LLM News and Articles
Friday, 2024-08-30 | ||||
12:59 | Amazon turns to Anthropic's AI for Alexa revamp https://www.reuters.com/technology/artificial-intelligence/amazon-turns-anthropics-claude-alexa-ai-revamp-2024-08-30/ | |||
12:34 | Solving Math Problems with LLMs https://medium.com/@arturgrygorian3/solving-math-problems-with-llms-921e287f5796 | |||
12:10 | “Hello World, LLM 2.0” —Relooking at using LLMs locally https://medium.com/@ar.arun/hello-world-llm-2-0-relooking-at-using-llms-locally-52f379998e6d | |||
11:42 | Mistral Models vs. Competitors: A Performance Showdown Across NLP, Code, and Multilingual Tasks https://medium.com/@researchgraph/mistral-models-vs-competitors-a-performance-showdown-across-nlp-code-and-multilingual-tasks-af2f901455bc | |||
11:40 | Trying LLM(gpt-4o-mini) on TweetQA dataset https://chinsj.medium.com/trying-llm-gpt-4o-mini-on-tweetqa-dataset-73efbba4605f | |||
11:34 | Relevance Revolution: How Re-ranking Transforms RAG Systems https://medium.com/@nirdiamant21/relevance-revolution-how-re-ranking-transforms-rag-systems-0ffaa15f1047 | |||
11:33 | Setting Up Your Own Local AI Search engine with Memfree,Supporting Knowledge Base Uploads https://medium.com/@pamperherself/setting-up-your-own-local-ai-search-engine-with-memfree-supporting-knowledge-base-uploads-6e13f78fbbea | |||
11:15 | Feds to get early access to OpenAI, Anthropic AI to test for doomsday scenarios https://arstechnica.com/tech-policy/2024/08/feds-to-get-early-access-to-openai-anthropic-ai-to-test-for-doomsday-scenarios/ | |||
11:05 | Amazon to Launch New AI-Powered Alexa Using Anthropic's Claude https://www.macrumors.com/2024/08/30/amazon-launching-new-alexa-claude-ai/ | |||
10:43 | Small vs. Large — The Battle of Language Models in AI https://medium.com/@researchgraph/small-vs-large-the-battle-of-language-models-in-ai-3a0970ae7194 | |||
10:18 | Efficient Fine-Tuning with LoRA and QLoRA https://medium.com/tuitech/efficient-fine-tuning-with-lora-and-qlora-71566d0804ed | |||
10:13 | Using LLMs to transpile code (from Go & Java to Ruby) https://medium.com/@symflower/using-llms-to-transpile-code-from-go-java-to-ruby-dbba6046298d | |||
10:05 | What is Multimodal AI? https://medium.com/@researchgraph/what-is-multimodal-ai-7b3cd41a020b | |||
09:54 | Open Source vs. Big Tech: Who Will Win the AI War? https://medium.com/@inetanel/open-source-vs-big-tech-who-will-win-the-ai-war-4e5fd17530e5 | |||
09:37 | Building a Search Generator https://medium.com/@cwakhusama/building-a-search-generator-43fe4f1a37b9 | |||
08:26 | Les dernières avancées et défis des Large Language Models https://medium.com/@patrick.darbeau/les-derni%C3%A8res-avanc%C3%A9es-et-d%C3%A9fis-des-large-language-models-62df831a99c6 | |||
08:06 | Deploying LLM Models with Node.js: A Comprehensive Guide https://medium.com/@a_farag/deploying-llm-models-with-node-js-a-comprehensive-guide-b5989cfbdd05 | |||
06:46 | Alibaba Cloud Customer Service Agent: Thoughts, Design, and Practices from Concept to… https://medium.com/@lararoself/alibaba-cloud-customer-service-agent-thoughts-design-and-practices-from-concept-to-7f3d6a7e6b2d | |||
06:31 | OpenAI says ChatGPT's weekly users have grown to 200M https://www.reuters.com/technology/artificial-intelligence/openai-says-chatgpts-weekly-users-have-grown-200-million-2024-08-29/ | |||
05:49 | Unraveling RAG: A Non-Exhaustive Brief to Get Started — Part 2 https://medium.com/@maruthiprithivirajan/unraveling-rag-a-non-exhaustive-brief-to-get-started-part-2-6ddfe091a8d3 | |||
05:09 | Compressing Large Language Models (LLMs) https://towardsdatascience.com/compressing-large-language-models-llms-9f406eea5b5e | |||
05:04 | 101 Python Automation Scripts: Streamlining Tasks and Boosting Productivity(Part #1)Revised https://python.plainenglish.io/101-python-automation-scripts-streamlining-tasks-and-boosting-productivity-part-1-revised-f9d2b4db6539 | |||
04:25 | Retrieval Augmented Generation (RAG) https://medium.com/@aminajavaid30/retrieval-augmented-generation-rag-1cb29b19e77b | |||
