LLM News and Articles
Tuesday, 2024-09-03 | ||||
07:31 | Revolutionizing Real Estate: How LLMs and API Integration Are Shaping the Future of Property… https://medium.com/@m.aghababaie/revolutionizing-real-estate-how-llms-and-api-integration-are-shaping-the-future-of-property-3168d1ad9dd8 | |||
07:26 | How Far Can You Automate Equity Research Report Using AI? https://medium.com/@ganeshshankar_92476/how-far-can-you-automate-equity-research-report-using-ai-6cfc408c7eb8 | |||
06:54 | Rama The Llama Launches Ollama https://medium.com/@hananke0/rama-the-llama-launches-ollama-9264404a472d | |||
06:42 | Automating Customer Service and Support with AI Magic https://dirk-schmidt.medium.com/automating-customer-service-and-support-with-ai-magic-f2315456c6be | |||
06:12 | LLM and NLP: How These Technologies Help To Reduce Business Costs https://medium.com/@ossystem9/llm-and-nlp-how-these-technologies-help-to-reduce-business-costs-21bceaf84bd9 | |||
05:42 | Understand 30 pluss LLMs Business Use Cases in 5 minutes Subscribe ❤️ https://manralai.medium.com/understand-30-pluss-llms-business-use-cases-in-5-minutes-subscribe-%EF%B8%8F-494449cecf6a | |||
05:26 | Smaller, Weaker, yet Better: Training LLM Reasoners via Compute-Optimal Sampling https://arxiv.org/abs/2408.16737 | |||
05:25 | Build generative AI applications in Go using Amazon Titan Text Premier model https://itnext.io/build-generative-ai-applications-in-go-using-amazon-titan-text-premier-model-ea508a8106f3 | |||
05:21 | ReMamba: Enhancing Long-Sequence Modeling with a 3.2-Point Boost on LongBench and 1.6-Point Improvement on L-Eval Benchmarks https://www.marktechpost.com/2024/09/02/remamba-enhancing-long-sequence-modeling-with-a-3-2-point-boost-on-longbench-and-1-6-point-improvement-on-l-eval-benchmarks/ | |||
05:20 | Building a Language Translation API with Langserve, FastAPI, and LangChain https://aadhil-imam.medium.com/building-a-language-translation-api-with-langserve-fastapi-and-langchain-d4dfd638af39 | |||
04:54 | Building An Extract Transform And Load Pipeline (ETL) For Neo4j GraphRAG Application | Part 2 https://medium.com/@princekrampah/building-an-extract-transform-and-load-pipeline-etl-for-neo4j-graphrag-application-part-2-123be950946e | |||
04:54 | Building An Extract Transform And Load Pipeline (ETL) For Neo4j GraphRAG Application | Part 2 https://ai.gopubby.com/building-an-extract-transform-and-load-pipeline-etl-for-neo4j-graphrag-application-part-2-123be950946e | |||
04:51 | How Retrieval-Augmented Generation (RAG) Works https://medium.com/@punya8147_26846/how-retrieval-augmented-generation-rag-works-928c2d9ccbce | |||
04:19 | Why Can’t LLMs Like ChatGPT Accurately Determine Whether 9.11 or 9.9 is Larger? https://medium.com/mr-plan-publication/why-cant-llms-like-chatgpt-accurately-determine-whether-9-11-or-9-9-is-larger-19ce0879b1b2 | |||
04:14 | Enhancing Retrieval Augmented Generation with Two-Stage Retrieval, FlashRank, and Query Expansion https://medium.com/@sherinegeorge21/enhancing-retrieval-augmented-generation-with-two-stage-retrieval-flashrank-and-query-expansion-ec4089d85e1b | |||
03:42 | Red-teaming your LLM with ALERT and LlamaCPP https://medium.com/pythoneers/red-teaming-your-llm-with-alert-and-llamacpp-4519a3e4cfaf | |||
02:26 | Under the Hood of Llama 3.1 70B Distributed Inference https://whatdhack.medium.com/under-the-hood-of-llama-3-1-70b-distributed-inference-8b3c03886f22 | |||
02:22 | What is LangChain and its Alternatives? https://medium.com/@jimwang3589/what-is-langchain-and-its-alternatives-c5f8ab749a5b | |||
