LLM News and Articles
| Thursday, 2024-07-25 | ||||
| 18:16 | OpenAI announces SearchGPT, its AI-powered search engine https://www.theverge.com/2024/7/25/24205701/openai-searchgpt-ai-search-engine-google-perplexity-rival | |||
| 18:15 | OpenAI Announces SearchGPT https://chatgpt.com/search | |||
| 18:04 | GenAI — Best Practices for Using Vector DB Collections https://verticalserve.medium.com/genai-best-practices-for-using-vector-db-collections-a4bf87a87911 | |||
| 18:02 | Generative AI in Nutshell https://medium.com/@abhishekvirat0/generative-ai-in-nutshell-b076f3265bb1 | |||
| 18:01 | Why is Llama 3.1 Such a Big deal? https://pub.towardsai.net/why-is-llama-3-1-such-a-big-deal-e06a81511801 | |||
| 16:45 | What does the Transformer Architecture Tell Us? https://towardsdatascience.com/what-does-the-transformer-architecture-tell-us-cd3a4fd6a59d | |||
| 16:43 | Key Figures Shaping AI LLM Research in 2024 https://medium.com/@alexbuzunov/key-figures-shaping-ai-llm-research-in-2024-a213765e060f | |||
| 16:17 | Understanding Meta LLM Compiler Made-Easy https://medium.com/techcraft-chronicles/understanding-meta-llm-compiler-made-easy-748cf9d6047b | |||
| 16:02 | Applying Jamba-Instruct to Long Context Use Cases in Snowflake Cortex AI https://medium.com/snowflake/applying-jamba-instruct-to-long-context-use-cases-in-snowflake-cortex-ai-fcbbb9fc2df3 | |||
| 16:02 | Porting LLMs to Local Machines, Physical Intelligence, Software Engineering & AI, and 70% Off ODSC… https://medium.com/odscjournal/porting-llms-to-local-machines-physical-intelligence-software-engineering-ai-and-70-off-odsc-4a95c2a3c20e | |||
| 16:02 | 5 AI Real-World Projects To Set Foot in The Door https://pub.towardsai.net/5-ai-real-world-projects-to-set-foot-in-the-door-fd46bac6b4fe | |||
| 15:24 | Understanding Gemini Configuration Parameters https://medium.com/@punya8147_26846/understanding-gemini-configuration-parameters-25c1d867c8e7 | |||
| 15:02 | #33 Is LoRA the Right Alternative to Full Fine-Tuning? https://pub.towardsai.net/33-is-lora-the-right-alternative-to-full-fine-tuning-168e84e015cd | |||
| 15:01 | Have You Met… Your Coworker? https://medium.com/binbash-inc/have-you-met-your-coworker-3c26f7ae5f23 | |||
| 14:56 | Have You Met… Your Coworker? https://medium.com/@emiliano.brest/have-you-met-your-coworker-70ab4c436301 | |||
| 14:14 | Introduction to Text-to-Speech Using LLM’s https://medium.com/@prajwal_/introduction-to-text-to-speech-using-llms-58ef41a92f9e | |||
| 13:40 | Top 10 Use Cases of LLMs in Aviation https://medium.com/@lynnfdsouza/top-10-use-cases-of-llms-in-aviation-7f7ba11e2437 | |||
| 13:36 | Jais and Jais-chat https://medium.com/@muhammadhelmymmo/jais-and-jais-chat-e4c71a619cd3 | |||
| 13:07 | Sam Altman: AI's future must be democratic https://www.washingtonpost.com/opinions/2024/07/25/sam-altman-ai-democracy-authoritarianism-future/ | |||
| 13:02 | Optimizing NLP Models: Fine-Tuning Strategies with MonsterAPI https://medium.com/@erkajalkumari/optimizing-nlp-models-fine-tuning-strategies-with-monsterapi-ed73735b1166 | |||
| 12:57 | Why GPT-4o-mini is a Game-Changer for AI and a Much Bigger Deal Than You Thought https://ai.gopubby.com/why-gpt-4o-mini-is-a-game-changer-for-ai-and-a-much-bigger-deal-than-you-thought-f3487461b610 | |||
