LLM News and Articles
| Wednesday, 2024-07-10 | ||||
| 16:49 | You probably don’t need GraphRAG https://medium.com/@amrwrites/you-probably-dont-need-graphrag-0bc9cf671db1 | |||
| 16:44 | Create a Text Summarization App with Gradio https://medium.com/@emhaihsan/create-a-text-summarization-app-with-gradio-76e9a9cc76b3 | |||
| 16:31 | Rank RAG // not a surprise https://sbagency.medium.com/rank-rag-not-a-surprise-1e8a9dfb81d9 | |||
| 16:19 | A bird’s-eye view on the evolution of language models for text generation https://towardsdatascience.com/a-birds-eye-view-on-the-evolution-of-language-models-for-text-generation-9b6b3fcb96a4 | |||
| 15:54 | Goodbye, OpenAI https://medium.com/@askverablog/goodbye-openai-b4dcaebb9840 | |||
| 15:45 | TheoremLlama: An End-To-End Framework to Train a General-Purpose Large Language Model to Become a Lean4 Expert https://www.marktechpost.com/2024/07/10/theoremllama-an-end-to-end-framework-to-train-a-general-purpose-large-language-model-to-become-a-lean4-expert/ | |||
| 15:43 | Microsoft gives up OpenAI board observer seat https://www.axios.com/2024/07/10/microsoft-openai-board-seat-observer | |||
| 15:39 | How to set up Django from Scratch with Celery + Channels + Redis + Docker — Real Time Django… https://medium.com/@cubode/how-to-set-up-django-from-scratch-with-celery-channels-redis-docker-real-time-django-0845eb7e083c | |||
| 15:35 | Easier development of LLM applications with motleycache https://medium.com/motleycrew-ai/easier-development-of-llm-applications-with-motleycache-fb169e021d34 | |||
| 15:26 | OpenAI board shakeup: Microsoft out, Apple backs away https://arstechnica.com/information-technology/2024/07/openai-board-shakeup-microsoft-out-apple-backs-away-amid-ai-partnership-scrutiny/ | |||
| 15:04 | Show HN: MailMate GPT plugin – Use ChatGPT/Claude to write emails in MailMate https://github.com/mickn/mailmate_ai_assistant | |||
| 15:01 | Poetic Web Magic with Amazon Bedrock https://medium.com/@Gowtham_CP/poetic-web-magic-with-amazon-bedrock-dbf70afba192 | |||
| 14:48 | OpenAI and Los Alamos National Laboratory announce bioscience research https://openai.com/index/openai-and-los-alamos-national-laboratory-work-together/ | |||
| 14:32 | Enhancing LLMs: A Journey like TUI’s https://medium.com/tuitech/enhancing-llms-a-journey-like-tuis-53bbc1f33530 | |||
| 14:25 | The Monster of FrankenstAIn https://medium.com/@fractionai/the-monster-of-frankenstain-12525e53ea7e | |||
| 14:20 | A Layman’s Dive into LLMs: Decoding The Dreams Coming Alive. Part 1 — The History https://medium.com/@mouryag99/a-laymans-dive-into-llms-decoding-the-dreams-coming-alive-part-1-the-history-dfeede81de7a | |||
| 14:17 | How to build a multi-agent content development team using LangGraph https://medium.com/indiciumtech/how-to-build-a-multi-agent-content-development-team-using-langgraph-d062ce4051c3 | |||
| 13:50 | Are Your Generative AI Models Falling Short? https://medium.com/@mariejeannegroot/are-your-generative-ai-models-falling-short-e84df3c28faa | |||
| 13:49 | Unlocking the Power of Meta-Learning: Crafting a Multi-Task LLM Model https://medium.com/@geosar/unlocking-the-power-of-meta-learning-crafting-a-multi-task-llm-model-0550e82d7b4c | |||
| 13:43 | Microsoft and Apple drop OpenAI seats amid antitrust scrutiny https://www.ft.com/content/ecfa69df-5d1c-4177-9b14-a3a73072db12 | |||
| 13:42 | How to Set Up and Run text-generation-webui on a GPU-Powered VM (vast.ai) https://medium.com/@jacktheflipper/how-to-set-up-and-run-text-generation-webui-on-a-gpu-powered-vm-vast-ai-7e8d249d242a | |||
