LLM News and Articles
| Friday, 2024-07-19 | ||||
| 16:21 | Remember That? How Semantic Caching Supercharges AI Assistants https://medium.com/@ganeshkannappan/remember-that-how-semantic-caching-supercharges-ai-assistants-246cbeb14af1 | |||
| 16:14 | Rapid protein evolution by few-shot learning with a protein language model https://www.biorxiv.org/content/10.1101/2024.07.17.604015v1 | |||
| 16:12 | GPT-4o-mini is out! Let’s see how it performs https://medium.com/@tihomir.manushev/gpt-4o-mini-is-out-lets-see-how-it-performs-c459fbd016cb | |||
| 16:06 | Considerations for building an AI-driven for Document Search and Retrieval System https://medium.com/@paul.ekwere/considerations-for-building-an-ai-driven-for-document-search-and-retrieval-system-88d7b20e976e | |||
| 15:56 | LangChain in Chains #30: Document Chatbots https://medium.com/@okanyenigun/langchain-in-chains-30-document-chatbots-3918bac29a26 | |||
| 15:51 | Choosing the Best Structured Output Parser Approach | 3 Ways To Generate Structured Output https://kaushikshakkari.medium.com/choosing-the-best-structured-output-parser-approach-3-ways-to-generate-structured-output-d9686482729c | |||
| 15:51 | Choosing the Best Structured Output Parser Approach | 3 Ways To Generate Structured Output https://blog.gopenai.com/choosing-the-best-structured-output-parser-approach-3-ways-to-generate-structured-output-d9686482729c | |||
| 15:14 | Understanding Large Language Models : Chapter 1- Transformers and Transformer block. https://viraajkadam.medium.com/understanding-large-language-models-chapter-1-transformers-and-transformer-block-a6d65462ddfe | |||
| 15:12 | Meta won't release its multimodal Llama AI model in the EU https://www.theverge.com/2024/7/18/24201041/meta-multimodal-llama-ai-model-launch-eu-regulations | |||
| 15:04 | Fine-tuning LLMs On Educational Datasets- An Overview https://medium.com/@balajiwork01/fine-tuning-llms-on-educational-datasets-an-overview-54d24b55bde7 | |||
| 15:02 | Apple Open-Sources LLM DCLM-7B https://huggingface.co/apple/DCLM-7B | |||
| 14:49 | Enhancing Contextual Understanding with ReALM: A Novel Method for Conversational Agents https://vishwanathkamath.medium.com/enhancing-contextual-understanding-with-realm-a-novel-method-for-conversational-agents-75a3e05cf8a6 | |||
| 14:38 | RAG-boosted with Knowledge Graph https://medium.com/totalenergies-digital-factory/rag-boosted-with-knowledge-graph-60b5f4c5afcb | |||
| 14:34 | Massive Windows Outage Causes Global Chaos https://autoblogs.medium.com/massive-windows-outage-causes-global-chaos-cf7eb351cc3d | |||
| 14:31 | Have you ever thought that Artificial Intelligence was some kind of black magic? https://andreabelvedere.medium.com/have-you-ever-thought-that-artificial-intelligence-was-some-kind-of-black-magic-1b7e05591b0a | |||
| 14:18 | Bridging Two Worlds: How to Unite Symbolic and Connectionist AI for the Future of LLM-Empowered… https://medium.com/@wwzzyy9982/bridging-two-worlds-how-to-unite-symbolic-and-connectionist-ai-for-the-future-of-llm-empowered-5d6ec95ceccd | |||
| 14:02 | AI Hallucinations https://pub.towardsai.net/ai-hallucinations-6d0091726b86 | |||
| 13:54 | Worldwide IT Blackout https://autoblogs.medium.com/worldwide-it-blackout-e7d4643a1915 | |||
| 13:51 | Multimodal Retrieval Augmented Generation for Sustainable Finance — With Code https://medium.com/artificial-corner/multimodal-retrieval-augmented-generation-for-sustainable-finance-with-code-5a910f3b666c | |||
