LLM News and Articles
Wednesday, 2024-07-17 | ||||
19:03 | Product Analytics — Traditional vs AI Products https://medium.com/feedback-intelligence/product-analytics-traditional-vs-ai-products-5ead2b32afce | |||
19:03 | Optimizing Model Deployment: A Guide to Quantization with llama-cpp Python https://medium.com/@sanjaykumar.kedu/optimizing-model-deployment-a-guide-to-quantization-with-llama-cpp-python-1c45b4664189 | |||
18:51 | Quantization: A Beginner’s Guide https://medium.com/@sanjaykumar.kedu/quantization-a-beginners-guide-07439f5bf699 | |||
18:47 | Multimodal Batch Predictions with Gemini https://ravi-manjunatha.medium.com/multimodal-batch-predictions-with-gemini-896830dbe50d | |||
18:36 | The Road to FinGPT — Instructive Fine-tuned Market Forecaster https://medium.com/@ll3713/the-road-to-fingpt-instructive-fine-tuned-market-forecaster-cfe7cbf9038b | |||
18:33 | Installation of llama-cpp Python with CUDA Support: A Beginner’s Guide https://medium.com/@sanjaykumar.kedu/installation-of-llama-cpp-python-with-cuda-support-a-beginners-guide-be87a8a437d2 | |||
18:28 | Building an LLM App: My Experience with Ollama, LLaMA 3, and ChatGPT https://medium.com/@punitvara/building-an-llm-app-my-experience-with-ollama-llama-3-and-chatgpt-139d498dcd81 | |||
18:18 | What LeBron James’ lies taught me about B2B marketing. https://medium.com/@rubenfransz/what-lebron-james-lies-taught-me-about-b2b-marketing-a569a4463d51 | |||
18:08 | Is a Zero Temperature Deterministic? https://medium.com/google-cloud/is-a-zero-temperature-deterministic-c4a7faef4d20 | |||
18:02 | Fine-Tuning LLMs with Synthetic Data for High-Quality Content Generation https://pub.towardsai.net/fine-tuning-llms-with-synthetic-data-for-high-quality-content-generation-aff1204ba750 | |||
17:54 | AI-Enhanced Presentation Maker: Automating PowerPoint Generation with Python and Gemini-Pro Model https://medium.com/@syncwithdanish/ai-enhanced-presentation-maker-automating-powerpoint-generation-with-python-and-gemini-pro-model-06dd723a138d | |||
17:26 | Microsoft Phi-3 Mini: Highly capable language model running locally on a cell-phone. https://medium.com/@ashishsingh.chunar2017/microsoft-phi-3-mini-highly-capable-language-model-running-locally-on-a-cell-phone-ab79ce1467d4 | |||
17:22 | The n-gram Language Model https://github.com/EurekaLabsAI/ngram | |||
17:15 | Agentic AI: Creating An AI Agent Which Can Navigate The Internet https://cobusgreyling.medium.com/agentic-ai-creating-an-ai-agent-which-can-navigate-the-internet-655fe5596a0c | |||
17:15 | Prover-Verifier Games improve legibility of language model outputs https://openai.com/index/prover-verifier-games-improve-legibility/ | |||
16:39 | Looks Like AI Is Finally Peaking — The Real Work Begins https://quentincott.medium.com/looks-like-ai-is-finally-peaking-the-real-work-begins-4a54d6fa6d9c | |||
16:18 | Llama Nanobodies: A Breakthrough in Building HIV Immunity https://news.gsu.edu/research-magazine/breakthrough-in-building-hiv-immunity | |||
16:16 | Information on Major Large Language Models (LLMs) https://medium.com/@zhu-y11/information-on-major-large-language-models-llms-707f185fd62f | |||
16:12 | GenAI Falls Short in Predictions and Troubleshooting, but Shines When Combined with Waylay Tech https://veselin-30085.medium.com/genai-falls-short-in-predictions-and-troubleshooting-but-shines-when-combined-with-waylay-tech-58668066cea6 | |||
16:08 | Cybersecurity Audits: The Power of Generative AI https://medium.com/@KobrinArtem/cybersecurity-audits-the-power-of-generative-ai-78eaa6d0d414 | |||
