LLM News and Articles
Saturday, 2024-07-27 | ||||
00:17 | Strategies for Marketing to Large Language Models (LLMs) https://redepapa.medium.com/strategies-for-marketing-to-large-language-models-llms-e1602517c1c8 | |||
Friday, 2024-07-26 | ||||
23:20 | Hands on LangChain: Chains (Part 3) https://medium.com/@ai-data-drive/hands-on-langchain-chains-part-3-b05ee7b097cc | |||
23:01 | Hands on LangChain: Memory(Part 2) https://medium.com/@ai-data-drive/hands-on-langchain-memory-part-2-52d2eba9ba6d | |||
22:44 | Hands on LangChain: Models (Part 1) https://medium.com/@ai-data-drive/hands-on-langchain-models-part-1-3553624c84ec | |||
22:32 | Best ‘Free & Offline’ chatGPT Alternatives You Can Install on Your Computers (Windows & Mac)… https://medium.com/@shiv.p.singh94/best-free-offline-chatgpt-alternatives-you-can-install-on-your-computers-windows-mac-39c8e14cf788 | |||
21:57 | Information Theory, Inference, and Learning Algorithms https://inference.org.uk/itila/book.html | |||
20:44 | Using LLMs for Recommendation Systems: A Netflix Use Case https://medium.com/@imteyazkashif8/using-llms-for-recommendation-systems-a-netflix-use-case-967c007dd173 | |||
19:54 | SMALL SIZE, BIG IMPACT https://medium.com/@NSK.AI/small-size-big-impact-e1e70f544177 | |||
19:23 | Llama-3.1 supports tool calls via prompting https://www.braintrust.dev/docs/cookbook/recipes/LLaMa-3_1-Tools | |||
19:12 | Self-Route: A Simple Yet Effective AI Method that Routes Queries to RAG or Long Context LC based on Model Self-Reflection https://www.marktechpost.com/2024/07/26/self-route-a-simple-yet-effective-ai-method-that-routes-queries-to-rag-or-long-context-lc-based-on-model-self-reflection/ | |||
19:06 | Anthropic accused of 'egregious' data scraping https://www.ft.com/content/07611b74-3d69-4579-9089-f2fc2af61baa | |||
19:05 | Who is Leading OpenSource AI?? https://medium.com/@achanandhi.m/who-is-leading-opensource-ai-aafe1a481b9f | |||
18:56 | Automated Knowledge Sharing - Case Study https://medium.com/pressw/automated-knowledge-sharing-case-study-ce63926d40be | |||
18:27 | Unveiling AI’s Canvas: The Future of Art Prompt Engineering https://medium.com/@alexbuzunov/unveiling-ais-canvas-the-future-of-art-prompt-engineering-b7d43b824834 | |||
18:27 | Unveiling AI’s Canvas: The Future of Art Prompt Engineering https://blog.gopenai.com/unveiling-ais-canvas-the-future-of-art-prompt-engineering-b7d43b824834 | |||
18:00 | A Historic Week for ̶O̶p̶e̶n̶ ̶S̶o̶u̶r̶c̶e̶ AI https://www.llmwatch.com/p/a-historic-week-for-open-source-ai | |||
17:55 | OrphaGPT: Leveraging GPT-3.5 Turbo for Orphan Disease Information & Classification https://blog.gopenai.com/orphagpt-leveraging-gpt-3-5-turbo-for-orphan-disease-information-classification-d577175ae8b4 | |||
17:49 | Revolutionize Web Development: Integrating AJAX in Javascript and guide to Chatgpt Automate https://medium.com/@riddhimos2001/revolutionize-web-development-integrating-ajax-in-javascript-and-guide-to-chatgpt-automate-650e4af12c16 | |||
17:45 | Context Embeddings for Efficient Answer Generation in RAG https://medium.com/@has.dhia/context-embeddings-for-efficient-answer-generation-in-rag-f64dfc03a1c9 | |||
17:26 | An Overview: Instruction Tuning for LLMs https://medium.com/@edmond.po/an-overview-instruction-tuning-for-llms-440228e7edab | |||
17:03 | ✨HALLUCINATIONS✨: Mitigating Contextual Hallucinations in LLMs: A Novel Attention-Based Approach https://readquick.medium.com/hallucinations-mitigating-contextual-hallucinations-in-llms-a-novel-attention-based-approach-b5b465263ee5 | |||
