LLM News and Articles
Friday, 2024-07-12 | ||||
01:15 | Former OpenAI employee quit to avoid 'working for the Titanic of AI' https://cointelegraph.com/news/open-ai-artificial-intelligence-safety-employee-quit-titanic | |||
00:49 | Claude Promotes LLM Interface Development https://generativeai.pub/claude-promotes-llm-interface-development-d90d000ea498 | |||
00:47 | I Made The World’s First GenAI Fighting Game https://generativeai.pub/i-made-the-worlds-first-genai-fighting-game-2f8880fd140c | |||
00:09 | Advanced RAG Retrieval Strategies Using Knowledge Graphs https://generativeai.pub/advanced-rag-retrieval-strategies-using-knowledge-graphs-12c9ce54d2da | |||
Thursday, 2024-07-11 | ||||
22:07 | ETL in the age of LLMs https://medium.com/@thibaut_gourdel/etl-in-the-age-of-llms-5e476cd919c9 | |||
21:51 | Show HN: CipherAI – Technical interview prep platform with LLM to assist you https://www.cipherai.dev/ | |||
21:34 | Evaluating Long-Form Responses with Prometheus-Eval and Langtest https://medium.com/john-snow-labs/evaluating-long-form-responses-with-prometheus-eval-and-langtest-a8279355362e | |||
21:11 | Strategies for Team Success in LLM Application Development https://medium.com/@jelkhoury880/strategies-for-team-success-in-llm-application-development-6a4d5a6ede10 | |||
21:09 | Top 17 LLMs Explain the Phillips Curve https://medium.com/@cristian.nedelcu/top-17-llms-explain-the-phillips-curve-d7bd7899cec6 | |||
20:55 | Mastering Model Evaluation: Introducing the Comprehensive Ranking & Leaderboard System in LangTest https://medium.com/john-snow-labs/mastering-model-evaluation-introducing-the-comprehensive-ranking-leaderboard-system-in-langtest-5242927754bb | |||
20:11 | Review-LLM: A Comprehensive AI Framework for Personalized Review Generation Using Large Language Models and User Historical Data in Recommender Systems https://www.marktechpost.com/2024/07/11/review-llm-a-comprehensive-ai-framework-for-personalized-review-generation-using-large-language-models-and-user-historical-data-in-recommender-systems/ | |||
19:38 | Researchers from Stanford and the University at Buffalo Introduce Innovative AI Methods to Enhance Recall Quality in Recurrent Language Models with JRT-Prompt and JRT-RNN https://www.marktechpost.com/2024/07/11/researchers-from-stanford-and-the-university-at-buffalo-introduce-innovative-ai-methods-to-enhance-recall-quality-in-recurrent-language-models-with-jrt-prompt-and-jrt-rnn/ | |||
19:35 | Running Local LLMs is More Useful and Easier Than You Think https://towardsdatascience.com/running-local-llms-is-more-useful-and-easier-than-you-think-f735631272ad | |||
19:31 | Exploring AI Models on Gaianet: A Comprehensive Overview https://medium.com/@zulfanbaswedan/exploring-ai-models-on-gaianet-a-comprehensive-overview-d4e2e967a1f3 | |||
19:21 | Karpathy: Let's reproduce GPT-2 (1.6B): one 8XH100 node 24h 2 in llm.c https://github.com/karpathy/llm.c/discussions/677 | |||
19:15 | Why we need a new paradigm to achieve AGI https://bkarak.medium.com/why-we-need-a-new-paradigm-to-achieve-agi-53daf10fd2bd | |||
19:05 | Install LLM Server at home https://medium.com/@sungcheol.kim78/install-llm-server-at-home-cdc5df4b486c | |||
19:02 | Enforcing Structure and Assembling Our AI Agent https://odupuis.medium.com/enforcing-structure-and-assembling-our-ai-agent-b91a5013bab0 | |||
19:01 | Large Language Models — Retrieval Augmented Generation (RAG), Part 6 https://medium.com/@linghuang_76674/large-language-models-retrieval-augmented-generation-rag-part-6-01ac918de1cc | |||