| 13:36 | Skild AI: 0M Funding Round for Revolutionary feats in future Robotics https://medium.com/@ssark/skild-ai-300m-funding-round-for-revolutionary-feats-in-future-robotics-d1f4787fddb4 | |||
| 13:22 | AIAnthropic’s Claude Introduces a Prompt Playground to Boost Your AI Apps https://marketinginnovation.medium.com/aianthropics-claude-introduces-a-prompt-playground-to-boost-your-ai-apps-1334d3a9bd77 | |||
| 13:15 | How to Set Up and Run Ollama on a GPU-Powered VM (vast.ai) https://medium.com/@jacktheflipper/how-to-set-up-and-run-ollama-on-vast-ai-9bf91ee10243 | |||
| 13:07 | Large Language Model Concepts for Curious Users: The Static, Stateless, and Directional Nature of… https://medium.com/@daveziegler/large-language-model-concepts-for-curious-users-the-static-stateless-and-directional-nature-of-a0f4d8ec2972 | |||
| 13:03 | The most cited NLP papers each year https://thebestnlppapers.com/ | |||
| 12:59 | Introducing Lavita AI’s Medical Evaluation Sphere https://lavita-ai.medium.com/introducing-lavita-ais-medical-evaluation-sphere-bf01e3546b04 | |||
| 12:56 | How to Kickstart Your AI Learning Journey: Practical Steps and Tips https://medium.com/@hrleek/how-to-kickstart-your-ai-learning-journey-practical-steps-and-tips-53f9fcd3a75d | |||
| 12:50 | Introduction to Large Language Model https://medium.com/@sampratap/introduction-to-large-language-model-d3e069bf41d1 | |||
| 12:19 | Language Processing Unit: LPU https://ai.plainenglish.io/language-processing-unit-lpu-30bac307be42 | |||
| 11:48 | Steps for Developing Efficient Large Language Model (LLM) Applications https://medium.com/@jennifer.wales22/steps-for-developing-efficient-large-language-model-llm-applications-1c9cc347a0dc | |||
| 11:17 | LangFuse with LLM for RAG: A Comprehensive Guide https://medium.com/@pysquad/langfuse-with-llm-for-rag-a-comprehensive-guide-7a77b69e8d39 | |||
| 11:01 | [The best LLM?] Gen-3’s Astonishing Transitions: 10 Wild Examples of AI Mastery https://yukitaylor00.medium.com/the-best-llm-gen-3s-astonishing-transitions-10-wild-examples-of-ai-mastery-bf9c91ed8f42 | |||
| 10:55 | Claude 3 Haiku and Other Budget King LLMs https://medium.com/@marketing_novita.ai/claude-3-haiku-and-other-budget-king-llms-df32c1bb0be5 | |||
| 10:54 | State-of-art retrieval-augmented LLM: bge-large-en-v1.5 https://medium.com/@marketing_novita.ai/state-of-art-retrieval-augmented-llm-bge-large-en-v1-5-4cd5abbcbf0a | |||
| 09:53 | The Need for Explainability and Simulation in Preference Optimization https://towardsdatascience.com/the-need-for-explainability-and-simulation-in-preference-optimization-bcc43f010a32 | |||
| 09:49 | Should LLMs have unit tests? https://blog.gopenai.com/should-llms-have-unit-tests-2d378358990e | |||
| 09:30 | Apple Drops OpenAI Board Observer Role Amid Regulatory Scrutiny https://www.macrumors.com/2024/07/10/apple-drops-openai-board-observer-role/ | |||
| 09:20 | Practical example of LLM’s hallucinating ? https://justlike.medium.com/practical-example-of-llms-hallucinating-bbccc4f8c906 | |||
| 09:14 | Intel Extension for Transformers & PyTorch LLM Optimisation https://medium.com/@agarapuramesh/intel-extension-for-transformers-pytorch-llm-optimisation-4d43ee23da4a | |||
| 08:53 | Inside GraphRAG: Analyzing Microsoft’s Innovative Framework for Knowledge Graph Processing https://medium.com/percena/inside-graphrag-analyzing-microsofts-innovative-framework-for-knowledge-graph-processing1-6f84deec5499 | |||