16:57 | RouteLLM: Optimizing the Cost-Quality Trade-Off in Large Language Model Deployment https://vivekpandit.medium.com/routellm-optimizing-the-cost-quality-trade-off-in-large-language-model-deployment-c48b7abb2cfa | |||
16:24 | Potential collapse of AI-trained LLMs, researchers indicate https://medium.com/@faiz.neet/potential-collapse-of-ai-trained-llms-researchers-indicate-fa637f33a035 | |||
16:19 | Introducing Llama 3.1: Meta’s Most Advanced Open-Source AI Model https://medium.com/@kagglepro.llc/introducing-llama-3-1-metas-most-advanced-open-source-ai-model-fd838aa7fa45 | |||
15:32 | Cognates and Collaborations: The Global Appeal of ‘Mamushi’ https://medium.com/@ciaraatmoozi/cognates-and-collaborations-the-global-appeal-of-mamushi-37cd8916e13d | |||
15:24 | OpenAI Launches SearchGPT: A New AI-Powered Search Engine to Compete with Google https://medium.com/@icreativek/openai-launches-searchgpt-a-new-ai-powered-search-engine-to-compete-with-google-d485fee7a0d1 | |||
15:22 | Dappier Partners with HomeLife Brands to Monetize IHeartDogs & IHeartCats content for AI Usage https://dappier.medium.com/dappier-partners-with-homelife-brands-to-monetize-iheartdogs-iheartcats-content-for-ai-usage-0a764cbacbd3 | |||
15:17 | Tiny LLMs: AI in Your Pocket https://naveen-bhati.medium.com/tiny-llms-ai-in-your-pocket-98a2edee653a | |||
15:16 | Fine-Tuning Large Language Models https://adnanwritess.medium.com/fine-tuning-large-language-models-8103f46a5ce2 | |||
15:09 | Introducing GPUStack: An open-source GPU cluster manager for running LLMs https://medium.com/@gpustack.ai/introducing-gpustack-an-open-source-gpu-cluster-manager-for-running-llms-0f0a3cb104a7 | |||
15:02 | Meta conseguirá passar a frente na corrida da IA com seu modelo Llama 3.1? https://profissaoia.com/meta-conseguir%C3%A1-passar-a-frente-na-corrida-da-ia-com-seu-modelo-llama-3-1-564280774c34 | |||
14:38 | Building an LLM Chat and Task Bot with Durable Execution https://restate.dev/blog/building-an-llm-chat-task-bot-with-restate/ | |||
14:29 | Llama 3.1: All You Must Know About Meta’s Most Capable LLM https://medium.com/@datasciencedojo/llama-3-1-all-you-must-know-about-metas-most-capable-llm-1261cbef9309 | |||
14:07 | What We Still Don’t Understand About Machine Learning https://towardsdatascience.com/what-we-still-dont-understand-about-machine-learning-699e0002a057 | |||
13:56 | When Will I Finally Get My AI Assistant? https://medium.com/omar-orqueda-blog/when-will-i-finally-get-my-ai-assistant-36e8e1dc4e8a | |||
13:47 | How Are Large Language Models (LLMs) Transforming AI? https://alliancetek.medium.com/how-are-large-language-models-llms-transforming-ai-d4739f593384 | |||
13:47 | Hindu asli amil baba Pakistan, Karachi, lahore Amil Baba | Hindu asli amil baba Pakistan, Karachi… https://medium.com/@bm6983140/hindu-asli-amil-baba-pakistan-karachi-lahore-amil-baba-hindu-asli-amil-baba-pakistan-karachi-1d33acfd535f | |||
13:47 | Arcee Cloud: start adapting models in minutes https://julsimon.medium.com/arcee-cloud-start-adapting-models-in-minutes-c6feae9896b8 | |||
13:46 | **ChatGPT vs. AI: Unraveling the Distinctions in Modern Technology** https://medium.com/@fniazi201276/chatgpt-vs-ai-unraveling-the-distinctions-in-modern-technology-eb72d6b717d8 | |||
12:31 | Optimal Execution Strategies for Llama 3.1 https://medium.com/anolytics/optimal-execution-strategies-for-llama-3-1-d4b6f1cf6181 | |||
12:06 | Web search with RAG // SearchGPT https://sbagency.medium.com/web-search-with-rag-searchgpt-b15c3f7d3671 | |||
