LLM News and Articles
Sunday, 2024-09-15 | ||||
07:35 | Keeping Humans in the Loop: Essential for LLMs in Research https://medium.com/@udilumnitz/keeping-humans-in-the-loop-essential-for-llms-in-research-44f4f9db2722 | |||
07:24 | Building NotebookLLM using PHP and OpenAI APIs https://twitter.com/motyar/status/1834996164590289254 | |||
07:21 | Complete Generative AI Roadmap in 2024 https://medium.com/@mdirfan5702/complete-generative-ai-roadmap-in-2024-9138450be2db | |||
07:18 | How to Understand the Link Between LLM and GANs https://medium.com/@asakisakamoto02/how-to-understand-the-link-between-llm-and-gans-f291f59f0ffc | |||
07:00 | Navigating OpenAI O1: Options Beyond the Preview Quota https://medium.com/@JugemuAI/navigating-openai-o1-options-beyond-the-preview-quota-698a4b4fafaa | |||
06:46 | From Transformers to Transporters — Why LLM Agents are best for the Logistics Industry https://medium.com/@arjunbhasin88/from-transformers-to-transporters-why-llm-agents-are-best-for-the-logistics-industry-023253b99c5e | |||
06:16 | How to Use Product Integrations for Better Efficiency https://medium.com/@tayloroakley/how-to-use-product-integrations-for-better-efficiency-bd6edb163d5d | |||
06:10 | Overcoming Backend Challenges in LAWIE’s iOS App: Integrating RevenueCat, Managing Python GIL… https://emon1521.medium.com/overcoming-backend-challenges-in-lawies-ios-app-integrating-revenuecat-managing-python-gil-324147931947 | |||
06:08 | Debunking the Myth: Why LLMs Are More Than “Simple Next Word Guessing” Algorithms https://medium.com/@enesesvetkuzucu/debunking-the-myth-why-llms-are-more-than-simple-next-word-guessing-algorithms-7d58d9fa1021 | |||
05:45 | Mixtral vs Mistral: A Comprehensive Review of LLMs, Pricing, and Use Cases https://medium.com/@getanakin/mixtral-vs-mistral-a-comprehensive-review-of-llms-pricing-and-use-cases-53ea9c21cb83 | |||
05:35 | How to Use Sonnet 3.5 API for Efficient Data Processing https://medium.com/@lisakim01/how-to-use-sonnet-3-5-api-for-efficient-data-processing-ca399fb8faa3 | |||
05:31 | Gen AI and LLM https://medium.com/@gauravverma.career/gen-ai-and-llm-60b1f4b3f391 | |||
04:52 | Parsing Bitcoin transaction data or: The Joys of using Cursor https://sacha-schwab.medium.com/parsing-bitcoin-transaction-data-or-the-joys-of-using-cursor-710b3f32c1b5 | |||
04:25 | How to Handle Mixed File Types in Langchain Document Loaders https://medium.com/@garysvenson09/how-to-handle-mixed-file-types-in-langchain-document-loaders-b5c04e8f80ad | |||
03:25 | Show HN: Wordllama – Things you can do with the token embeddings of an LLM https://github.com/dleemiller/WordLlama | |||
03:18 | How to Determine If FiveTran Is Built on Open Source https://medium.com/@asakisakamoto02/how-to-determine-if-fivetran-is-built-on-open-source-f770d1cf363b | |||
02:16 | How to Use Flat File Integration for Seamless Data Transfer https://medium.com/@tayloroakley/how-to-use-flat-file-integration-for-seamless-data-transfer-4cf86d038f41 | |||
01:45 | Mistral vs Opus: Large Language Models Comparison Guide https://medium.com/@getanakin/mistral-vs-opus-large-language-models-comparison-guide-b70f6697d8ad | |||
01:35 | How to Use OpenAI API for Fast and Efficient Responses https://medium.com/@lisakim01/how-to-use-openai-api-for-fast-and-efficient-responses-5bbd255d40be | |||
01:04 | DataGemma: enhancing numerical and statistical facts accuracy of LLM with RIG and RAG approaches on… https://medium.com/@techsachin/datagemma-enhancing-numerical-and-statistical-facts-accuracy-of-llm-with-rig-and-rag-approaches-on-066da70efe0e | |||