18:24 | Calculate : How much GPU Memory you need to serve any LLM ? https://ksingh7.medium.com/calculate-how-much-gpu-memory-you-need-to-serve-any-llm-67301a844f21 | |||
18:21 | Finetuning LLMs - A brief Overview https://medium.com/@kaushiksp/finetuning-llms-a-brief-overview-29ba836d1e13 | |||
18:19 | Graph RAG — An Overview https://medium.com/@SohaibAhmedAbbasi/graph-rag-e383fe6f7e9f | |||
18:09 | How are LLMs like ChatGPT Trained? https://medium.com/@shubhamprajapati7748/how-are-llms-like-chatgpt-trained-5aa24238c26c | |||
18:07 | What the Heck is RAG? https://medium.com/@visheshtaposthali/what-the-heck-is-rag-b2fc7c27ab21 | |||
17:56 | GenAI with Python: LLM vs Agents https://towardsdatascience.com/genai-with-python-llm-vs-agents-5c3de7ec82a7 | |||
17:56 | Paper Review: Are LLMs Good at Search? https://medium.com/tr-labs-ml-engineering-blog/paper-review-are-llms-good-at-search-1d8724527132 | |||
17:24 | Estimated OpenAI Revenue Breakdown https://futuresearch.ai/openai-revenue-report | |||
16:56 | Mistral 7b Meets Darija : A Continual Pre-training Journey https://medium.com/@ayoubkirouane3/mistral-7b-meets-darija-a-continual-pre-training-journey-90e037c5cbef | |||
16:09 | Large Language Model — LLM Model Efficient Inference https://medium.com/@linghuang_76674/large-language-model-llm-model-efficient-inference-c9b05fce9ec1 | |||
16:04 | Is ChatGPT Falling Behind Claude 3.5 Sonnet? https://ai.plainenglish.io/is-chatgpt-falling-behind-claude-3-5-sonnet-702b4b4f64ae | |||
15:42 | Wren AI in Kubernetes: Text-to-SQL https://blog.getwren.ai/wren-ai-in-kubernetes-text-to-sql-39b82bda3d34 | |||
15:27 | Six Essential Tips for Mastering Prompt Engineering in LLMs https://medium.com/@sahin.samia/six-essential-tips-for-mastering-prompt-engineering-in-llms-743fa3970940 | |||
15:00 | Build Your Own Autonomous Agents using OpenAGI https://medium.aiplanet.com/build-your-own-autonomous-agents-using-openagi-f6ae8e1f9825 | |||
14:55 | Fine-tuning Large Models: Detailed Explanation and Applications https://medium.com/@threehappyer/fine-tuning-large-models-detailed-explanation-and-applications-8e9660047ff9 | |||
14:54 | An Introduction to Vector Databases https://medium.com/@nusatenko/an-introduction-to-vector-databases-b0c7775ed0ca | |||
14:48 | Form without substance: Generative artificial intelligence and the cheapening of creation https://medium.com/@andrewgoldsteintv/form-without-substance-generative-artificial-intelligence-and-the-cheapening-of-creation-7d8425dd9cae | |||
14:48 | Monster API’s Instruction Synthesizer API: A New Frontier in Language Model Development https://medium.com/@raagulbharatwaj/monster-apis-instruction-synthesizer-api-a-new-frontier-in-language-model-development-c7b0ddb78223 | |||
14:43 | Easily query your database using LLMs without writing SQL and then import the data into Microsoft… https://blog.getwren.ai/easily-query-your-database-using-llms-without-writing-sql-and-then-import-the-data-into-microsoft-871c9672c656 | |||
14:35 | LLMs are Dead, Long Live LLMs https://medium.com/@anais.monlong/llms-are-dead-long-live-llms-208c24de1c5d | |||
14:12 | CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy https://arxiv.org/abs/2403.16008 | |||
13:33 | Build Multilingual Translation with Cohere Model on Amazon Bedrock https://blog.shellkode.com/build-multilingual-translation-with-cohere-model-on-amazon-bedrock-989ff905916f | |||
13:00 | Finetune your first LLM model with LoRA and QLoRA https://medium.com/@aionlinecourse/finetune-your-first-llm-model-with-lora-and-qlora-e535dc1411d7 | |||