12:02 | Unleash the power of LangChain with Local LLM https://pub.towardsai.net/unleash-the-power-of-langchain-with-local-llm-34f7ce9d09e7 | |||
12:00 | Advanced Phrase Matching in Clinical Texts in Healthcare NLP https://medium.com/john-snow-labs/advanced-phrase-matching-in-clinical-texts-in-healthcare-nlp-df7909d750ac | |||
11:50 | Transform Your Business with knowledge-augmented LLMs: An introduction to Retrieval-Augmented… https://medium.com/newnow-blog/transform-your-business-with-knowledge-augmented-llms-an-introduction-to-retrieval-augmented-afdbd24502e9 | |||
11:38 | Microsoft GraphRAG: Redefining AI-Based Content Interpretation and Search | Local Search | PART 2 https://medium.com/@jinglemind.dev/microsoft-graphrag-redefining-ai-based-content-interpretation-and-search-local-search-part-2-c7505eb344db | |||
11:30 | What’s an AI like ChatGPT but Has No Restrictions? (How to Uncensor LLMs) https://towards-agi.medium.com/whats-an-ai-like-chatgpt-but-has-no-restrictions-how-to-uncensor-llms-9666a0554c1c | |||
11:30 | This AI Paper Introduces AssistantBench and SeePlanAct: A Benchmark and Agent for Complex Web-Based Tasks https://www.marktechpost.com/2024/07/26/this-ai-paper-introduces-assistantbench-and-seeplanact-a-benchmark-and-agent-for-complex-web-based-tasks/ | |||
11:25 | Why a Knowledge Graph is Indispensable for Successful RAG Operations in LLM Applications https://medium.com/@ramkumar_manoharan/why-a-knowledge-graph-is-indispensable-for-successful-rag-operations-in-llm-applications-226caced3fa2 | |||
11:22 | OpenAI’s SearchGPT — Will this be a Perplexity Clone? https://medium.com/augmented-startups/openais-searchgpt-will-this-be-a-perplexity-clone-54b138433d21 | |||
11:21 | AI for All: Reducing Bias in Large Language Models https://medium.com/@lmontgomery_86960/ai-for-all-reducing-bias-in-large-language-models-30d77136002e | |||
10:58 | More enjoyable Code Reviews with Gemini https://medium.com/google-cloud/more-enjoyable-code-reviews-with-gemini-85ca661b843d | |||
10:57 | AI Use Cases in Ecommerce: Changing Online Shopping https://medium.com/@marketing_novita.ai/ai-use-cases-in-ecommerce-changing-online-shopping-72a520ce5e78 | |||
10:56 | A Friendly Guide to Retrieval-Augmented Generation Systems Evaluation https://medium.com/@hajar.mousannif/a-friendly-guide-to-retrieval-augmented-generation-systems-evaluation-e979fe153020 | |||
10:40 | Part 2: Benchmarks for NLSQL models https://rojojojo.medium.com/part-2-benchmarks-for-nlsql-models-6f76ec6547af | |||
10:29 | AI models have an expiry date — Continual Learning may be an answer https://alicjadobrzeniecka.medium.com/ai-models-have-expiry-date-9a6e2c9c0a9f | |||
10:06 | Microsoft GraphRAG: Redefining AI-Based Content Interpretation and Search | PART 1 https://medium.com/@jinglemind.dev/microsoft-graphrag-redefining-ai-based-content-interpretation-and-search-part-1-6491dab0e2b3 | |||
09:58 | Building Safer AI Applications: Guardrails On Amazon Bedrock https://generativeai.pub/building-safer-ai-applications-guardrails-on-amazon-bedrock-3402440521c6 | |||
09:30 | Transforming Database Access: The LLM-based Text-to-SQL Approach https://www.marktechpost.com/2024/07/26/transforming-database-access-the-llm-based-text-to-sql-approach/ | |||
08:00 | LMMS-EVAL: A Unified and Standardized Multimodal AI Benchmark Framework for Transparent and Reproducible Evaluations https://www.marktechpost.com/2024/07/26/lmms-eval-a-unified-and-standardized-multimodal-ai-benchmark-framework-for-transparent-and-reproducible-evaluations/ | |||