16:01 | Quantization: Post Training Quantization, Quantization Error, and Quantization Aware Training https://pub.towardsai.net/quantization-post-training-quantization-quantization-error-and-quantization-aware-training-21c9c3d297d1 | |||
15:54 | Exploring the Gemini API: https://medium.com/the-ai-archives/exploring-the-gemini-api-fe9cf4a993fa | |||
15:36 | Transformers: Theory and Maths https://medium.com/@shwet.prakash97/transformers-theory-and-maths-19ef6a8b9433 | |||
15:31 | Pair programming an LLM-app https://medium.com/@diogo.norinho_68239/pair-programming-an-llm-app-4ca1629295d0 | |||
15:01 | Join the Revolution: Experience Unmatched Efficiency with ARC Reactor! https://medium.com/@jamison_gg/join-the-revolution-experience-unmatched-efficiency-with-arc-reactor-4c15f50cf8f5 | |||
14:50 | Good, my AI RAG code is working…! https://medium.com/@ove.hansen/good-my-ai-rag-code-is-working-0487ef2a8059 | |||
14:27 | Discovering new knowledge with Differential Privacy https://medium.com/sarus/discovering-new-knowledge-with-differential-privacy-8782c11dd6ad | |||
14:23 | Joining Arcee.ai! https://julsimon.medium.com/joining-arcee-ai-67ad5b8210f5 | |||
14:03 | GraphRAG Is the Logical Step From Rag — So Why the Sudden Hype? https://pub.towardsai.net/graphrag-is-the-logical-step-from-rag-so-why-the-sudden-hype-5bd8594c90aa | |||
14:02 | Timing is the New Location https://medium.com/@fractionai/timing-is-the-new-location-24d1548e9ee9 | |||
13:44 | Unveiling Archaeological Gifts to the United Nations: A Computational Exploration https://mehtaplus.medium.com/unveiling-archaeological-gifts-to-the-united-nations-a-computational-exploration-ce3fb751fe2b | |||
13:32 | AI-OS or LLM-OS https://medium.com/@sawanesanskar07/ai-os-or-llm-os-1e76d4102a91 | |||
12:38 | RAG https://medium.com/@gargishika1998/rag-838ba02fda03 | |||
12:36 | Llama-3-Groq-Tool-Use Models https://wow.groq.com/introducing-llama-3-groq-tool-use-models/ | |||
12:27 | Llama3 LLM Sohbet Botu: Kapsamlı Kurulum ve Kullanım Rehberi https://aerdincdal.medium.com/llama3-llm-sohbet-botu-kapsaml%C4%B1-kurulum-ve-kullan%C4%B1m-rehberi-630e1e400758 | |||
12:27 | Why Your LLM is in Need of a Good Therapy Session https://bundleiq.medium.com/why-your-llm-is-in-need-of-a-good-therapy-session-fae33045daeb | |||
12:26 | Imprecise Learning for dummies: A new perspective on training ML models for real-world https://medium.com/@anurags.it/imprecise-learning-for-dummies-a-new-perspective-on-training-ml-models-for-real-world-0021d2ba5eb7 | |||
12:18 | Have you ever thought about how frustrating it is to wait for a chatbot’s response? https://andreabelvedere.medium.com/have-you-ever-thought-about-how-frustrating-it-is-to-wait-for-a-chatbots-response-cf8c4afdab17 | |||
11:50 | What on earth is attention mechanism in transformers? https://medium.com/@taaha.com/what-on-earth-is-attention-mechanism-in-transformers-4a5a052c9105 | |||
11:45 | AutoBencher: A Metrics-Driven AI Approach Towards Constructing New Datasets for Language Models https://www.marktechpost.com/2024/07/17/autobencher-a-metrics-driven-ai-approach-towards-constructing-new-datasets-for-language-models/ | |||
11:23 | A short journey through LLM prompting https://medium.com/mpb-tech/a-short-journey-through-llm-prompting-b6ce9dd8c8b3 | |||
11:15 | Bioptimus Unveils H-optimus-0: A New State-of-the-Art Open-Source Foundation AI Model for Pathology https://www.marktechpost.com/2024/07/17/bioptimus-unveils-h-optimus-0-a-new-state-of-the-art-open-source-foundation-ai-model-for-pathology/ | |||