| 07:53 | Exploring Medusa and Multi-Token Prediction https://towardsdatascience.com/exploring-medusa-and-multi-token-prediction-de7f8312e4a7 | |||
| 07:43 | Multi-Modal Protein Language Models: Protein Function Prediction https://medium.com/krishna-yerramsetty/multi-modal-protein-language-models-protein-function-prediction-14c768bca14b | |||
| 07:33 | Presenting New CellStrat Course : “Prompt Engineering for Generative AI” https://cellstrat.medium.com/presenting-new-cellstrat-course-prompt-engineering-for-generative-ai-72af4e77b14f | |||
| 07:31 | LLMRoute : Simplifying & Optimizing Large Language Model Deployment https://medium.com/@tiro2000/llmroute-simplifying-optimizing-large-language-model-deployment-e531a1614997 | |||
| 07:20 | OpZest Ecosystem — Lite paper https://medium.com/@operationzest/opzest-ecosystem-lite-paper-009c6126398c | |||
| 06:20 | Introducing LightRAG — The PyTorch Library for LLM Applications https://liyin2015.medium.com/introducing-lightrag-the-pytorch-library-for-llm-applications-8c1d3dcd5111 | |||
| 05:33 | DexGem’s LLMs https://medium.com/@dexgemai/dexgems-llms-6bb8bf5e5b27 | |||
| 05:32 | Asking an LLM to build a simple web tool https://eli.thegreenplace.net/2024/asking-an-llm-to-build-a-simple-web-tool/ | |||
| 05:31 | Lookback-lens: Detect and Mitigate Hallucinations in LLMs with Attention Maps https://medium.com/@techsachin/lookback-lens-detect-and-mitigate-hallucinations-in-llms-with-attention-maps-8241a06d3f2c | |||
| 05:13 | Mastering the Seven Sins: Effective Evaluation Strategies for Large Language Models https://ppujari.medium.com/mastering-the-seven-sins-effective-evaluation-strategies-for-large-language-models-c6edff02b855 | |||
| 04:49 | Mistral 7B vs. Llama 3 70B vs. Gemma 2 9B: A Comprehensive Benchmark Showdown https://medium.com/@samir20/mistral-7b-vs-llama-3-70b-vs-gemma-2-9b-a-comprehensive-benchmark-showdown-9c3128f24b23 | |||
| 03:42 | Optimise Large * Models in Production https://ravishtiwari.medium.com/improve-large-model-inference-in-production-8e195e81de86 | |||
| 03:36 | AI ChatBots are Running RAGged https://medium.com/@dylanabrock/ai-chatbots-are-running-ragged-b97963c47f18 | |||
| 03:13 | Route LLM: Learning to route LLMs with Preference data https://medium.com/@sulbha.jindal/route-llm-learning-to-route-llms-with-preference-data-53361ceb9c43 | |||
| 02:50 | LLaSA: Large Multimodal Agent for Human Activity Analysis Through Wearable Sensors https://medium.com/@positive_brandy_tortoise_947/llasa-large-multimodal-agent-for-human-activity-analysis-through-wearable-sensors-4c96de20b040 | |||
| 02:11 | Ollama 0.2 — revolutionizing local model management with concurrency https://medium.com/@simeon.emanuilov/ollama-0-2-revolutionizing-local-model-management-with-concurrency-2318115ce961 | |||
| 02:08 | PAPER SUMMARY: How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation https://medium.com/@msayeedi212049/paper-summary-how-good-are-gpt-models-at-machine-translation-a-comprehensive-evaluation-9e7a2ca9fe08 | |||
| 02:03 | From GPT-4 to AGI: Counting the OOMs https://situational-awareness.ai/from-gpt-4-to-agi/#Compute | |||
| 01:41 | Running GraphRag by Microsoft Locally for Free: The Ultimate Tutorial Part 2 https://medium.com/@lompojeanolivier/running-graphrag-by-microsoft-locally-for-free-the-ultimate-tutorial-part-2-af99489c0f32 | |||