07:56 | Three Steps to Create Synthetic Data for LLM Training Using Llama 3.1 405B https://towards-agi.medium.com/three-steps-to-create-synthetic-data-for-llm-training-using-llama-3-1-5ec8cfb559a3 | |||
07:30 | Precision 7960 Tower & LLMs In Dell Precision Workstations https://medium.com/@agarapuramesh/precision-7960-tower-llms-in-dell-precision-workstations-3a0534c3ac2b | |||
07:10 | iFixit CEO takes shots at Anthropic for hitting servers a million times in 24h https://www.pcgamer.com/software/ai/ifixit-ceo-takes-shots-at-anthropic-for-hitting-our-servers-a-million-times-in-24-hours-and-even-the-ai-companys-own-chatbot-disapproves/ | |||
07:10 | A New AI Study from MIT Shows Someone’s Beliefs about an LLM Play a Significant Role in the Model’s Performance and are Important for How It is Deployed https://www.marktechpost.com/2024/07/26/a-new-ai-study-from-mit-shows-someones-beliefs-about-an-llm-play-a-significant-role-in-the-models-performance-and-are-important-for-how-it-is-deployed/ | |||
07:08 | Mistral Large 2 vs Llama 405B vs GPT-4 vs Claude 3.5 Sonnet: Real Life Comparison https://towards-agi.medium.com/mistral-large-2-vs-llama-405b-vs-gpt-4-vs-claude-3-5-sonnet-real-life-comparison-90e50c863c29 | |||
07:01 | Meta AI: Pioneering the Future of Artificial Intelligence https://medium.com/@ayushisingh1609/meta-ai-pioneering-the-future-of-artificial-intelligence-1a96e5db8d8c | |||
06:45 | OpenAI tests new search engine called SearchGPT amid AI arms race https://www.theguardian.com/business/article/2024/jul/25/openai-search-engine-searchgpt | |||
06:16 | AI Integration in Xcode: Creating Extensions with Local LLMs https://rohitsainier.medium.com/ai-integration-in-xcode-creating-extensions-with-local-llms-072e8993372f | |||
06:15 | Designing Intelligent Agent Behavior with AutoGen https://medium.com/@abhilasha.sinha/designing-intelligent-agent-behavior-with-autogen-aae401ecc370 | |||
06:11 | OpenAI to Launch Searchgpt https://www.ft.com/content/16c56117-a4f4-45d6-8c7b-3ef80d17d254 | |||
06:11 | Unlock AI’s Promise with an LAM https://medium.com/@ernie_8818/unlock-ais-promise-with-an-lam-415ef3192413 | |||
06:05 | How to use Gorilla on MacOS: A Comprehensive Guide https://medium.com/@researchgraph/how-to-use-gorilla-on-macos-a-comprehensive-guide-57524e17451e | |||
05:31 | Running Llama 3.1 Locally on Mac in Three Simple Commands https://towardsdev.com/running-llama-3-1-locally-on-mac-in-three-simple-commands-bfdfe39489e1 | |||
05:13 | Comprehensive list of LLM benchmarks- Part 1 https://medium.com/@meerakrsna/comprehensive-list-of-llm-benchmarks-part-1-b22c284b140f | |||
04:55 | Imposter.AI: Unveiling Adversarial Attack Strategies to Expose Vulnerabilities in Advanced Large Language Models https://www.marktechpost.com/2024/07/25/imposter-ai-unveiling-adversarial-attack-strategies-to-expose-vulnerabilities-in-advanced-large-language-models/ | |||
04:25 | Insights from LLAMA 3.1 Paper https://medium.com/@minh.hoque/insights-from-llama-3-1-paper-4bee090dd5c5 | |||
03:42 | OpenAI just announced a new search tool. Its demo already got something wrong https://www.theatlantic.com/technology/archive/2024/07/searchgpt-openai-error/679248/ | |||
02:48 | How developers can use Meta Llama 3.1 405B to build advanced models https://sahajgodhani777.medium.com/how-developers-can-use-meta-llama-3-1-405b-to-build-advanced-models-06b5998c5a35 | |||