| 12:46 | Optimizing LLMs with RLHF https://medium.com/feedback-intelligence/optimizing-llms-with-rlhf-c1ebc7d998ad | |||
| 12:15 | Fine-Tuning an LLM vs. RAG Approach https://medium.com/@way2mhemanth/fine-tuning-an-llm-vs-rag-approach-55e82b5e8b71 | |||
| 12:14 | Transforming Robot Programming with Language AI https://medium.com/@haitham.bouammar71/transforming-robot-programming-with-language-ai-c8ed974c4df5 | |||
| 12:00 | Exploring the Frontiers of Text Segmentation for Better RAG Systems https://medium.com/@hajar.mousannif/exploring-the-frontiers-of-text-segmentation-for-better-rag-systems-1b9f9af49258 | |||
| 11:34 | Understand GPT Tokens and Models Comparison https://blog.gopenai.com/understand-gpt-tokens-and-models-comparison-16acc771a01c | |||
| 11:26 | Enhancing Mathematical Reasoning in AI: Integrating LLMs with Monte Carlo Tree Search https://medium.com/@chaudharysahil379/enhancing-mathematical-reasoning-in-ai-integrating-llms-with-monte-carlo-tree-search-b3ef188cba9a | |||
| 11:16 | Self-Attention Mechanism In Transformers https://medium.com/@govindarajpriyanthan/self-attention-mechanism-in-transformers-1e46af9e1afb | |||
| 11:12 | Wolfram LLM Benchmarking Project https://www.wolfram.com/llm-benchmarking-project/ | |||
| 11:12 | Refining the Role of GPT-4 LLM in Virtual Internships https://medium.com/@rishitmayank/refining-the-role-of-gpt-4-llm-in-virtual-internships-f4bdb5798ea3 | |||
| 10:43 | Transformers in Large Language Model https://medium.com/version-1/transformers-in-large-language-model-2f7d485f50b0 | |||
| 10:26 | Literature Review Generation using Llama and Arxiv https://medium.com/@khaoujai/literature-review-generation-using-llama-and-arxiv-8a25aecb3f04 | |||
| 10:19 | Simplify LLM Quantization Process for Success https://medium.com/@marketing_novita.ai/simplify-llm-quantization-process-for-success-7126c26633df | |||
| 10:09 | How Structure and Language Choices Impact Prompt Engineering for LLMs https://medium.com/@gprdino/how-structure-and-language-choices-impact-prompt-engineering-for-llms-8dd712421bd9 | |||
| 10:01 | LLM as a Service: Your Partner in LM Model Development https://medium.com/@krishani_70219/llm-as-a-service-your-partner-in-lm-model-development-302e2c72c054 | |||
| 09:31 | Master LLM Sentiment Analysis: A Simple Guide https://medium.com/@marketing_novita.ai/master-llm-sentiment-analysis-a-simple-guide-a9692001e780 | |||
| 09:15 | DotaMath: Advancing LLMs’ Mathematical Reasoning Through Decomposition and Self-Correction https://www.marktechpost.com/2024/07/19/dotamath-advancing-llms-mathematical-reasoning-through-decomposition-and-self-correction/ | |||
| 09:00 | OpenAI is releasing a cheaper, smarter model. ChatGPT 4o mini launches today https://www.theverge.com/2024/7/18/24200714/openai-new-cheaper-smarter-model-gpt-4o-mini | |||
| 09:00 | This Survey Paper Presents a Comprehensive Review of LLM-based Text-to-SQL https://www.marktechpost.com/2024/07/19/this-survey-paper-presents-a-comprehensive-review-of-llm-based-text-to-sql/ | |||
| 08:59 | The Art of Prompt Engineering https://medium.com/@Datafied/the-art-of-prompt-engineering-4f175f21835a | |||
| 08:40 | How to Build a RAG-Powered Chatbot with Google Gemini and MyScaleDB https://medium.com/@myscale/how-to-build-a-rag-powered-chatbot-with-google-gemini-and-myscaledb-79c0024cd237 | |||