11:00 | MELLE: A Novel Continuous-Valued Tokens-based Language Modeling Approach for Text-to-Speech Synthesis (TTS) https://www.marktechpost.com/2024/07/17/melle-a-novel-continuous-valued-tokens-based-language-modeling-approach-for-text-to-speech-synthesis-tts/ | |||
10:58 | Elevate Your Business with Chatbot Consulting Services https://medium.com/@marketing_novita.ai/elevate-your-business-with-chatbot-consulting-services-a67238a622d1 | |||
10:53 | Best Tools for LLM Development in 2024 https://medium.com/@krishani_70219/best-tools-for-llm-development-in-2024-aaf2dd3fa17a | |||
10:46 | Top AI APIs for NLP Across Five Scenarios https://medium.com/@marketing_novita.ai/top-ai-apis-for-nlp-across-five-scenarios-a264ad78aed0 | |||
10:41 | Microsoft CTO Kevin Scott thinks LLM "scaling laws" will hold despite criticism https://arstechnica.com/information-technology/2024/07/microsoft-cto-defies-critics-ai-progress-not-slowing-down-its-just-warming-up/ | |||
10:11 | Semantic search for Emojis in 50+ languages using AI https://medium.com/@badr.alabsi/semantic-search-for-emojis-in-50-languages-using-ai-f85a36a86f21 | |||
09:53 | Framework de Evaluación para el patrón RAG implementado en Justicio (II) https://medium.com/@bukosabino/framework-de-evaluaci%C3%B3n-para-el-patr%C3%B3n-rag-implementado-en-justicio-ii-8d3c2a1dbf28 | |||
09:52 | Improved Malware Analysis with Google Gemini 1.5 flash https://medium.com/@agarapuramesh/improved-malware-analysis-with-google-gemini-1-5-flash-d17a598e1ea6 | |||
09:40 | Framework de Evaluación para el patrón RAG implementado en Justicio https://medium.com/@bukosabino/framework-de-evaluaci%C3%B3n-para-el-patr%C3%B3n-rag-implementado-en-justicio-d8ca06bee17f | |||
09:37 | Training LLMs to Draft Replies to Parliamentary Questions — Fine-tuning Llama 3 and Gemma 2 with… https://medium.com/dsaid-govtech/training-llms-to-draft-replies-to-parliamentary-questions-fine-tuning-llama-3-and-gemma-2-with-f9e161b72d0e | |||
09:34 | Finally Found My Groove: Diving Deep into Generative AI https://medium.com/@priyanshu.paikra/finally-found-my-groove-diving-deep-into-generative-ai-a482caea84a2 | |||
09:32 | Enhance Efficiency: Fastest LLM API for Developers https://medium.com/@marketing_novita.ai/enhance-efficiency-fastest-llm-api-for-developers-b4b95648dd88 | |||
09:09 | Utilizing Generative AI for Classification Problems using Streamlit, EC2, API Gateway, Lambda… https://medium.com/@abdellimohamedammar/utilizing-generative-ai-for-classification-problems-using-streamlit-ec2-api-gateway-lambda-83c49a64af56 | |||
07:52 | Where next? GenAI’s evolution in knowledge, understanding, reasoning and scaling https://pollington.medium.com/where-next-genais-evolution-in-knowledge-understanding-reasoning-and-scaling-d9834f92defe | |||
07:10 | Run Ollama in Google Colab https://machinelearningengineer.medium.com/run-ollama-in-google-colab-e45b9fc913a0 | |||
07:02 | ChatGPT vs. LLM Apps https://medium.com/@punya8147_26846/chatgpt-vs-llm-apps-35788fd2ab9b | |||
07:01 | AI’nt That Easy #4: Claude 3.5 Sonnet vs ChatGPT https://aint-that-easy.medium.com/aint-that-easy-4-claude-3-5-sonnet-vs-chatgpt-350b366ee67a | |||
06:32 | What to Learn When Someone Says to Learn AI: A Beginner’s Guide to Understanding AI and Generative… https://medium.com/@chandraprakashtekwani8/what-to-learn-when-someone-says-to-learn-ai-a-beginners-guide-to-understanding-ai-and-generative-a551a28d7e7e | |||
06:31 | llamafile: Local LLM with CPU https://medium.com/@sumant1122/llamafile-local-llm-with-cpu-364195cbb670 | |||
06:01 | Show HN: Mockingbird is an LLM that outperforms GPT4 on RAG https://vectara.com/blog/mockingbird-is-a-rag-specific-llm-that-beats-gpt-4-gemini-1-5-pro-in-rag-output-quality/ | |||