00:54 | Open Source Gems https://medium.com/sourcescribes/open-source-gems-f51435998767 | |||
00:41 | Case Study: Exploring Prompt Engineering in Retirement Planning with a GPT Assistant https://medium.com/@arthur.amorim0211/case-study-exploring-prompt-engineering-in-retirement-planning-with-a-gpt-assistant-3deff38d88dc | |||
00:27 | Efficient Summarization of Large Documents: Exploring Compression Techniques and Model Comparisons https://medium.com/@richik.ghosh/efficient-summarization-of-large-documents-exploring-compression-techniques-and-model-comparisons-09182b923dd0 | |||
00:25 | How to Load HTML Documents in LangChain: A Step-by-Step Guide https://medium.com/@garysvenson09/how-to-load-html-documents-in-langchain-a-step-by-step-guide-fd538dfc53ac | |||
00:00 | Day 14: Pair Programming with LLMs https://blog.gopenai.com/day-14-pair-programming-with-llms-57426caeb9e4 | |||
Saturday, 2024-09-14 | ||||
23:54 | Summary of the paper “MutaBot: A Mutation Testing Approach for Chatbots” https://medium.com/@k.e.elsayed/summary-of-the-paper-mutabot-a-mutation-testing-approach-for-chatbots-2b3e4f78ddf8 | |||
23:40 | How to Build and Automate the Deployment of a Generative AI Web Application Using Google Cloud https://nikita-kohli.medium.com/how-to-build-and-automate-the-deployment-of-a-generative-ai-web-application-using-google-cloud-4b45ea5d2943 | |||
23:21 | Mistral Large 2 French Open Source Model Newcomer Leading AI Innovation, Surpassing Llama3.1 https://beckmoulton.medium.com/mistral-large-2-french-open-source-model-newcomer-leading-ai-innovation-surpassing-llama3-1-78d99f45414a | |||
23:18 | How to InvokeAI Use the Second GPU for Enhanced Performance https://medium.com/@asakisakamoto02/how-to-invokeai-use-the-second-gpu-for-enhanced-performance-9c015507fdd5 | |||
22:16 | How to Use ActiveCampaign API Key for Integration Success https://medium.com/@tayloroakley/how-to-use-activecampaign-api-key-for-integration-success-f0f56487985e | |||
22:13 | LLM - Persona Pattern: Personalizzare le Interazioni per Risultati Più Rilevanti https://medium.com/@pasquale.verta/llm-e-il-pattern-di-persona-personalizzare-le-interazioni-per-risultati-pi%C3%B9-rilevanti-6aa41dc6067f | |||
22:05 | Chatbot System Design Using RAG: Key Components and Considerations https://mzeeshannawaz.medium.com/chatbot-system-design-using-rag-key-components-and-considerations-34f0bcb5c5c7 | |||
22:04 | Mapping NDCs to ATC-5 using a Large LanguaM (GPT o1-preview) https://medium.com/@pub_79863/mapping-ndcs-to-atc-5-using-a-large-languam-gpt-o1-preview-60dff41c13f2 | |||
21:55 | Agentic AI system: Building of a Tech Research agentic workflow using flowise https://medium.com/@odhitom09/agentic-ai-system-building-of-a-tech-research-agentic-workflow-using-flowise-b4eaf92c6a76 | |||
21:45 | Mistral vs Mistral Instruct: LLMs Review, Pricing & Use Cases https://medium.com/@getanakin/mistral-vs-mistral-instruct-llms-review-pricing-use-cases-a5f04501fafa | |||
21:35 | How to Use OpenAI API GPT-4 for Your Projects Effectively https://medium.com/@lisakim01/how-to-use-openai-api-gpt-4-for-your-projects-effectively-5f705387aac2 | |||
21:20 | LLM-Question Refinement Pattern: Ottimizzare le Interazioni con i Modelli Linguistici https://medium.com/@pasquale.verta/llm-e-il-pattern-di-raffinamento-delle-domande-ottimizzare-le-interazioni-con-i-modelli-f441a13677e4 | |||
21:12 | Sleeper AI Agents might sound insane, but they will become a reality one day and we’re not at all… https://medium.com/@lassetrevland/sleeper-ai-agents-might-sound-insane-but-they-will-become-a-reality-one-day-and-were-not-at-all-f25b5c87bebd | |||