| 08:34 | OpenAI Unveils Cost-Effective GPT-4o Mini: A Game-Changer for Developers and Startups https://medium.com/ai-news-nuggets/openai-unveils-cost-effective-gpt-4o-mini-a-game-changer-for-developers-and-startups-10a96bdbd1da | |||
| 08:33 | Dialogue with Claude 7 https://medium.com/@chatc3po/dialogue-with-claude-7-1d43c23e8d17 | |||
| 08:21 | Crunching Nonsense: ChatGPT and Data Analysis https://medium.datasquirrel.ai/crunching-nonsense-chatgpt-and-data-analysis-3198f14b5338 | |||
| 08:17 | Lessons Learned from Week 3 of the LLM Zoomcamp: Vector Search and Embeddings https://hunglethanh.medium.com/lessons-learned-from-week-3-of-the-llm-zoomcamp-vector-search-and-embeddings-32d3b31dd8b9 | |||
| 08:14 | How to Run InternLM2 Locally: A Comprehensive Guide https://towards-agi.medium.com/how-to-run-internlm2-locally-a-comprehensive-guide-e1aad4044956 | |||
| 08:12 | How to run LLMs on CPU-based systems https://medium.com/@simeon.emanuilov/how-to-run-llms-on-cpu-based-systems-1623e04a7da5 | |||
| 08:06 | How to Run Mistral NeMo 12B Locally: A Comprehensive Guide https://towards-agi.medium.com/how-to-run-mistral-nemo-12b-locally-a-comprehensive-guide-75b74510dbff | |||
| 07:34 | Enhancing Model Capacity with Mixture-of-Experts: The Rise of Mixtral 8x7B https://vishwanathkamath.medium.com/enhancing-model-capacity-with-mixture-of-experts-the-rise-of-mixtral-8x7b-78dfc79cb64a | |||
| 07:24 | Mem0: The Missing Link in Long-Term AI Interactions https://medium.com/@omkamal/mem0-the-missing-link-in-long-term-ai-interactions-4e89e906d30c | |||
| 07:17 | Retrieval-Augmented Thoughts: Revolutionizing Long-Horizon Tasks with Retrieval-Augmented Thoughts https://vishwanathkamath.medium.com/retrieval-augmented-thoughts-revolutionizing-long-horizon-tasks-with-retrieval-augmented-thoughts-500a162b846d | |||
| 07:10 | Leveraging Large Language Models (LLMs) in AWS for Advanced Data Recommendation Systems https://blog.stackademic.com/leveraging-large-language-models-llms-in-aws-for-advanced-data-recommendation-systems-73fbb1db3b7a | |||
| 07:06 | The Rise of the AI LLMs https://medium.com/@Nilabh/the-rise-of-the-ai-llms-644b262e67f9 | |||
| 06:23 | Can TTT models beat transformers? Unveiling Learning at testing for the next frontier in AI https://medium.com/@justinliu1205/can-ttt-models-beat-transformers-unveiling-learning-at-testing-for-the-next-frontier-in-ai-b7423065d1b1 | |||
| 06:18 | Introducing ELM Turbo: Next-generation Efficient, Decomposable LLMs https://medium.com/sujith-ravi/introducing-elm-turbo-next-generation-efficient-decomposable-llms-a2347bd08676 | |||
| 06:17 | A Comprehensive Analysis of LoRA Variants https://medium.com/@atharv6f_47401/a-comprehensive-analysis-of-lora-variants-b0eee98fc9e1 | |||
| 06:12 | Build a scalable RAG ingestion pipeline using 74.3% less code https://medium.com/decodingml/build-a-scalable-rag-ingestion-pipeline-using-74-3-less-code-ac50095100d6 | |||
| 05:51 | What is GPT-4o mini and what does it mean for Finance and FP&A https://christianmartinezfinancialfox.medium.com/what-is-gpt-4o-mini-and-what-does-it-mean-for-finance-and-fp-a-3576edc11272 | |||
| 05:45 | Building an LLM Chatbot with SQL Integration https://medium.com/@raipragya256/building-an-llm-chatbot-with-sql-integration-9ee0c9d3df89 | |||
| 05:41 | GPT-40 Mini: Advancing Cost-Efficient Intelligence https://medium.com/@manoranjan.rajguru/gpt-40-mini-advancing-cost-efficient-intelligence-aee5957ff95f | |||