05:56 | Unlocking Domain Expertise with LLMs: The Power of Retrieval Augmented Generation (RAG) https://blog.gopenai.com/unlocking-domain-expertise-with-llms-the-power-of-retrieval-augmented-generation-rag-2d8804116a66 | |||
05:50 | Deriving value from LLMs using RAG https://medium.com/@anands282/deriving-value-from-llms-using-rag-15fd8b26a8d5 | |||
05:32 | A Leap Forward in AI: Exploring EM-LLM’s Episodic Memory Breakthrough https://theblueowls.medium.com/a-leap-forward-in-ai-exploring-em-llms-episodic-memory-breakthrough-d0c32f34350f | |||
05:08 | Summarize Large Documents or Text Using LLMs and LangChain https://medium.com/@NLPEngineers/summarize-large-documents-or-text-using-llms-and-langchain-3116543df4ba | |||
04:52 | GraphRAG 101: A New Dawn in Retrieval Augmented Generation https://theblueowls.medium.com/graphrag-101-a-new-dawn-in-retrieval-augmented-generation-c8e99af2e9fe | |||
04:48 | The fastest hybrid search — A glimpse into Infinity v0.2 features https://medium.com/@infiniflowai/the-fastest-hybrid-search-a-glimpse-into-infinity-v0-2-features-eec84bc02c8f | |||
04:37 | OpenAGI 0.2.7 Release: Improved Human Intervention, New Actions and Claude LLM Integrations https://medium.aiplanet.com/openagi-0-2-7-release-improved-human-intervention-new-actions-and-claude-llm-integrations-f04aa729a92a | |||
04:34 | Multimodal Retrieval Augmented Generation for Sustainable Finance https://zoumanakeita.medium.com/multimodal-retrieval-augmented-generation-for-sustainable-finance-1bc664ac2511 | |||
04:24 | WTF?GPT-4o and Claude Sonnet 3.5 Even Don’t Know 9.11 and 9.9 Which Is Greater https://medium.com/@giant_chen1688/wtf-gpt-4o-and-claude-sonnet-3-5-even-dont-know-9-11-and-9-9-which-is-greater-d59bb8797fc2 | |||
04:16 | The Best Generative AI Workplace Productivity Tools https://blog.cubed.run/the-best-generative-ai-workplace-productivity-tools-f8a948101e51 | |||
04:08 | Ollama vs VLLM: Which Tool Handles AI Models Better? https://medium.com/@tripathinaman.1014/ollama-vs-vllm-which-tool-handles-ai-models-better-a93345b911e6 | |||
04:02 | Can AI Think? https://andisama.medium.com/can-ai-think-4bc7ee3a073d | |||
03:56 | Prompt Engineering for starters (in Burmese) https://medium.com/@minsithu_53495/prompt-engineering-for-starters-in-burmese-abf2c396aecb | |||
03:52 | Mistral AI Unveils Mathstral 7B and Math Fine-Tuning Base: Achieving 56.6% on MATH and 63.47% on MMLU, Restructuring Mathematical Discovery https://www.marktechpost.com/2024/07/16/mistral-ai-unveils-mathstral-7b-and-math-fine-tuning-base-achieving-56-6-on-math-and-63-47-on-mmlu-restructuring-mathematical-discovery/ | |||
03:49 | Best Large Language Models (LLMs) of 2024: A Comprehensive Comparison and Analysis https://medium.com/@unpluggedreview/best-large-language-models-llms-of-2024-a-comprehensive-comparison-and-analysis-6d9d345ab0e3 | |||
03:47 | Dense vector + Sparse vector + Full text search + Tensor reranker = Best retrieval for RAG? https://medium.com/@infiniflowai/dense-vector-sparse-vector-full-text-search-tensor-reranker-best-retrieval-for-rag-9c86b02a55ef | |||
03:38 | “Judge an LLM Judge”: A Dual-Layer Evaluation Framework for Continous Improvement of LLM-App’s… https://towardsdatascience.com/judge-an-llm-judge-a-dual-layer-evaluation-framework-for-continous-improvement-of-llm-apps-7450d0e81e17 | |||
03:06 | An Update on ProteinGPT https://medium.com/@divyan.bavan/an-update-on-proteingpt-3fa870a9965a | |||
01:37 | G.A.Ns don’t need Agreements. https://medium.com/@pkompally/g-a-ns-dont-need-agreements-c0c8cc2d924b | |||