00:29 | Leveraging LLM Power: Integrating Azure OpenAI with Custom Tools https://medium.com/@anupghogare/leveraging-llm-power-integrating-azure-openai-with-custom-tools-adb88065498f | |||
Monday, 2024-09-02 | ||||
23:49 | LLM by Examples: Inference with TinyLlama 1.1B https://medium.com/@mb20261/llm-by-examples-inference-with-tinyllama-1-1b-4efe083bfc93 | |||
23:48 | LLM by Examples: Fine Tunng and Quantization with TinyLlama 1.1B https://medium.com/@mb20261/llm-by-examples-fine-tunng-and-quantization-with-tinyllama-1-1b-00caaf58d061 | |||
23:47 | Updates on VLSTLLM Technology for Generative AI https://generativeai.pub/updates-on-vlstllm-technology-for-generative-ai-762baf9d79fe | |||
22:59 | Policy: Generative AI (e.g., ChatGPT) is banned https://meta.stackoverflow.com/questions/421831/policy-generative-ai-e-g-chatgpt-is-banned | |||
22:54 | Anthropic injecting prompt into API requests https://twitter.com/jpohhhh/status/1830737983495983614 | |||
22:37 | LLMs as Bridges Reformulating Grounded Multimodal Named Entity Recognition https://medium.com/@EleventhHourEnthusiast/llms-as-bridges-reformulating-grounded-multimodal-named-entity-recognition-9bbf3aa4a43a | |||
22:28 | Exploring the Landscape of Language Model Fine-Tuning Datasets https://medium.com/@mb20261/exploring-the-landscape-of-language-model-fine-tuning-datasets-3d67fea79e88 | |||
22:22 | Building a Smart Semantic Search App for Documents Query: A Step-by-Step Guide https://monzurularashiut.medium.com/building-a-smart-semantic-search-app-for-documents-query-a-step-by-step-guide-524937cf90c6 | |||
22:17 | Using Q-LORA To Embed a Personality into LLAMA 3.1 https://medium.com/@coldstart_coder/using-q-lora-to-embed-a-personality-into-llama-3-1-95f8cf5d22ac | |||
22:10 | MemLong: Memory-Augmented Retrieval for Long Text LLM Generation https://medium.com/@techsachin/memlong-memory-augmented-retrieval-for-long-text-llm-generation-118081c2c545 | |||
21:57 | Llm2vec — A Novel way to unlock the Embedding capabilities of LLMs https://medium.com/@ElGueddari/llm2vec-a-novel-way-to-unlock-the-embedding-capabilities-of-llms-b1bc0054977b | |||
21:56 | Unleashing the Power of Piper TTS: Achieve 10x Faster, Real-Time, Local AI-Driven Text-to-Speech… https://medium.com/@monsuralirana/unleashing-the-power-of-piper-tts-transforming-text-to-speech-10x-faster-with-ai-human-like-voice-eadf2065d66d | |||
21:16 | Construindo um Prompt para o Gemini https://medium.com/google-cloud-brasil/construindo-um-prompt-para-o-gemini-3f03ba552675 | |||
21:06 | What is Generative AI? + Key GenAI Vocabulary https://medium.com/@sean.gahagan/what-is-generative-ai-key-genai-vocabulary-237453864ffd | |||
20:31 | Reading Notes — LoRA https://lzhangstat.medium.com/reading-notes-lora-21be4c73a284 | |||
20:22 | LLM output tokens are upto 200x slower than input tokens https://minusx.ai/blog/input-vs-output-tokens/ | |||
19:56 | Unlocking the Power of GenAI Agents and Digital Twins https://aisutra.com/unlocking-the-power-of-genai-agents-and-digital-twins-9e4b7e4ef119 | |||
19:50 | Web scraping with GPT-4o: powerful but expensive https://blancas.io/blog/ai-web-scraper/ | |||
19:23 | LangGraph — Part 1 https://gunjanvi.medium.com/langgraph-part-1-dd37e2936ca9 | |||
19:22 | Revolution in Search: How Perplexity AI Surpasses Google https://medium.com/@LegionSVK/revolution-in-search-how-perplexity-ai-surpasses-google-927e792711fd | |||
19:08 | Prompt Engineering Basic Guide https://medium.com/@Shashi.Kiran.AI/prompt-engineering-basic-guide-69c1b872b872 | |||