12:46 | Introduction to Google Gemini 1.5 https://medium.com/@data_carlos/introduction-to-google-gemini-1-5-2b15cd270e56 | |||
12:10 | Top 10 Large Language Model Development Companies (2024) https://medium.com/@jigar.agrawal/top-large-language-model-development-companies-cf049e17e642 | |||
11:49 | Top Courses to Master Artificial Intelligence in 2024 https://medium.com/@1090504938/top-courses-to-master-artificial-intelligence-in-2024-83f15e4bdb81 | |||
11:32 | The complete guide for TDD with LLMs https://rchavesferna.medium.com/the-complete-guide-for-tdd-with-llms-1dfea9041998 | |||
11:01 | VESSL 2.0 is Here: Experience Our Sleek New Interface https://medium.com/vessl-ai/vessl-2-0-is-here-experience-our-sleek-new-interface-134ec134709d | |||
11:00 | Agentless: An Agentless AI Approach to Automatically Solve Software Development Problems https://www.marktechpost.com/2024/07/11/agentless-an-agentless-ai-approach-to-automatically-solve-software-development-problems/ | |||
10:58 | Augmented Retrieval Makes LLMs Better at Long-Context Tasks https://medium.com/@marketing_novita.ai/augmented-retrieval-makes-llms-better-at-long-context-tasks-de5abd4a9560 | |||
10:58 | How to Use Mistral Chat Template? https://medium.com/@marketing_novita.ai/how-to-use-mistral-chat-template-e0b2a973f031 | |||
10:58 | The Transformative Power of Generative AI: Exploring Innovations, Applications, and Future… https://medium.com/@akasshkrishnan1811/the-transformative-power-of-generative-ai-exploring-innovations-applications-and-future-0744ebc4174f | |||
10:52 | Human-like AI: Cognitive LLM Agents https://egeatmaca.medium.com/human-like-ai-cognitive-llm-agents-c6c771c4dbc1 | |||
10:52 | Human-like AI: Cognitive LLM Agents https://blog.gopenai.com/human-like-ai-cognitive-llm-agents-c6c771c4dbc1 | |||
10:26 | Intro to AI Evaluation with Langsmith https://medium.com/syntonize/intro-to-ai-evaluation-with-langsmith-f85799788f51 | |||
09:30 | From Local to Global: The Story of Graph RAG’s https://medium.com/@m-aliabbas/from-local-to-global-the-story-of-graph-rags-cd823250286c | |||
09:30 | John Snow Labs Announced a Major Update on Its Flagship Library : Healthcare NLP v5.4 https://medium.com/john-snow-labs/john-snow-labs-announced-a-major-update-on-its-flagship-library-healthcare-nlp-v5-4-5e01965dbc85 | |||
08:59 | Use Case: How Small Startups Can Capitalize on AI Large Language Models KellyOnTech https://kellyontech.medium.com/use-case-how-small-startups-can-capitalize-on-ai-large-language-models-kellyontech-94ddfc4fb3de | |||
08:50 | Introducing Code Llama 70B best-performing model in the Code Llama family https://emaddehnavi.medium.com/introducing-code-llama-70b-best-performing-model-in-the-code-llama-family-e1278af6f933 | |||
08:31 | What are the most popular LLM benchmarks? https://medium.com/@symflower/what-are-the-most-popular-llm-benchmarks-ba0438cb59ab | |||
08:27 | Large Language Models (LLMs) and Data Leaks https://medium.com/@shubham_3306/large-language-models-llms-and-data-leaks-51eafcf83fb6 | |||
07:53 | Building Jahez’s Cuisines Classification with Large Language Models https://jahez.digital/building-jahezs-cuisines-classification-with-large-language-models-8bddc97ff22b | |||
07:36 | AI TRiSM Integration for Enterprise Environments https://medium.com/@padhyecharudatta2/ai-trism-integration-for-enterprise-environments-63941cd557d5 | |||
07:25 | maadaa AI News & Datasets: Privacy Patches, Hollywood Narrations, Bot Battles, Emotional Decoding &… https://maadaa-ai.medium.com/maadaa-ai-news-datasets-privacy-patches-hollywood-narrations-bot-battles-emotional-decoding-6bcc57afee4b | |||