01:14 | Order Matters: Assessing LLM Sensitivity in Multiple-Choice Tasks https://megagonlabs.medium.com/order-matters-assessing-llm-sensitivity-in-multiple-choice-tasks-43bf4f3740f4 | |||
00:46 | Explaining Large Language Models: The Challenges, the Benefits, and the Fast-Approaching Future https://medium.com/@ep-apac.sales/explaining-large-language-models-the-challenges-the-benefits-and-the-fast-approaching-future-cdff991451c3 | |||
00:33 | Modular vs Monolithic: Small Graphs as Micro-services https://medium.com/enterprise-rag/modular-vs-monolithic-small-graphs-as-micro-services-230042072c31 | |||
00:29 | Deep Dive with WiTQA: When Does Retrieval Augmentation Help (or Hurt) Language Models? https://megagonlabs.medium.com/deep-dive-with-witqa-when-does-retrieval-augmentation-help-or-hurt-language-models-1daabc5e37a4 | |||
Tuesday, 2024-07-16 | ||||
23:46 | Token Sampling Methods — Temperature to heat things up. https://medium.com/@chitrakumarsai/token-sampling-methods-temperature-to-heat-things-up-af0c1e36dafc | |||
22:36 | Google’s Gemini Pro: The AI That Thinks More Like Us
Have you ever wished your phone’s virtual… https://medium.com/@dreamschaser612/googles-gemini-pro-the-ai-that-thinks-more-like-us-have-you-ever-wished-your-phone-s-virtual-3cf0db72a358 | |||
21:58 | How Good Is Elastic for Semantic Search, Really? https://medium.com/@artem.mykytyshyn/how-good-is-elastic-for-semantic-search-really-4bcb7719919b | |||
20:38 | IA: Os Diferentes Níveis Reais e Virtuais https://medium.com/@iheringguedes/ia-os-diferentes-n%C3%ADveis-reais-e-virtuais-d9d94a068ce2 | |||
20:20 | Mastering Text Splitting in Langchain https://medium.com/@harsh.vardhan7695/mastering-text-splitting-in-langchain-735313216e01 | |||
19:50 | LangChain in Chains #29: SitemapLoader https://awstip.com/langchain-in-chains-29-sitemaploader-c9c0bf08b6e3 | |||
19:41 | Implementing a Retrieval Augmented Generation (RAG) System for Directory Inquiry Services in… https://medium.com/@davoud.badamchi/implementing-a-retrieval-augmented-generation-rag-system-for-directory-inquiry-services-in-905ca5b13ccb | |||
19:40 | Leveraging RAG and LLMs: Transforming Data Interaction in Healthcare and Beyond https://medium.com/@jennifer.d.davis.ai/leveraging-rag-and-llms-transforming-data-interaction-in-healthcare-and-beyond-23684c7554a4 | |||
19:05 | Advanced RAG Techniques — The Corrective RAG strategy https://gabrielgomes61320.medium.com/advanced-rag-techniques-the-corrective-rag-strategy-93451a49db61 | |||
18:56 | DevRel at HuggingFace https://dx.tips/huggingface | |||
18:48 | Mockingbird: A RAG-Focused LLM https://vectara.com/blog/mockingbird-a-rag-and-structured-output-focused-llm/ | |||
18:13 | At the Intersection of Legal and Medical Problems: How AI Can Bridge the Gap https://medium.com/@asimsultan2/at-the-intersection-of-legal-and-medical-problems-how-ai-can-bridge-the-gap-1ede9b9c41e4 | |||
18:13 | Show HN: Try Codestral Mamba (Mistral's new model) using OpenAI's API format https://github.com/token-js/token.js | |||
18:11 | Exploring AWS Bedrock-Unleash Your Inner AI Avenger! https://medium.com/@Gowtham_CP/exploring-aws-bedrock-unleash-your-inner-ai-avenger-ef199f3f9d56 | |||
18:02 | COCOM: An Effective Context Compression Method that Revolutionizes Context Embeddings for Efficient Answer Generation in RAG https://www.marktechpost.com/2024/07/16/cocom-an-effective-context-compression-method-that-revolutionizes-context-embeddings-for-efficient-answer-generation-in-rag/ |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803