| 01:12 | Unveiling the Power of Chroma DB: A Comprehensive Guide to Vector Databases https://mayursurani.medium.com/unveiling-the-power-of-chroma-db-a-comprehensive-guide-to-vector-databases-b6584edfc1b5 | |||
| 00:45 | ChatGPT System Prompts Analysis — How OpenAI LLMs use Persistent Memory, Tool Usage, Code… https://medium.com/@sawradip0/chatgpt-system-prompts-analysis-how-openai-llms-use-persistent-memory-tool-usage-code-e6022cd8c2ea | |||
| 00:38 | Mistral’s Text Generation with Different Message Roles https://medium.com/@izzybreezylearn/mistrals-text-generation-with-different-message-roles-a5bdef0321cc | |||
| 00:35 | RouteLLM: A framework for serving and evaluating LLM routers https://github.com/lm-sys/RouteLLM | |||
| 00:11 | Running GraphRag by Microsoft Locally for Free: The Ultimate Tutorial Part 1 https://medium.com/@lompojeanolivier/running-graphrag-by-microsoft-locally-for-free-the-ultimate-tutorial-part-1-7bd113937465 | |||
| 00:00 | Experimenting with Automatic PII Detection on the Hub using Presidio https://huggingface.co/blog/presidio-pii-detection | |||
| 00:00 | Announcing New Hugging Face and Keras NLP integration https://huggingface.co/blog/keras-nlp-integration | |||
| Tuesday, 2024-07-09 | ||||
| 23:48 | Implement a Bedrock Java Client with the AWS SDK https://medium.com/@tbwin/implement-a-bedrock-java-client-with-the-aws-sdk-73680e2f9d15 | |||
| 23:44 | Optimizing deep learning training for language tasks https://medium.com/@rakesh9177/optimizing-deep-learning-training-for-language-tasks-de3ce079a285 | |||
| 22:01 | Training LLMs with Synthetic Data https://pub.towardsai.net/training-llms-with-synthetic-data-649c34337f06 | |||
| 21:15 | Upgrade Your Code Reviews: Let an AI Handle the Mundane https://rajath8venkatesh.medium.com/upgrade-your-code-reviews-let-an-ai-handle-the-mundane-39612d44dc93 | |||
| 20:25 | Large Language Model Basics for Casual Users: Tokenization https://medium.com/@daveziegler/large-language-model-basics-for-casual-users-tokenization-f6ab74ae0e60 | |||
| 20:22 | Large Langauge Model Basics Concepts for Casual Users: Tokenization https://medium.com/@daveziegler/large-langauge-model-basics-concepts-for-casual-users-tokenization-f55869026b3f | |||
| 20:12 | Libchatty: A faster ChatGPT wrapper in pure C https://github.com/yisding/libchatty | |||
| 20:05 | The future is not prompt engineered https://medium.com/design-debt-club/the-future-is-not-prompt-engineered-9847e5535b44 | |||
| 19:41 | GPT-4 é confundido com ser humano https://medium.com/@carolinescherer/gpt-4-%C3%A9-confundido-com-ser-humano-d6abe5d2ff89 | |||
| 19:40 | A RAG system backpacked with Feedback Intelligence https://medium.com/feedback-intelligence/a-rag-system-backpacked-with-feedback-intelligence-c2a04c85f986 | |||
| 19:14 | Scaling Law Of Language Models https://towardsdatascience.com/scaling-law-of-language-models-5759de7f830c | |||
| 19:02 | LLM OS and Software 2.0: The Dawn of a New Computing Era https://mansour-damanpak.medium.com/llm-os-and-software-2-0-the-dawn-of-a-new-computing-era-12d59a007ef8 | |||
| 18:19 | Show HN: Perplexity Without the Filler https://justtheanswer.vercel.app/ | |||
| 18:13 | Show HN: LLM agents to extract web data https://twitter.com/asimdotshrestha/status/1810720478111371581 | |||
| 18:02 | Structured Financial data Extraction from Unstructured data https://pub.towardsai.net/structured-financial-data-extraction-from-unstructured-data-ca2c8d166de6 | |||