06:15 | Generative AI Bootcamp — Day 6 Takeaways https://medium.com/@frncsfndl/generative-ai-bootcamp-day-6-takeaways-6ee30e11cff2 | |||
06:15 | Revolutionizing Education: https://medium.com/@717821i128/revolutionizing-education-9c62af21522c | |||
04:52 | Generative AI Privacy Risks https://towardsdatascience.com/generative-ai-privacy-risks-5983f2f594e4 | |||
04:33 | Towards Monosemanticity: A step towards understanding large language models https://towardsdatascience.com/towards-monosemanticity-a-step-towards-understanding-large-language-models-e7b88380d7b3 | |||
04:16 | Unleashing the Power of Collective Intelligence: The Mixture-of-Agents Approach in Large Language… https://medium.com/@LakshmiNarayana_U/unleashing-the-power-of-collective-intelligence-the-mixture-of-agents-approach-in-large-language-330b4ae5eadf | |||
03:54 | Quick Read: MM1 Study: Elevating Multimodal LLMs through Pre-training Innovations https://vishwanathkamath.medium.com/quick-read-mm1-study-elevating-multimodal-llms-through-pre-training-innovations-985a3eacc041 | |||
03:45 | NuminaMath 7B TIR Released: Transforming Mathematical Problem-Solving with Advanced Tool-Integrated Reasoning and Python REPL for Competition-Level Accuracy https://www.marktechpost.com/2024/07/10/numinamath-7b-tir-released-transforming-mathematical-problem-solving-with-advanced-tool-integrated-reasoning-and-python-repl-for-competition-level-accuracy/ | |||
03:42 | Many Shots In-Context learning (ICL): DeepMind - Paper Review https://medium.com/@sulbha.jindal/many-shots-in-context-learning-icl-deepmind-paper-review-85c868641245 | |||
03:29 | How to add memory to LLM Bot using DynamoDB https://amlana21.medium.com/how-to-add-memory-to-llm-bot-using-dynamodb-670dfd5e4594 | |||
03:09 | Managing Model Registry using Model Catalogs (for Large Language Models) in Azure https://medium.com/@nayan.j.paul/managing-model-registry-using-model-catalogs-for-large-language-models-in-azure-2999a26f72e6 | |||
02:46 | Discover LM Studio: An Easy Introduction to Running AI Models Locally https://medium.com/@omkamal/discover-lm-studio-an-easy-introduction-to-running-ai-models-locally-674c58339f4b | |||
02:31 | Real-Time Analytics: Weekly Roundup July 10, 2024 https://medium.com/rtinsights/real-time-analytics-weekly-roundup-july-10-2024-d0a7ac5b3ea2 | |||
01:28 | What we have learned about LLM agents over 1.5y building an AI data and analytics assistant https://blog.getdot.ai/what-we-have-learned-about-llm-agents-over-1-5y-building-an-ai-data-and-analytics-assistant-d32da3f847fd | |||
00:41 | How To Create Your Own Base Knowledge Chatbot ? https://medium.com/@ntarik.loukili/how-to-create-your-own-base-knowledge-chatbot-0f424fd51049 | |||
00:12 | Code Generation with Mistral’s Codestral https://medium.com/@izzybreezylearn/code-generation-with-mistrals-codestral-6700604fc91c | |||
00:00 | How NuminaMath Won the 1st AIMO Progress Prize https://huggingface.co/blog/winning-aimo-progress-prize | |||
Wednesday, 2024-07-10 | ||||
23:19 | Eliza chat with an OpenAI compatible API https://elizallm.com | |||
23:07 | Building a Multi-Hop Search System: Integrating Databricks Vector Search and Model Serving with… https://matthewmccoy6.medium.com/building-a-multi-hop-search-system-integrating-databricks-vector-search-and-model-serving-with-5c9d77936b2e | |||
22:54 | Show HN: Open-source tool that writes Nvidia Triton Inference Glue code for you https://github.com/inferless/triton-co-pilot | |||