| 12:42 | Mistral Large 2: the LLM Focused on Multilinguality and Coding https://medium.com/@elmo92/mistral-large-2-the-llm-focused-on-multilinguality-and-coding-cb2beabc5697 | |||
| 12:35 | Why Current LLM Evaluations Are Rigged: The Case for Better Benchmarks https://metrix-ai-blogs.medium.com/why-current-llm-evaluations-are-rigged-the-case-for-better-benchmarks-6ca81b47d873 | |||
| 12:17 | Llama 3.1 is available for home AI clusters! Run 8B model with the full context https://github.com/b4rtaz/distributed-llama/releases/tag/v0.10.0 | |||
| 12:00 | Mistral Large 2 — OpenAI is sweating now. https://medium.com/augmented-startups/mistral-large-2-0245fd48f05e | |||
| 11:52 | Testing the new Mistral Large 2 LLM https://ai.gopubby.com/testing-the-new-mistral-large-2-llm-9fd4a2e40e65 | |||
| 11:24 | Meta ရဲ့ Llama 3.1 https://medium.com/@iamkokomg/meta-%E1%80%9B%E1%80%B2%E1%80%B7-llama-3-1-e087143c7c29 | |||
| 11:04 | Power of DSpy: A Python Library That Will Change How You Analyze Data https://medium.com/@nisharathod5093/power-of-dspy-a-python-library-that-will-change-how-you-analyze-data-44d27d968803 | |||
| 11:00 | This AI Paper Introduces Long-form RobustQA Dataset and RAG-QA Arena for Cross-Domain Evaluation of Retrieval-Augmented Generation Systems https://www.marktechpost.com/2024/07/25/this-ai-paper-introduces-long-form-robustqa-dataset-and-rag-qa-arena-for-cross-domain-evaluation-of-retrieval-augmented-generation-systems/ | |||
| 10:43 | Llama 3.1 405B Inference Service Deployment: Beginner’s Guide https://medium.com/@marketing_novita.ai/llama-3-1-405b-inference-service-deployment-beginners-guide-667531f92cfd | |||
| 10:31 | Building enterprise solutions with LLMs https://medium.com/@greger_ottosson/building-enterprise-solutions-with-llms-936180b0c784 | |||
| 10:31 | Build a Secure Local RAG Application with Chat History using LangChain, llama3, Qdrant, Redis &… https://medium.com/@hemz/build-a-secure-local-rag-application-with-chat-history-using-langchain-llama3-qdrant-redis-986be3628a94 | |||
| 10:24 | LangChain — II: Basic Chatbot Unpacked https://techblogs.cloudlex.com/langchain-ii-basic-chatbot-unpacked-a60510b9ac6b | |||
| 09:38 | ModelBox Now Offers Gemma 2 27B Inference https://medium.com/@modelbox/modelbox-now-offers-gemma-2-27b-inference-94fb9b4b3a76 | |||
| 09:37 | Document Parsing Using Large Language Models — With Code https://towardsdatascience.com/document-parsing-using-large-language-models-with-code-9229fda09cdf | |||
| 09:31 | 10 Chatbot Best Practices for Successful Automation https://medium.com/@marketing_novita.ai/10-chatbot-best-practices-for-successful-automation-7e4457b167ee | |||
| 09:27 | Small Language Models: Efficient Solutions for Next-Gen AI Challenges https://medium.com/@mirekal2404/small-language-models-efficient-solutions-for-next-gen-ai-challenges-ad111f966e2b | |||
| 09:21 | Mainframe vs Standalone LLMs — Data Privacy and Limitations https://medium.com/@seguigomezolea/mainframe-vs-standalone-llms-data-privacy-and-limitations-752a566ca029 | |||
| 09:14 | Coding with Llama 3.1, New DeepSeek Coder and Mistral Large https://aider.chat/2024/07/25/new-models.html | |||
| 09:09 | Creating ChatGPT based data analyst: first steps https://medium.com/sightfull-developers-blog/leveraging-genai-to-superpower-our-analytics-platforms-users-b251f764ea1c | |||
