blog.aim-intelligence.com/ensuring-safety-in-large-language-models-approaches-and-challenges-3444aa021b23 | |||
09:04 | Automating LLM Jailbreaking: Advanced Mutation Strategies and the Rationalize Technique https://blog.aim-intelligence.com/automating-llm-jailbreaking-advanced-mutation-strategies-and-the-rationalize-technique-7cd751de5087 | |||
08:27 | Step-by-step guide on how to build LLM automation script using JavaScript with Node.js https://medium.com/@praveencs87/step-by-step-guide-on-how-to-build-llm-automation-script-using-javascript-with-node-js-3a49507ec879 | |||
08:21 | Practical use cases of large language models (LLMs) in digital marketing https://medium.com/@praveencs87/practical-use-cases-of-large-language-models-llms-in-digital-marketing-2a4e471043b7 | |||
08:02 | Unlocking the Power of Function Calling with LLMs https://medium.com/@hopsworks_ai/unlocking-the-power-of-function-calling-with-llms-d6256a3026d6 | |||
07:29 | Reflection Llama 3.1: A Deep Dive https://medium.com/@researchgraph/reflection-llama-3-1-a-deep-dive-3122b743cf32 | |||
07:12 | AI Conversation: 100 using four 9's https://sukuya.medium.com/ai-conversation-100-using-four-9s-e24a67118966 | |||
06:52 | Hello, K.AI — How I Trained a Chatbot of Myself Without Coding https://kai-waehner.medium.com/hello-k-ai-how-i-trained-a-chatbot-of-myself-without-coding-748d36b281f9 | |||
06:40 | What is LM Studio? https://medium.com/@researchgraph/what-is-lm-studio-ca2e60766364 | |||
06:36 | Unlocking the Power of ChatGPT’s Advanced Voice Mode https://medium.com/@researchgraph/unlocking-the-power-of-chatgpts-advanced-voice-mode-69467a559783 | |||
06:23 | [Evening Read] Malla: Demystifying Real-World LLM Integrated Malicious Services https://nabeelxy.medium.com/evening-read-malla-demystifying-real-world-llm-integrated-malicious-services-7bc3177beecd | |||
06:17 | Ready to Say Goodbye to Data Chaos? Discover Metadata Filtering for AI Agents on Epsilla Cloud https://blog.epsilla.com/ready-to-say-goodbye-to-data-chaos-discover-metadata-filtering-for-ai-agents-on-epsilla-cloud-62f251640dcf | |||
06:02 | OpenAGI: Introducing Long-Term Memory https://medium.aiplanet.com/openagi-introducing-long-term-memory-eeb956293c4d | |||
06:00 | RAG vs. Long-Context LLMs — Who is winner ? https://generativeai.pub/rag-vs-long-context-llms-who-is-winner-87e9458bad62 | |||
05:37 | JudgeIt: Automated Evaluation of GenAI with ease of GUI https://medium.com/towards-generative-ai/judgeit-automated-evaluation-of-genai-with-ease-of-gui-b98f4213a8dc | |||
05:29 | AI Will Kill Us All https://medium.com/@marrouchi.mohamed/ai-will-kill-us-all-9dc90740b176 | |||
03:48 | The Real Impact of Generative AI: Beyond the Hype Cycle https://agustinus-nalwan.medium.com/the-real-impact-of-generative-ai-beyond-the-hype-cycle-4ac17eab4f99 | |||
03:42 | How does AI Find Stuff? https://theaimagicmemo.medium.com/how-does-ai-find-stuff-a66163c091d1 | |||
01:58 | Finetuning Phi3-mini-4k-instruct on custom Data + CPU Inference https://medium.com/@koby.choy/finetuning-phi3-mini-4k-instruct-on-custom-data-cpu-inference-cc07db77945c | |||
01:11 | ASPIRE: A New Era of Confidence in AI Decision-Making https://medium.com/@teendifferent/aspire-a-new-era-of-confidence-in-ai-decision-making-38be57d359b7 | |||
00:36 | How Data3 is Unlocking Exclusive Data to Train AI https://arcanumcapital.medium.com/how-data3-is-unlocking-exclusive-data-to-train-ai-0fded0bf464c | |||
00:15 | Show HN: Airgapped Offline RAG – Run LLMs Locally with Llama, Mistral, & Gemini https://github.com/vincentkoc/airgapped-offfline-rag | |||
00:12 | Enhancing LLM Instruction following with DECOMPOSE, CRITIQUE, AND REFINE (DECRIM) self-correction… https://medium.com/@techsachin/enhancing-llm-instruction-following-with-decompose-critique-and-refine-decrim-self-correction-863e32182dc8 | |||
00:12 | Google AI Introduces Tx-LLM: A Large Language Model (LLM) Fine-Tuned from PaLM-2 to Predict Properties of Many Entities that are Relevant to Therapeutic Development https://www.marktechpost.com/2024/10/10/tx-llm-a-large-language-model-llm-fine-tuned-from-palm-2-to-predict-properties-of-many-entities-that-are-relevant-to-therapeutic-development/ | |||