22:39 | Claude 3.5 Sonnet Is Really Good https://medium.com/@impure/claude-3-5-sonnet-is-really-good-ae9816c79882 | |||
22:17 | Microsoft Quits OpenAI's Board Amid Antitrust Scrutiny https://www.wsj.com/tech/ai/microsoft-withdraws-from-openais-board-amid-antitrust-scrutiny-aab6ff1e | |||
22:02 | Six Key Challenges and Lessons Learned While Building Enterprise Large Language Model (LLM)… https://medium.com/@vsrinivasanapps/six-key-challenges-and-lessons-learned-while-building-enterprise-large-language-model-llm-c1872539068b | |||
22:00 | Microsoft, Apple Drop OpenAI Board Plans as Scrutiny Grows https://www.bloomberg.com/news/articles/2024-07-10/microsoft-quits-openai-board-after-antitrust-scrutiny-grows | |||
21:18 | The 2024 LLM Directory: Find the Best Models for Your Use Cases https://medium.com/@hendrix_56915/the-2024-llm-directory-find-the-best-models-for-your-use-cases-c9d5e04fca3b | |||
21:04 | Harnessing the Power of Bigrams: A Dive into Language Modeling and Text Generation https://medium.com/@talal.atef.801/harnessing-the-power-of-bigrams-a-dive-into-language-modeling-and-text-generation-a8c9e781ffbe | |||
20:05 | Problem to solve: Taking notes while exercising https://medium.com/@torjelucian/problem-to-solve-taking-notes-while-exercising-f62152fc4c93 | |||
19:03 | Integrating LLMs with Blockchain Technology: A Step-by-Step Guide for Enterprises https://medium.com/@padhyecharudatta2/integrating-llms-with-blockchain-technology-a-step-by-step-guide-for-enterprises-4e11cb8af115 | |||
18:57 | SenseTime Unveiled SenseNova 5.5: Setting a New Benchmark to Rival GPT-4o in 5 Out of 8 Key Metrics https://www.marktechpost.com/2024/07/10/sensetime-unveiled-sensenova-5-5-setting-a-new-benchmark-to-rival-gpt-4o-in-5-out-of-8-key-metrics/ | |||
18:43 | Unlocking the Secrets of AI: Mastering Prompt Engineering https://medium.com/@riddhimos2001/unlocking-the-secrets-of-ai-mastering-prompt-engineering-e6fa63d55111 | |||
18:05 | Research to Production: Relative Answer Quality (RAQ) and NVIDIA NIM https://medium.com/@luisroque/research-to-production-relative-answer-quality-raq-and-nvidia-nim-15ce0c45b3b6 | |||
17:39 | I tried to create create a GP guideline Chatbot using RAG method but! https://nyeimchankoko.medium.com/i-tried-to-create-create-a-gp-guideline-chatbot-using-rag-method-but-598bdd6430bd | |||
17:24 | Mastering Prompt Engineering: A Beginner’s Guide to AI Interaction https://medium.com/@tuhinsharma121/mastering-prompt-engineering-a-beginners-guide-to-ai-interaction-2a28434ccb67 | |||
17:20 | LangChain Agent Using Groq Open-Source LLMs: Comparison of Llama 3, Gemma, and Mixtral 8x7b https://medium.com/@keisuke-veritone/langchain-agent-using-groq-open-source-llms-comparison-of-llama-3-gemma-and-mixtral-8x7b-9c936c5aa5ec | |||
17:19 | OpenAI Partners with Los Alamos to Test AI's Value for Scientific Research https://www.bloomberg.com/news/articles/2024-07-10/openai-partners-with-los-alamos-to-test-ai-s-value-for-lab-work | |||
17:18 | The Ultimate Handbook for LLM Quantization https://towardsdatascience.com/the-ultimate-handbook-for-llm-quantization-88bb7cb0d9d7 | |||
17:16 | How AI & LLMs Scale Your SaaS Business? Free Up 20% to 50% of your team’s time! https://medium.com/@makhmali.saeid/how-ai-llms-scale-your-saas-business-free-up-20-to-50-of-your-teams-time-c414cf9cde12 | |||
17:14 | AI Skeleton Key napad — Sajber Info Security https://medium.com/@sasadjuric.do/ai-skeleton-key-napad-sajber-info-security-59a9033c5ca5 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803