| 09:01 | Unlock Image Creation with OpenAI DALL-E | Create, Edit & Manipulate https://blog.gopenai.com/unlock-image-creation-with-openai-dall-e-create-edit-manipulate-b37a5a81f40e | |||
| 08:37 | Next Token Prediction Task with https://medium.com/@jiangmen28/next-token-prediction-task-with-bff7e7aa8e38 | |||
| 08:33 | LLama 3.1 Zuckerbergs Open Source model from Meta https://medium.com/augmented-startups/llama-3-1-zuckerbergs-open-source-model-from-meta-945a1c099291 | |||
| 07:57 | LLM Agents: Everything You Need to Know https://medium.com/@addepto/llm-agents-everything-you-need-to-know-57416c5f7a3f | |||
| 07:52 | Fine Tuning Meta LLAMA 3 with custom data https://medium.com/@naikaa/fine-tuning-llma-3-with-custom-data-dfa6d0a5e3d3 | |||
| 07:48 | Fine-Tuning LLM: Enhancing Efficiency with PEFT https://medium.com/@swetachaturvedi10/fine-tuning-llm-enhancing-efficiency-with-peft-bf1792a28014 | |||
| 07:33 | Building a Custom Mixture of Experts Model for our Darija: From Tokenization to Text Generation https://blog.gopenai.com/building-a-custom-mixture-of-experts-model-for-our-darija-from-tokenization-to-text-generation-b30ba49ae7cc | |||
| 07:20 | Revolutionising Unit Test Generation With Llms https://medium.com/@keployio/revolutionising-unit-test-generation-with-llms-229813743853 | |||
| 07:19 | Affordable LLMs: The Smart Choice for Production https://aakashgupta.medium.com/affordable-llms-the-smart-choice-for-production-4179e0e1e20c | |||
| 07:17 | Exploring Meta’s LLaMA 3: A Leap Forward in Large Language Models https://medium.com/@anshikagupta.js/exploring-metas-llama-3-a-leap-forward-in-large-language-models-999ae1e66a5f | |||
| 07:15 | Top Large Language Models LLMs Courses https://www.marktechpost.com/2024/07/25/top-large-language-models-llms-courses/ | |||
| 07:02 | LangChain Search AI Agent Using GPT-4o-mini https://cobusgreyling.medium.com/langchain-search-ai-agent-using-gpt-4o-mini-ce2b7442479b | |||
| 06:18 | What is Retrieval Augmented Generation(RAG) and how does it work? https://medium.com/@aydinKerem/what-is-retrieval-augmented-generation-rag-and-how-does-it-work-05ad3c1ed669 | |||
| 05:32 | Discovering Gemini Chat Model https://medium.com/@punya8147_26846/discovering-gemini-chat-model-3dbc6affaf2f | |||
| 05:07 | The Secret Dials of AI Creativity: Mastering top_p and Temperature https://medium.com/@tripathinaman.1014/the-secret-dials-of-ai-creativity-mastering-top-p-and-temperature-d884872af28c | |||
| 04:40 | Mistral Large 2 https://medium.com/@akshithpottigari/mistral-large-2-78a325a9e77b | |||
| 04:13 | AI Decodes Project 2025 To Expose Its Real Intent https://medium.com/@Democracy_Labs/ai-decodes-project-2025-to-expose-its-real-intent-f9894f3c8a72 | |||
| 03:36 | Creating Gradient Palettes: Fine-Tuning granite-7b for Analogous Gradient Palettes https://shift.zone/creating-gradient-palettes-fine-tuning-granite-7b-for-analogous-gradient-palettes-13a90dd1fea2 | |||
| 03:34 | Language Models (LLMs) https://medium.com/@Mandeep2002/language-models-llms-736fa96f3cb5 | |||
| 03:28 | Fine-Tuning Llama 3.1 405B on a Single Node https://www.snowflake.com/engineering-blog/fine-tune-llama-single-node-snowflake/ | |||