18:53 | Offline AI: Run on Windows/Mac/Linux, LLM (Large Language Models with single llamafile. https://medium.com/free-or-open-source-software/offline-ai-run-on-windows-mac-linux-llm-large-language-models-with-single-llamafile-b79112e0ccad | |||
18:32 | From Literal to Fluent: The Evolution of Machine Translation https://medium.com/@khanna.niharika09/from-literal-to-fluent-the-evolution-of-machine-translation-714a19bf1476 | |||
18:04 | Lab #7: 10 Prompt Implementation Patterns You Should Know (Part 1) https://ai.gopubby.com/lab-7-10-prompt-implementation-patterns-you-should-know-part-1-82e3794ec33f | |||
17:56 | LLM-PEFT-Methods-Performance-Review https://medium.com/@gharikrishnareddy7696/llm-peft-methods-performance-review-b831dfaefdb9 | |||
17:53 | Say Goodbye to boring Chatbots by combining Structure (Bot Frameworks) & Flexibility (LLMs) https://ai.gopubby.com/say-goodbye-to-boring-chatbots-by-combining-structure-bot-frameworks-flexibility-llms-18ae70bc73c5 | |||
17:33 | From Classroom to Code: Must-Try Machine Learning Projects for Students https://medium.com/@pasanbathiya246/from-classroom-to-code-must-try-machine-learning-projects-for-students-f9f94200158d | |||
17:02 | Breaking down Meta’s LLaMa 3.1 https://medium.com/@laxmipanch/breaking-down-metas-llama-3-1-4eca6c1a05e2 | |||
17:00 | Simplifying LLM Optimisation https://cobusgreyling.medium.com/simplifying-llm-optimisation-f82f4ea9e3b3 | |||
16:42 | Forecasting electricity prices with Amazon Chronos https://medium.com/@fg-research/forecasting-electricity-prices-with-amazon-chronos-c8b86afd7748 | |||
16:22 | Build a Multi-Query RAG pipeline in Langflow https://medium.com/logspace/build-a-multi-query-rag-pipeline-in-langflow-67d7d43b0699 | |||
16:21 | Creating a Multimodal Agent with CrewAI, Groq, and Replicate https://medium.com/@kram254/creating-a-multimodal-agent-with-crewai-groq-and-replicate-b90fb8a55949 | |||
16:18 | Supercharging Your AI Applications: Integrating Function Calling with Gpt-4o https://medium.com/@milenppavlov/supercharging-your-ai-applications-integrating-function-calling-with-gpt-4o-334a36cd2aad | |||
16:01 | Month in 4 Papers (August 2024) https://pub.towardsai.net/month-in-4-papers-august-2024-09d3ad9979ec | |||
16:01 | Behind the AI Curtain: Exposing Critical Vulnerabilities in LLM Applications https://medium.com/curiously-ai/behind-the-ai-curtain-exposing-critical-vulnerabilities-in-llm-applications-07a161a829e5 | |||
15:54 | Reasoning-Aware Self-Consistency : Leveraging Reasoning Paths for Efficient LLM generation Sampling https://medium.com/@techsachin/reasoning-aware-self-consistency-leveraging-reasoning-paths-for-efficient-llm-generation-sampling-ea4ac310bd5e | |||
15:44 | Natural Language Queries Over a Power BI Dataset s— Elastacloud Summer of Code! https://medium.com/@robmcdonnell95/natural-language-queries-over-a-power-bi-dataset-s-elastacloud-summer-of-code-6b8fa58d207f | |||
15:31 | Ever wondered how the unread message indicator works at scale of millions? https://medium.com/nerd-for-tech/ever-wondered-how-the-unread-message-indicator-works-at-scale-of-millions-6ee319d26bb8 | |||
15:28 | All You Need to know about RAG — When, Why, and How to use it? https://millenniumbismay.medium.com/all-you-need-to-know-about-rag-when-why-and-how-to-use-it-1d70ec2f2ea4 | |||
15:14 | Talk to X(Twitter) data https://wire.insiderfinance.io/talk-to-x-twitter-data-6e268ced03ca | |||
15:13 | What are RAG Evaluators (2/3) https://medium.com/@nimeeshsharma/what-are-rag-evaluators-2-3-94e9e7d5feb3 | |||
15:06 | How to Improve LLM Responses With Better Sampling Parameters https://towardsdatascience.com/how-to-improve-llm-responses-with-better-sampling-parameters-b31a348381f7 | |||