21:00 | The safety paradox at the heart of OpenAI's "Strawberry" model https://www.vox.com/future-perfect/371827/openai-chatgpt-artificial-intelligence-ai-risk-strawberry | |||
20:57 | How to run Oobabooga in Docker? https://medium.com/@dmitrytrifonov/how-to-run-oobabooga-in-docker-d58d827b37ba | |||
20:25 | How to Navigate Langchain Documentation for Beginners https://medium.com/@garysvenson09/how-to-navigate-langchain-documentation-for-beginners-726e4e954870 | |||
19:49 | OpenAI’s O1: A New Era of Reasoning in AI https://blog.stackademic.com/openais-o1-a-new-era-of-reasoning-in-ai-a50b6237e380 | |||
19:31 | Oscar Health's early observations on OpenAI o1-preview https://www.hioscar.ai/blog/oscar-healths-early-observations-on-openai-o1-preview | |||
19:31 | Erweiterung des Prompt-Templates für Web-Recherchen https://medium.com/@soeren.bey/erweiterung-des-prompt-templates-f%C3%BCr-web-recherchen-e2a8d35a4d23 | |||
19:28 | Doge vs Blar: Not Your Usual Saturday Morning https://medium.com/@jose_82211/doge-vs-blar-not-your-usual-saturday-morning-d72fd4560cbd | |||
19:18 | How to InvokeAI Bulk Remove Missing Models Easily https://medium.com/@asakisakamoto02/how-to-invokeai-bulk-remove-missing-models-easily-22eaff4b5d18 | |||
18:24 | RAG Simplified!! https://medium.com/@tejeswar_79802/rag-simplified-657dc61bccd9 | |||
18:16 | How to Use an API Aggregator for Seamless Integration https://medium.com/@tayloroakley/how-to-use-an-api-aggregator-for-seamless-integration-8236643de30f | |||
18:07 | Building a Transformer with PyTorch https://medium.com/@girimanaskumar1998/building-a-transformer-with-pytorch-de65e3d0ee5e | |||
17:49 | Building a MultiModal Document Analysis Agent with Docling and LangChain https://medium.com/@techwithkrooz/building-a-multimodal-document-analysis-agent-with-docling-and-langchain-22c0d94267f5 | |||
17:45 | Mistral vs Llama 3: Large Language Models Review & Pricing https://medium.com/@getanakin/mistral-vs-llama-3-large-language-models-review-pricing-b8e575d15990 | |||
17:36 | How to Use OpenAI 4.0 API for Your Projects Effectively https://medium.com/@lisakim01/how-to-use-openai-4-0-api-for-your-projects-effectively-98d2773076f7 | |||
17:30 | Ready for production grade RAG?? https://medium.com/@adityachowdary5555/ready-for-production-grade-rag-3c20d765b14d | |||
17:24 | OpenAI Reasons 'o1' is a Better Name than 'Strawberry' https://spyglass.org/strawberry-openai-o1/ | |||
17:12 | Build a tokenizer for the Thai Language from scratch https://pub.towardsai.net/build-a-tokenizer-for-the-thai-language-from-scratch-0e4ea5f2a8b3 | |||
17:11 | LlamaIndex: Adding Personal Data to LLMs https://medium.com/@girimanaskumar1998/llamaindex-adding-personal-data-to-llms-1acdfb3623f8 | |||
17:01 | Top 8 Open-Source LLMs for 2024 and Their Uses https://medium.com/@girimanaskumar1998/top-8-open-source-llms-for-2024-and-their-uses-9339f535601f | |||
16:59 | Intelligent Conversations: Crafting a Custom AI Chatbot with your data https://medium.com/@kmbathija/intelligent-conversations-crafting-a-custom-ai-chatbot-with-your-data-c5cba57a50d0 | |||
16:39 | From GPT-3.5 vs. GPT-4 vs. Llama 3: Performance and Cost Analysis on Practical NLP Tasks https://medium.com/@jzljohn18_71393/from-gpt-3-5-vs-gpt-4-vs-llama-3-performance-and-cost-analysis-on-practical-nlp-tasks-b1b422a2567d | |||
16:37 | Typing Speed: The Overlooked Catalyst for Developer Productivity in the AI Era https://medium.com/@fauzulkc/typing-speed-the-overlooked-catalyst-for-developer-productivity-in-the-ai-era-67fdc5950955 | |||