| 03:20 | What Ifs in AI and Media: ‘Left, Right & Centre’ https://ritvvijparrikh.medium.com/what-ifs-in-ai-and-media-left-right-centre-6206260428d9 | |||
| 01:49 | Why ChatGPT is a lousy assistant for data engineers https://medium.com/@brendan.mckenna/why-chatgpt-is-a-lousy-assistant-for-data-engineers-657476089be9 | |||
| 01:39 | Day 855 https://chepenikconor.medium.com/day-855-9ae6f88b192c | |||
| 01:38 | Tokens: The Electricity Powering the LLM Revolution https://medium.com/@soheil.sarmadi/tokens-the-electricity-powering-the-llm-revolution-98802fe1da00 | |||
| 01:24 | Large Language Models and Their Feasibility for Natural Language Processing https://medium.com/@investince/large-language-models-and-their-feasibility-for-natural-language-processing-0543f6f92c01 | |||
| 00:24 | How to Generate Bert Embeddings Faster and More Reliably for large dataset https://ragrawal-24314.medium.com/how-to-generate-bert-embeddings-faster-and-more-reliably-for-large-dataset-896b1f0a0528 | |||
| 00:23 | Affordable Platforms for Fine-Tuning & Training Large Language Models (LLMs) https://levelup.gitconnected.com/affordable-platforms-for-fine-tuning-training-large-language-models-llms-1812cdb8e592 | |||
| 00:05 | Understanding Anthropic Claude: The Future of AI Interaction https://medium.com/@darrenrobinson777/understanding-anthropic-claude-the-future-of-ai-interaction-2c625bf0cc8d | |||
| 00:01 | Unlocking the Power of Knowledge Graphs: Advanced Uses and Integration with LangChain https://medium.com/@pankaj_pandey/unlocking-the-power-of-knowledge-graphs-advanced-uses-and-integration-with-langchain-d7a806fb3230 | |||
| 00:00 | LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning? https://huggingface.co/blog/lave | |||
| 00:00 | LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning? https://huggingface.co/blog/zero-shot-vqa-docmatix | |||
| Wednesday, 2024-07-24 | ||||
| 23:00 | Nvidia AI Proposes ChatQA 2: A Llama3-based Model for Enhanced Long-Context Understanding and RAG Capabilities https://www.marktechpost.com/2024/07/24/nvidia-ai-proposes-chatqa-2-a-llama3-based-model-for-enhanced-long-context-understanding-and-rag-capabilities/ | |||
| 22:59 | OpenAI is set to lose B this year https://www.datacenterdynamics.com/en/news/openai-training-and-inference-costs-could-reach-7bn-for-2024-ai-startup-set-to-lose-5bn-report/ | |||
| 22:44 | Data Science Spotlight: Cracking the SQL Interview at Instacart (LLM Edition) https://tech.instacart.com/data-science-spotlight-cracking-the-sql-interview-at-instacart-llm-edition-52d04bde474c | |||
| 22:30 | Exploring the Impact of OpenAI on Modern Technology https://medium.com/@darrenrobinson777/exploring-the-impact-of-openai-on-modern-technology-e822b08f1fd9 | |||
| 22:14 | GenAI — LLM-Based Agents: Architecture, Best Practices, and Frameworks https://verticalserve.medium.com/genai-llm-based-agents-architecture-best-practices-and-frameworks-6dba19d194fb | |||
| 22:09 | GenAI — LLM Monitoring and Its Importance https://verticalserve.medium.com/genai-llm-monitoring-and-its-importance-8bf07d2d2dfb | |||
| 21:43 | NEW Named Entity Recognition — GLiNER https://medium.com/@Lorenzo_Pozzi/new-named-entity-recognition-gliner-27d4284cc268 | |||
| 21:32 | A Conversation with Meta Llama 3.1-405B https://medium.com/@adampaigge_30167/a-conversation-with-meta-llama-3-1-405b-2b02aca81d9b | |||