14:42 | How to Train AI Agents with crewai. https://medium.com/@samarrana407/how-to-train-ai-agents-with-crewai-1e3a2cf74712 | |||
14:11 | The Gold Standard for Production-Ready LLM Orchestration https://medium.com/@jldevtech/the-gold-standard-for-production-ready-llm-orchestration-003f27646b2a | |||
14:01 | Meta’s Transfusion - A Game Changer Model!! https://pub.towardsai.net/metas-transfusion-a-game-changer-model-ac8e4c4be503 | |||
13:57 | LLMs for Developers: A Practical Guide to Licensing and Ethical Use https://medium.com/@callingmahendra/llms-for-developers-a-practical-guide-to-licensing-and-ethical-use-d40582a9dc32 | |||
13:49 | AI at Work: Automating Meeting Transcriptions(Assembly.ai) and Performance Reviews(Multimodal RAG) https://medium.com/@mohantydibyajyoti47/ai-at-work-automating-meeting-transcriptions-assembly-ai-and-performance-reviews-multimodal-rag-112e27a9be2c | |||
13:30 | How to Run Llama 3 Locally and Integrate It into Your Applications with a Free REST API: A Complete… https://sameerk2k01.medium.com/how-to-run-llama-3-locally-and-integrate-it-into-your-applications-with-a-free-rest-api-a-complete-57f158c7139e | |||
13:13 | Recommendation System Using LLM, Part 7 https://medium.com/@linghuang_76674/recommendation-system-using-llm-part-7-afca15ecb0f4 | |||
12:53 | Grounding Techniques for Large Language Models https://medium.com/technology-nineleaps/grounding-techniques-for-large-language-models-53d21efc8b6d | |||
12:34 | Inside GameNGen: Google DeepMind’s New Model that can Simulate Entire 1993’s DOOM Game in Real Time https://pub.towardsai.net/inside-gamengen-google-deepminds-new-model-that-can-simulate-entire-1993-s-doom-game-in-real-time-6f2dab764bb5 | |||
12:33 | Why AI Models like GPT4o are still inefficient and can Never Cross This Line https://medium.com/pythoneers/why-ai-models-like-gpt4o-are-still-inefficient-and-can-never-cross-this-line-1571b84e76b9 | |||
12:33 | Bio-Informatics is Beyond LLMs https://medium.com/pythoneers/bio-informatics-is-beyond-llms-1ace649dfe16 | |||
12:31 | Do your research: the STORM method for improving long-form document generation https://medium.com/one-cool-thing/do-your-research-the-storm-method-for-improving-long-form-document-generation-06e51efb49da | |||
12:31 | Apache SeaTunnel 2.3.7 Released: New Support for Large Language Model Data Transformation https://apacheseatunnel.medium.com/apache-seatunnel-2-3-7-released-new-support-for-large-language-model-data-transformation-6f8f73a2fcde | |||
12:29 | Code Without Any Syntax https://pub.towardsai.net/code-without-any-syntax-0c7a0c5d27b4 | |||
12:21 | A Revolução do Processamento de Linguagem Natural: Impactos e Aplicações no Mundo dos Negócios https://medium.com/@wilton_21143/a-revolu%C3%A7%C3%A3o-do-processamento-de-linguagem-natural-impactos-e-aplica%C3%A7%C3%B5es-no-mundo-dos-neg%C3%B3cios-028f2500f140 | |||
12:19 | Tracing — Why it’s essential for Agentic & Compound AI Systems https://medium.com/@vandan.parmar/tracing-why-its-essential-for-agentic-compound-ai-systems-b9a341908c28 | |||
11:38 | Understanding the Air India-Vistara Merger: Key Changes and Impacts https://medium.com/@andy1729/understanding-the-air-india-vistara-merger-key-changes-and-impacts-c7d565439857 | |||
11:27 | Microsoft-CrowdStrike issue causes ‘largest IT outage in history’ https://medium.com/@andy1729/microsoft-crowdstrike-issue-causes-largest-it-outage-in-history-59a1f396eb2a | |||
11:00 | Introducing the New Window.ai: Free AI Model Control for Your Web Apps https://shaxadd.medium.com/introducing-the-new-window-ai-free-ai-model-control-for-your-web-apps-a41b6c0499ab | |||