16:37 | Typing Speed: The Overlooked Catalyst for Developer Productivity in the AI Era https://medium.com/elobyte-software/typing-speed-the-overlooked-catalyst-for-developer-productivity-in-the-ai-era-67fdc5950955 | |||
16:32 | RAG Simplified!! https://medium.com/@tejeswar_79802/rag-simplified-99dfce72c598 | |||
16:25 | How to Use DirectoryLoader Without CSV Headers in LangChain https://medium.com/@garysvenson09/how-to-use-directoryloader-without-csv-headers-in-langchain-7fb4fc36342a | |||
16:21 | OpenAI, Anthropic, Google employees support California AI bill https://www.axios.com/2024/09/09/openai-anthropic-deepmind-employees-ai-bill | |||
16:02 | Revolutionizing Personalized Medicine: How AI Tailors Treatments to Individual Needs https://pub.towardsai.net/revolutionizing-personalized-medicine-how-ai-tailors-treatments-to-individual-needs-1fc3c67c31af | |||
15:56 | Building a Sentiment-based News Article Summarizer with Flask and Transformers https://medium.com/@tirumalaphanendra11/building-a-sentiment-based-news-article-summarizer-with-flask-and-transformers-31dd149e69a7 | |||
15:52 | Should You Use Open Source Large Language Models? https://medium.com/@anandpawar26/should-you-use-open-source-large-language-models-ad5377e732ed | |||
15:21 | OpenAI’s o1 Mini vs o1 Preview: A Comprehensive Comparison https://sebastian-petrus.medium.com/openais-o1-mini-vs-o1-preview-a-comprehensive-comparison-b5d7b148dbda | |||
15:20 | Inside OpenAI’s O1: What’s Under the Hood? https://medium.com/@sai.aravind876/inside-openais-o1-what-s-under-the-hood-977bdfc9f429 | |||
15:18 | How to Install Frigate on QNAP Docker: Step-by-Step Guide https://medium.com/@asakisakamoto02/how-to-install-frigate-on-qnap-docker-step-by-step-guide-2c7bc2e58700 | |||
15:17 | What Are Knowledge Graphs? Your Gateway to Understanding Linked Data! https://hammad-munir.medium.com/what-are-knowledge-graphs-your-gateway-to-understanding-linked-data-110f7ac0e076 | |||
15:17 | Solving For the Invisible https://medium.com/@shantanudave/solving-for-the-invisible-fcbef7bced4e | |||
15:03 | Deploying LLM (Llama3) Chatbot on AWS Bedrock with Open WebUI Interface Using AWS ECS Fargate… https://medium.com/@hobballah.yasser/deploying-llm-llama3-chatbot-on-aws-bedrock-with-open-webui-interface-using-aws-ecs-fargate-5aee907e1ca0 | |||
15:02 | The Next Tech Revolution: Navigating the Future of Artificial General Intelligence (AGI) https://ai.gopubby.com/the-next-tech-revolution-navigating-the-future-of-artificial-general-intelligence-agi-d27e06aa8884 | |||
14:57 | Creating Task-Oriented Dialog systems with LangGraph and LangChain https://towardsdatascience.com/creating-task-oriented-dialog-systems-with-langgraph-and-langchain-fada6c9c4983 | |||
14:46 | What is Machine Learning and Generative AI? https://medium.com/@bibhup_mishra/what-is-machine-learning-and-generative-ai-e46f71299cb0 | |||
14:16 | How to Use the Trello API Key for Your Projects https://medium.com/@tayloroakley/how-to-use-the-trello-api-key-for-your-projects-a8e58065aba1 | |||
14:14 | Knowledge Distillation Using Qwen-7B and GPT-2 https://rabmcmenemy.medium.com/knowledge-distillation-using-qwen-7b-and-gpt-2-a339d6024f0e | |||
14:04 | Explaining how LLMs work in 7 levels of abstraction https://medium.com/@amgad-hasan/explaining-how-llms-work-in-7-levels-of-abstraction-3179de558686 | |||
14:01 | The Best RAG Stack to Date https://pub.towardsai.net/the-best-rag-stack-to-date-8dc035075e13 | |||
14:01 | Langchain application 1: summarize an article https://medium.com/@sean.liu.job/langchain-application-1-summarize-an-article-389e4c28b2b2 | |||