| 21:27 | GraphRAG: Unlocking Contextual Understanding https://medium.com/@agarwaladitya611/graphrag-unlocking-contextual-understanding-0f144b7d3ed8 | |||
| 20:55 | Exploring the Benefits of Chat GPT for Effective Communication https://medium.com/@darrenrobinson777/exploring-the-benefits-of-chat-gpt-for-effective-communication-a2ad94e95a18 | |||
| 20:47 | A Visual Guide to Quantization https://towardsdatascience.com/a-visual-guide-to-quantization-930ebcd9be94 | |||
| 20:42 | Llama 3 versus Llama 3.1 License Terms https://writing.kemitchell.com/2024/07/24/Llama-3-versus-Llama-3-1-License | |||
| 20:07 | Llama Llama-3-405B? https://thezvi.substack.com/p/llama-llama-3-405b | |||
| 20:02 | Important LLMs Papers for the Week from 15/07 to 21/07 https://pub.towardsai.net/important-llms-papers-for-the-week-from-15-07-to-21-07-f7f1d0a9d7e1 | |||
| 19:39 | LLM’s for data extraction https://medium.com/@nevinbaiju_77488/llms-for-data-extraction-ad3d492c439b | |||
| 19:23 | Getting Started with LLaMA 3.1 https://medium.com/@edmond.po/getting-started-with-llama-3-1-2830320cf10b | |||
| 19:12 | Agents as a MicroService | Beginner Guide to llama-agents https://medium.com/@mahimairaja/agents-as-a-microservice-beginner-guide-to-llama-agents-b04d11f33174 | |||
| 19:09 | Announcing Llama 3.1: Meta’s Largest and Most Advanced AI Model https://ai.gopubby.com/llama-3-1-metas-largest-and-most-advanced-ai-model-01804789be9d | |||
| 19:09 | Announcing Llama 3.1: Meta’s Largest and Most Advanced AI Model https://medium.com/@PinkHatHacker/llama-3-1-metas-largest-and-most-advanced-ai-model-01804789be9d | |||
| 19:02 | Meet the Fellow: Shauli Ravfogel https://nyudatascience.medium.com/meet-the-fellow-shauli-ravfogel-5d2658e34f03 | |||
| 19:00 | Understanding LLM: The Future of Language Models https://medium.com/@darrenrobinson777/understanding-llm-the-future-of-language-models-f038de52bec7 | |||
| 18:59 | iFixit CEO Kyle Wiens calls out Anthropic for disruptive crawling https://twitter.com/kwiens/status/1816128302542905620 | |||
| 18:53 | Effective Methods to Mitigate Hallucinations in Large Language Models (LLMs) https://medium.com/@tselvaraj/effective-methods-to-mitigate-hallucinations-in-large-language-models-llms-f72f5a402889 | |||
| 18:44 | Show HN: Pairing LLM code generation with traditional templates https://github.com/mify-io/mify-llm-editor | |||
| 18:30 | Unlocking Generative AI Power in Spring Boot Applications https://medium.com/@pen.darkknight/unlocking-generative-ai-power-in-spring-boot-applications-85c15465df82 | |||
| 18:17 | The Guide to Evaluating Retrieval-Augmented Generation (RAG) systems https://blog.lastmileai.dev/the-guide-to-evaluating-retrieval-augmented-generation-rag-systems-01568ed02d0e | |||
| 18:09 | RAG Retrieval-augmented generation (RAG) https://medium.com/@aagamshah2501/rag-retrieval-augmented-generation-rag-284dcd358127 | |||
| 17:57 | Engenheiro de Dados 3.0 https://medium.com/@welsonplayqs/engenheiro-de-dados-3-0-c0f55e363cf5 | |||
| 17:49 | Pushing the Boundaries of Decentralized AI: SolderAI Partners with Netmind https://medium.com/@solderai.org/pushing-the-boundaries-of-decentralized-ai-solderai-partners-with-netmind-d81c506024e4 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803