10:51 | Zero-Shot Learning vs. Few-Shot Learning vs. Fine Tuning https://medium.com/@sophiamsac/zero-shot-learning-vs-few-shot-learning-vs-fine-tuning-07e6c9fd4fda | |||
10:44 | The Carbon Footprint of LLMs — A Disaster in Waiting? https://nathanbaileyw.medium.com/the-carbon-footprint-of-llms-a-disaster-in-waiting-6fc666235cd0 | |||
10:23 | Leveraging Sparse and Dense Vectors for Real-Time Financial Market Analysis https://medium.com/@gayathrisaranathan/leveraging-sparse-and-dense-vectors-for-real-time-financial-market-analysis-257ed61c907a | |||
10:10 | Getting Work Done with GenAI: Just do the opposite — 10 contrarian rules that may actually work https://medium.com/@darrenoberst/getting-work-done-with-genai-just-do-the-opposite-10-contrarian-rules-that-may-actually-work-634501602a27 | |||
09:54 | How to Make Your Product AI-Driven with Large Language Models (LLMs) https://medium.com/@centizennationwide/how-to-make-your-product-ai-driven-with-large-language-models-llms-e63b75413b7c | |||
09:52 | Optimizing Airport METAR Forecasts with Machine Learning and LLM Techniques https://robinat539.medium.com/optimizing-airport-metar-forecasts-with-machine-learning-and-llm-techniques-4da2f13025e9 | |||
09:45 | LLM-Based Solutions: Why LLM Technologies Are the Key to Outsmarting Your Competition? https://medium.com/ailogic/llm-based-solutions-key-to-outsmarting-competition-34b450c36892 | |||
09:32 | When CrewAI meets Arduino https://medium.com/@miguel.otero.pedrido.1993/when-crewai-meets-arduino-d69d32e84153 | |||
09:13 | How to reduce a Large Language Model to 450MB? https://generativeai.pub/how-to-reduce-a-large-language-model-to-450mb-3fda04d88578 | |||
09:10 | Enhancing Your RAG Pipeline: Adding Semantic Routing for Intent Handling https://medium.com/@shriyansnaik/enhancing-your-rag-pipeline-adding-semantic-routing-for-intent-handling-d95272123460 | |||
09:03 | Fine-Tuning LLM model (Meta-Llama-3.1–8B) for Text-to-SQL Data https://medium.com/@raftaarrashedin100/fine-tuning-llm-model-meta-llama-3-1-8b-for-text-to-sql-data-ea5a07620dd3 | |||
08:48 | How to Run Ollama Locally Using Docker https://khodeprasad.medium.com/how-to-run-ollama-locally-using-docker-2a5bdd90cc20 | |||
08:27 | Putting the (Gen AI) Puzzle Together https://medium.com/@kristina.stoitsova_19354/putting-the-gen-ai-puzzle-together-9470c3aaef7a | |||
08:19 | Elevating UX for AI-first products https://medium.com/@lequime/elevating-ux-for-ai-first-products-ab7e20132436 | |||
08:19 | RAG: The Secret Sauce for Sharper, Smarter AI https://medium.com/@sharmashrutiy7/rag-the-secret-sauce-for-sharper-smarter-ai-74096210bd56 | |||
08:16 | The Prompt Paradox: Why Your AI Doesn’t Understand You (And How to Fix It) https://medium.com/@avinashndatascientist/the-prompt-paradox-why-your-ai-doesnt-understand-you-and-how-to-fix-it-ece1812831a6 | |||
07:53 | How Model Collapse could revive authentic human communities https://mathewlowry.medium.com/how-model-collapse-could-revive-authentic-human-communities-e723d8048ef3 | |||
07:52 | GraphRAG (Graph Retrieval-Augmented Generation) https://medium.com/@chnwsw01/graphrag-graph-retrieval-augmented-generation-72ab921421a3 | |||
07:50 | Retrieval Augmented Generation Frameworks: AutoGen https://admantium.medium.com/retrieval-augmented-generation-frameworks-autogen-1e95735520ba | |||
07:03 | The Code Canaries Are Singing — Our Path Toward AGI https://akiranin.medium.com/the-code-canaries-are-singing-our-path-toward-agi-6c234cae0189 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803