| 17:53 | AI Fashion Stylist: Virtual Stylist Solution Using LLama and Gradio https://medium.com/@abuoghosa/ai-fashion-stylist-virtual-stylist-solution-using-llama-and-gradio-0ed3a2a571f7 | |||
| 17:49 | Efficient RAG for Mixed Context Texts with Indexify’s Framework, Gemini’s 1M Context & Arctic’s… https://medium.com/google-developer-experts/efficient-rag-for-mixed-context-texts-with-indexifys-framework-gemini-s-1m-context-arctic-s-df2882aad576 | |||
| 17:37 | Deep Dive into LSTMs & xLSTMs by Hand ✍️ https://towardsdatascience.com/deep-dive-into-lstms-xlstms-by-hand-%EF%B8%8F-c33e638bebb1 | |||
| 17:07 | Revolutionizing Product Design and Concept Design with Generative AI https://medium.com/@bhargavaganti/revolutionizing-product-design-and-concept-design-with-generative-ai-aec555b19d47 | |||
| 16:58 | Breaking the Context Barrier: Tackling the Context Length Limitation in GPT Models https://medium.com/@bhargavaganti/breaking-the-context-barrier-tackling-the-context-length-limitation-in-gpt-models-9baee5301ab3 | |||
| 16:52 | Implementing ‘From Local to Global’ GraphRAG with Neo4j and LangChain: Constructing the Graph https://medium.com/neo4j/implementing-from-local-to-global-graphrag-with-neo4j-and-langchain-constructing-the-graph-73924cc5bab4 | |||
| 16:49 | Show HN: Perplexity for work that's privacy-focused https://www.usefindr.com/ | |||
| 16:46 | Exploring Large Language Models (LLMs) https://medium.com/@er.sharmaanubhav05/exploring-large-language-models-llms-4d44d6c6ba55 | |||
| 16:43 | How to Create APIs for AutoGen https://levelup.gitconnected.com/how-to-create-apis-for-autogen-ffb63e17e8a0 | |||
| 16:39 | Embrace your latest AI programmer /assistant— Claude 3.5 with Artifacts! https://johnny0116.medium.com/embrace-your-latest-ai-programmer-assistant-claude-3-5-with-artifacts-6a4012d55ff8 | |||
| 16:31 | ModelFusion: Revolutionizing AI Access with Unbeatable Value https://medium.com/@modelfusion/modelfusion-revolutionizing-ai-access-with-unbeatable-value-f9318cb5803c | |||
| 16:12 | NVIDIA Introduces RankRAG: A Novel RAG Framework that Instruction-Tunes a Single LLM for the Dual Purposes of Top-k Context Ranking and Answer Generation in RAG https://www.marktechpost.com/2024/07/09/nvidia-introduces-rankrag-a-novel-rag-framework-that-instruction-tunes-a-single-llm-for-the-dual-purposes-of-top-k-context-ranking-and-answer-generation-in-rag/ | |||
| 16:02 | Podcast: How to Evaluate LLMs and RAG Applications with Pasquale Antonante https://odsc.medium.com/podcast-how-to-evaluate-llms-and-rag-applications-with-pasquale-antonante-eb46e9260663 | |||
| 15:47 | Taking Control: Setting Up Your Own AI Chatbot for Privacy-Focused Conversations https://santhoshsundar.medium.com/taking-control-setting-up-your-own-ai-chatbot-for-privacy-focused-conversations-ba93a880fb51 | |||
| 15:45 | Our child has just started spelling. https://medium.com/@salihturkoglu/our-child-has-just-started-spelling-cf6405ddbe3b | |||
| 15:20 | Build and Deploy a Multimodal Chatbot with Gemini API https://medium.com/@turna.fardousi/building-a-multimodal-chatbot-with-gemini-api-8015bfbee538 | |||
| 15:19 | Are LLMs overrated? https://medium.com/@kaspar_26936/are-llms-overrated-e3923bec3885 | |||
| 15:15 | Optimizing your AI Deployment: An Analysis of Databricks’ Pay-Per-Token and Provisioned Throughput… https://medium.com/tech-trends-genai-ml/optimizing-your-ai-deployment-an-analysis-of-databricks-pay-per-token-and-provisioned-throughput-940c8eeacf29 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803