02:09 | Mistral-Large-Instruct-2407 Released: Multilingual AI with 128K Context, 80+ Coding Languages, 84.0% MMLU, 92% HumanEval, and 93% GSM8K Performance https://www.marktechpost.com/2024/07/25/mistral-large-instruct-2407-released-multilingual-ai-with-128k-context-80-coding-languages-84-0-mmlu-92-humaneval-and-93-gsm8k-performance/ | |||
01:36 | Deploying Weights & Biases Model Checkpoints on Friendli Dedicated Endpoints https://medium.com/@friendli.ai/deploying-weights-biases-model-checkpoints-on-friendli-dedicated-endpoints-9a08285b637b | |||
01:36 | 100 Days of Generative AI — Day 1 — What is an LLM? https://devopslearning.medium.com/100-days-of-generative-ai-day-1-what-is-an-llm-ab56a4f5eb16 | |||
00:36 | ChatGPT-4o: Is your data safe? https://adithyagsundar.medium.com/chatgpt-4o-is-your-data-safe-2c8e25416f15 | |||
00:34 | How does AI think? An Introduction to Explainable AI (XAI) https://adithyagsundar.medium.com/how-does-ai-think-an-introduction-to-explainable-ai-xai-b90e9df87e33 | |||
00:33 | The Role of CSPs to reduce the carbon footprint of AI https://medium.com/@shahid.akhtar.us/the-role-of-csps-to-reduce-the-carbon-footprint-of-ai-0f2b981eb788 | |||
00:28 | LLM Değerlendirme (Benchmark) Metotları https://medium.com/@enesarslan./llm-de%C4%9Ferlendirme-benchmark-metotlar%C4%B1-7cc370fa13c3 | |||
00:18 | LLM revolutionizing supply chain https://medium.com/@soumyashantharaju/llms-revolutionizing-supply-chain-63569848c3c1 | |||
00:17 | Llama 3 Secrets Every Engineer Must Know https://www.anti-vc.com/p/llama-3-secrets-every-engineer-must | |||
00:17 | Technology Killed The Radio Star https://long.sweet.pub/technology-killed-the-radio-star-19ceb71f375a | |||
00:12 | You should be A/B testing your prompts. https://blog.promptlayer.com/you-should-be-a-b-testing-your-prompts-16d514b37ad2 | |||
00:02 | Nook’s Notes: Introduction to Large Language Models (2/2) https://medium.com/@blue.pear/nooks-notes-introduction-to-large-language-models-2-2-498377132651 | |||
00:01 | The Big Question — Do Large Language Models Learn Like Humans? https://medium.com/@billy.chau./the-big-question-do-large-language-models-learn-like-humans-c8bf525716ae | |||
Thursday, 2024-07-25 | ||||
23:05 | Show HN: ChainFactory – Run Structured LLM Inference with Easy Parallelism https://github.com/pankajgarkoti/ChainFactory | |||
22:24 | Llama 3.1 web search integrated into GPT4All Beta https://github.com/nomic-ai/gpt4all/releases/tag/v3.1.0-web_search_beta | |||
22:09 | Unlocking the Potential of Generative AI with Large Language Models — Part 1 https://medium.com/@shuchimishra_16245/unlocking-the-potential-of-generative-ai-with-large-language-models-part-1-949040fc0651 | |||
22:09 | How to Use PromptGuard – Meta's Llama Moderation Model https://www.trytaylor.ai/blog/promptguard | |||
22:08 | Contration https://johnwallbank.medium.com/contration-927f89cee94e | |||
22:01 | Faster Open-Source Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, VLLM) https://lmsys.org/blog/2024-07-25-sglang-llama3/ | |||
21:50 | Unlocking Generative AI on CPUs with NuPIC 2.0 https://medium.com/@Numenta/unlocking-generative-ai-on-cpus-with-nupic-2-0-d71135c632f2 | |||
21:38 | Llama 2 In Clinical Conversational AI https://medium.com/dhpb/llama-2-in-clinical-conversational-ai-3ec158ba05bf | |||
21:31 | OpenAI hits Google where it hurts with new SearchGPT prototype https://arstechnica.com/information-technology/2024/07/openai-hits-google-where-it-hurts-with-new-searchgpt-prototype/ | |||
21:14 | 9.11 or 9.9 — which one is higher? https://medium.com/insightium/9-11-or-9-9-which-one-is-higher-6efbdbd6a025 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501