13:46 | Under the Hood of OpenAI o1: Architectural Innovations in Reasoning-Based AI https://medium.com/@codenze/under-the-hood-of-openai-o1-architectural-innovations-in-reasoning-based-ai-97c90ace525f | |||
13:45 | Mistral vs Claude: Comprehensive Review of LLMs, Pricing, and Use Cases https://medium.com/@getanakin/mistral-vs-claude-comprehensive-review-of-llms-pricing-and-use-cases-4076fea37377 | |||
13:35 | How to Use Open API Token for Secure Data Access https://medium.com/@lisakim01/how-to-use-open-api-token-for-secure-data-access-60597f45c83d | |||
12:43 | Unlocking New Revenue Streams by Modeling Your Knowledge with My Buddy AI https://medium.com/@gch_54589/unlocking-new-revenue-streams-by-modeling-your-knowledge-with-my-buddy-ai-b26853f5222e | |||
12:25 | How to Load Multiple File Types with DirectoryLoader in LangChain https://medium.com/@garysvenson09/how-to-load-multiple-file-types-with-directoryloader-in-langchain-2e933a7c6dc3 | |||
12:17 | A little about LLMs from My readings https://medium.com/@Mohamad_dev/a-little-about-llms-from-my-readings-5d1d6fa8e7c0 | |||
12:15 | How ChatGPT scanned 170k lines of code in seconds and saved me hours of work https://www.zdnet.com/article/how-chatgpt-scanned-170k-lines-of-code-in-seconds-and-saved-me-hours-of-work/ | |||
12:08 | Semantic kernel dynamically selecting plugin to execute https://towardsdev.com/semantic-kernel-dynamically-selecting-plugin-to-execute-e43479c7de1e | |||
11:42 | Building a Customized AI model for Invoking APIs using LangChain and LLM based on user query. https://medium.com/@vishnurajs10/building-a-customized-ai-model-for-invoking-apis-using-langchain-and-llm-based-on-user-query-3d24540ec676 | |||
11:41 | How do you ensure the security of your LLM? https://medium.com/@ysfckmk/how-do-you-ensure-the-security-of-your-llm-c71b08f269bf | |||
11:33 | The Impact of AI and Automation on Job Quality: Lessons from History https://medium.com/@naveedspg/the-impact-of-ai-and-automation-on-job-quality-lessons-from-history-0b110c9d68a8 | |||
11:18 | How to Install Frigate on QNAP Container: Step-by-Step Guide https://medium.com/@asakisakamoto02/how-to-install-frigate-on-qnap-container-step-by-step-guide-f3393f5f5b4e | |||
10:47 | Keeping Up with the AI Race — Bookmark this Leaderboard-Page to Track the Best AI Models https://towardsdatascience.com/keeping-up-with-the-ai-race-bookmark-this-leaderboard-page-to-track-the-best-ai-models-da7606532ef7 | |||
10:42 | Fine-Tune Gemma 2 9b with Keras and LoRA (Part 3) https://medium.com/@rbinsafi/fine-tune-gemma-2-9b-with-keras-and-lora-part-3-331c84e7b0c7 | |||
10:28 | Building an MCQ Quiz Generator from PDFs Using Cursor https://medium.com/@munnayuva03/building-an-mcq-quiz-generator-from-pdfs-using-cursor-30fd0a89b8f7 | |||
10:27 | The Rise of OpenAI’s o1 Model: A New Era in AI and Coding https://s-hash-wat.medium.com/the-rise-of-openais-o1-model-a-new-era-in-ai-and-coding-b58cae5862f8 | |||
10:16 | How to Use a Unified API for Seamless Integration https://medium.com/@tayloroakley/how-to-use-a-unified-api-for-seamless-integration-933a443a57ce | |||
09:46 | Generative AI untuk Image Captioning: Implementasi LLM dengan Hugging Face di Jupyter Notebook https://medium.com/@santoso._san/generative-ai-untuk-image-captioning-implementasi-llm-dengan-hugging-face-di-jupyter-notebook-2547f8b69544 | |||
09:45 | Meta-Llama 3.1: Comparing Instruct vs Standard Model Review https://medium.com/@getanakin/meta-llama-3-1-comparing-instruct-vs-standard-model-review-7b9188ed3325 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803