Thursday, 2024-10-10 | ||||
23:52 | Manage your local language models https://medium.com/@manyi.yim/manage-your-local-language-models-569590c263f0 | |||
23:50 | Search: Beyond the Tannhäuser Gate and into the Data Stream Maelstrom https://medium.com/@julian.burns50/beyond-the-tannh%C3%A4user-gate-and-into-the-data-stream-maelstrom-981393a09089 | |||
23:18 | Important LLMs Papers for the Week from 30/09 to 06/10 https://medium.com/to-data-beyond/important-llms-papers-for-the-week-from-30-09-to-06-10-8b568a5c6270 | |||
23:06 | LLM Hallucinations https://medium.com/@esasyed/llm-hallucinations-80bc6f69a82f | |||
22:42 | No Single LLM Can Be Trusted in Isolation https://medium.com/@punkpeye/no-single-llm-can-be-trusted-in-isolation-ce52362ce2ce | |||
21:41 | Mastering Langchain: The Ultimate Beginner’s Guide to Supercharging Your LLM Projects https://medium.com/@athergenius777/mastering-langchain-the-ultimate-beginners-guide-to-supercharging-your-llm-projects-f67bbcee7e91 | |||
20:51 | Extracting financial disclosure and police reports with OpenAI Structured Output https://gist.github.com/dannguyen/faaa56cebf30ad51108a9fe4f8db36d8 | |||
20:11 | Transforming code development with LLMs https://pankajkgarg.medium.com/transforming-code-development-with-llms-e9ec7a0560e7 | |||
20:10 | Maritime: Commerciality is Tied to Supply Chain Transparency https://medium.com/shipping-intel/maritime-commerciality-is-tied-to-supply-chain-transparency-3a09ef56d5ba | |||
20:01 | 3 Emerging Trends in Data Engineering https://medium.com/@jagadeshjamjalanarayanan/3-emerging-trends-in-data-engineering-3334af711c9f | |||
19:36 | 12 Kaggle Notebook to Master Prompt Engineering https://levelup.gitconnected.com/12-kaggle-notebook-to-master-prompt-engineering-1dc8ce421aa9 | |||
19:27 | The Ultimate Guide to Crafting Better Prompts for Large Language Models (LLMs) https://medium.com/@tomskiecke/the-ultimate-guide-to-crafting-better-prompts-for-large-language-models-llms-7cdd26e27e5b | |||
19:19 | Harvard has a problem // not only Harvard, LLMs hallucinations https://sbagency.medium.com/harvard-has-a-problem-not-only-harvard-llms-hallucinations-39a0f925da18 | |||
19:18 | On the Future of Humanity and the Rights of Artificial Intelligence https://medium.com/@ayushyadav173/on-the-future-of-humanity-and-the-rights-of-artificial-intelligence-65c3a87af427 | |||
19:04 | Key Metrics for Optimizing LLM Inference Performance https://medium.com/athina-ai/key-metrics-for-optimizing-llm-inference-performance-56e81fc03844 | |||
19:04 | Squiggle: One line code change to add insights to the OpenAI Realtime API https://www.squiggle.ai/introduction | |||
18:41 | RAG Pipeline https://medium.com/@aditiagrawal267/rag-pipeline-c021c810914e | |||
18:15 | Automating the Back Office: Enhancing Efficiency and Experience at Startups https://medium.com/@Vectara/automating-the-back-office-enhancing-efficiency-and-experience-at-startups-4c0ea24d5bf0 | |||
18:12 | Why I Joined Vectara: Catching the Generative AI Rocket Ship https://medium.com/@Vectara/why-i-joined-vectara-catching-the-generative-ai-rocket-ship-83b3a223c1dc | |||
18:01 | Smaller, Faster, Smarter: The Power of Model Distillation https://pub.towardsai.net/smaller-faster-smarter-the-power-of-model-distillation-d002662308c7 | |||
18:00 | Is Google’s NotebookLM Going to Disrupt the Podcasting Industry? https://towardsdatascience.com/is-googles-notebooklm-going-to-disrupt-the-podcasting-industry-ea8e1ec7f431 | |||
17:58 | Practical Introduction to LLM tools in Lang chain. https://medium.com/@anubhavm48/practical-introduction-to-llm-tools-in-lang-chain-bb6b8b42d8b6 | |||
17:00 | High-Throughput Low-Latency LLM Serving with MLCEngine https://blog.mlc.ai/2024/10/10/optimizing-and-characterizing-high-throughput-low-latency-llm-inference |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803