| 04:48 | Understanding the Training of Large Language Models (LLMs) https://medium.com/@siddharthkharche/understanding-the-training-of-large-language-models-llms-6125cf801fdd | |||
| 04:37 | The Z Hypothesis: A Unified Framework for Human and AI Cognition https://medium.com/@greyboi/the-z-hypothesis-a-unified-framework-for-human-and-ai-cognition-f9d823982760 | |||
| 04:16 | Mathstral: 7B LLM designed for math reasoning and scientific discovery https://mistral.ai/news/mathstral/ | |||
| 04:16 | Deepset-Mxbai-Embed-de-Large-v1 Released: A New Open Source German/English Embedding Model https://www.marktechpost.com/2024/07/18/deepset-mxbai-embed-de-large-v1-released-a-new-open-source-german-english-embedding-model/ | |||
| 04:05 | Show HN: ChatGPT Chrome Extension to Keep Temporary Chat Enabled https://github.com/EliseiNicolae/chatgpt-always-temporary-chat-on | |||
| 02:37 | OpenAI Releases GPT-4o Mini — A Cheap and Fast Small Language Model https://generativeai.pub/openai-releases-gpt-4o-mini-a-cheap-and-fast-small-language-model-eb9ecec8c15f | |||
| 02:28 | How is “GPT-4o mini” Game Changer in AI space (Milan’s Outlook) https://medium.com/@itsmybestview/how-is-gpt-4o-mini-game-changer-in-ai-space-milans-outlook-ededfd3a8831 | |||
| 02:25 | [Paper Review/KR] MAVIS: Mathematical Visual Instruction Tuning https://medium.com/@halcyon0424/paper-review-kr-mavis-mathematical-visual-instruction-tuning-ea1d51e07867 | |||
| 02:02 | GPT-4o mini is significantly smarter and cheaper than GPT-3.5 Turbo https://twitter.com/OpenAIDevs/status/1813990748406317221 | |||
| 01:42 | How to Fine-Tune LLM’s for Summarization ?? https://medium.com/@khadkaujjwal47/how-to-fine-tune-llms-for-summarization-0f223a8bf15e | |||
| 01:17 | Challenges of Productionizing RAGs https://sivasathivel-kandasamy.medium.com/challenges-of-productionizing-rags-9545082b38b5 | |||
| 01:15 | The Art of AI: Reimagining Artwork Analysis with RAG and LLMs https://medium.com/@alicejeanchoi/the-art-of-ai-reimagining-artwork-analysis-with-rag-and-llms-640e0225421f | |||
| 00:01 | OWASP Top 10 for Large Language Models https://medium.com/@sampratap/owasp-top-10-for-large-language-models-0d8c61ae31ae | |||
| Thursday, 2024-07-18 | ||||
| 23:35 | Multi-model Learning Models https://medium.com/@LiliMeng1/multi-model-learning-models-5c7d2d204c90 | |||
| 23:25 | At 15c/million tokens, will GPT 4o Mini be the foundation of Agentic Workflows? https://chrisjanwust.medium.com/at-15c-million-tokens-will-gpt-4o-mini-be-the-foundation-of-agentic-workflows-7fd189138da4 | |||
| 23:21 | cloning myself using LoRA https://medium.com/@avikmalladi/cloning-myself-using-lora-5bb69d241337 | |||
| 22:54 | LLMs https://medium.com/@akshayhitendrashah/llms-1627909bf766 | |||
| 22:52 | From Hype to Reality: How TAS Design’s LLMOps is Reinvigorating Generative AI https://medium.com/@TASDesignGroup/from-hype-to-reality-how-tas-designs-llmops-is-reinvigorating-generative-ai-0202f1bbb92d | |||
| 22:38 | Beyond the Gen AI Hype https://medium.com/@sandeep.bose_6501/beyond-the-gen-ai-hype-b83d5f69df2b | |||
| 22:31 | GPT-3.5 Turbo FINALLY Has A Successor https://medium.com/@impure/gpt-3-5-turbo-finally-has-a-successor-51cb1e2f3507 | |||
| 22:30 | OpenAI Launches GPT-4o-Mini https://autoblogs.medium.com/openai-launches-gpt-4o-mini-d7266cb28305 | |||
| 22:15 | GPT-4o Mini https://simonwillison.net/2024/Jul/18/gpt-4o-mini/ | |||
| 22:03 | GPT-4o Mini — Thoughts, Pricing, and Independent Evaluation https://medium.com/@lars.chr.wiik/gpt-4o-mini-thoughts-pricing-and-independent-evaluation-140d5ab8aed1 | |||
| 21:37 | Revolutionizing Fashion E-commerce: My Journey with Generative AI at Fashom https://medium.com/@rdesai2000/revolutionizing-fashion-e-commerce-my-journey-with-generative-ai-at-fashom-ae817b28933c | |||
| 21:19 | Do AI Models Actually Understand Language? https://aarnetalman.medium.com/do-ai-models-actually-understand-language-ce2f4e9a7fb9 | |||
| 21:15 | Andrej Karpathy: "LLM model size competition is intensifying backwards https://twitter.com/karpathy/status/1814038096218083497 | |||
| 20:46 | Enhancing Performance with C/C++ Code Execution for Langchain Agents https://itnext.io/enhancing-performance-with-c-c-code-execution-for-langchain-agents-a8974c4000f5 | |||
| 19:43 | Production Ready Advanced RAG Optimization with Llama-Index and Qdrant Vector Database https://medium.com/rahasak/production-ready-advanced-rag-optimization-with-llama-index-and-qdrant-vector-database-23ad6427b20a | |||
| 19:38 | How to Accurately Conduct Data Analysis with ChatGPT 4.0 https://jobmill.com.ng/data-analysis-with-chatgpt-4-0/ | |||
| 19:37 | Mistral AI is on fire…AI innovation at its peak https://sandar-ali.medium.com/mistral-ai-is-on-fire-ai-innovation-at-its-peak-d78d1dbb86ff | |||
| 19:14 | How Large language Models work? https://ai.plainenglish.io/how-large-language-models-work-ae40b277ff5c | |||
| 19:10 | Large Language Models — Retrieval Augmented Generation (RAG), Part 7 https://medium.com/@linghuang_76674/large-language-models-retrieval-augmented-generation-rag-part-7-87a6e01d6e35 | |||
| 18:54 | Mistral AI and NVIDIA Collaborate to Release Mistral NeMo: A 12B Open Language Model Featuring 128k Context Window, Multilingual Capabilities, and Tekken Tokenizer https://www.marktechpost.com/2024/07/18/mistral-ai-and-nvidia-collaborate-to-release-mistral-nemo-a-12b-open-llm-featuring-128k-context-window-multilingual-capabilities-and-tekken-tokenizer/ | |||
| 18:38 | Efficiency vs Mediocrity: The Double-Edged Sword of Foundation Models https://medium.com/@andrei.ionut.damian/efficiency-vs-mediocrity-the-double-edged-sword-of-foundation-models-944461c9b036 | |||
| 18:29 | RAGS : A bare bones introduction and When you’ll need them https://medium.com/@harshar613/rags-a-bare-bones-introduction-and-when-youll-need-them-b1c81182012b | |||
| 18:26 | Unveiling the Truth: Spotting Hallucinations in LLMs https://blog.stackademic.com/unveiling-the-truth-spotting-hallucinations-in-llms-3aeeffc38815 | |||
| 18:19 | Exposing the “magic” of AI / LLMs https://medium.com/@martijn_moret/exposing-the-magic-of-ai-llms-1d35365a45ff | |||
| 18:17 | GPT-4o mini https://cobusgreyling.medium.com/gpt-4o-mini-5dc420aa3715 | |||
| 18:06 | OpenAI is too cheap to beat https://generatingconversation.substack.com/p/openai-is-too-cheap-to-beat-redux | |||
| 18:02 | Anatomy of TGI, Text Generation Inference (II) https://medium.com/@martiniglesiasgo/anatomy-of-tgi-text-generation-inference-ii-6aace06c5efb | |||
| 18:00 | Anatomy of TGI for LLM Inference (I) https://medium.com/@martiniglesiasgo/anatomy-of-tgi-for-llm-inference-i-6ac8895d903d | |||
| 17:55 | Together Inference Engine 2.0 with new Turbo and Lite endpoints https://www.together.ai/blog/together-inference-engine-2 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803