04:22 | Automated Multi Turn LLM Jailbreaks — Crescendo from Microsoft https://blog.aim-intelligence.com/automated-multi-turn-llm-jailbreaks-crescendo-from-microsoft-2ff54df304c7 | |||
04:21 | Entity Recognition with LLMs and the Importance of Prompt Engineering (all languages) https://medium.com/@lucasmassucci/entity-recognition-with-llms-and-the-importance-of-prompt-engineering-all-languages-ceda8a7ff3e2 | |||
03:15 | GraphRAG with Databricks and PuppyGraph https://medium.com/@ajmal.t.aziz/graphrag-with-databricks-and-puppygraph-5c7b1cda0e41 | |||
02:49 | AI’s Blind Spot: Detecting LLM Hallucinations https://medium.com/@vikasgautamacc/ais-blind-spot-unraveling-the-mysteries-of-llm-hallucinations-00441c415847 | |||
02:46 | OpenAI and Anthropic will share their models with the US government https://www.cnbc.com/2024/08/29/openai-and-anthropic-agree-to-let-us-ai-safety-institute-test-models.html | |||
02:37 | AWS’s Comprehensive Stack for Generative AI https://sanjmo.medium.com/awss-comprehensive-stack-for-generative-ai-d9233c89a775 | |||
02:04 | Generative AI will not save your lack of strategy in Personalization https://arvindmozumdar.medium.com/generative-ai-will-not-save-your-lack-of-strategy-in-personalization-bdcc39c342dd | |||
00:58 | Paper Digest: Mixture of LoRA Experts (ICLR’24) https://generativeai.pub/paper-digest-mixture-of-lora-experts-iclr24-4c59332b23db | |||
00:54 | How to detect Hallucinations in LLM? https://generativeai.pub/how-to-detect-hallucinations-in-llm-9b9e73e97566 | |||
00:48 | The Promise of Virtual Assistants https://generativeai.pub/the-promise-of-virtual-assistants-26777c30355c | |||
00:38 | Can ChatGPT do data science? https://austinhenley.com/blog/chatgptdatascience.html | |||
Thursday, 2024-08-29 | ||||
23:58 | A Paper + the KnowLLM Workshop — Research Summary #4 https://medium.com/@mkuthalam/a-paper-the-knowllm-workshop-research-summary-4-c6103834ca3b | |||
23:56 | 0B Medical Overbilling: Can LLMs & Protecto Provide the Cure? https://amarkanagaraj.medium.com/200b-medical-overbilling-can-llms-protecto-provide-the-cure-669da27ca3d2 | |||
23:28 | Unlock the Power of LogSeq with AssistSeq: Your Smart AI Companion https://medium.com/@galihlprakoso/unlock-the-power-of-logseq-with-assistseq-your-smart-ai-companion-2455c265c5f2 | |||
23:14 | The Journey of a Young Professional and the Power of Retrieval-Augmented Generation (RAG) https://medium.com/@oladayo_7133/the-journey-of-a-young-professional-and-the-power-of-retrieval-augmented-generation-rag-9602d32a2047 | |||
23:13 | How to get started with Gemma models https://medium.com/@viajesubmarino/how-to-get-started-with-gemma-models-e211564da3aa | |||
22:42 | Leveraging LLMs for Semantic Type Detection in Data Lakes https://megagonlabs.medium.com/leveraging-llms-for-semantic-type-detection-in-data-lakes-f38bc4e5c6ee | |||
22:21 | Anthropic's Prompt Engineering Interactive Tutorial https://github.com/anthropics/courses/tree/master/prompt_engineering_interactive_tutorial | |||
22:21 | Large Language Models https://medium.com/@surabhivasudev1993/large-language-models-031165519b39 | |||
22:12 | How to Enable Large Language Models (LLM) on an Excel File https://medium.com/@siladityaghosh/how-to-enable-large-language-models-llm-on-an-excel-file-4a9c5efd2f85 | |||
21:56 | ChatGPT now has 200M weekly users https://www.theverge.com/2024/8/29/24231685/openai-chatgpt-200-million-weekly-users | |||
21:41 | Comprehensive Guide: Deploying LLM Models over Python Servers https://medium.com/@a_farag/comprehensive-guide-deploying-llm-models-over-python-servers-98750f7c1b71 | |||
21:19 | The OSI Has Had Enough Of Mark Zuckerberg’s BS https://medium.com/@impure/the-osi-has-had-enough-of-mark-zuckerbergs-bs-c566d202801b | |||
21:18 | Nvidia Discusses Joining OpenAI's Latest Funding Round https://www.bloomberg.com/news/articles/2024-08-29/nvidia-has-held-discussions-about-joining-openai-s-funding-round | |||
21:06 | How to create an AI chatbot using one API to access multiple LLMs https://medium.com/streamlit/how-to-create-an-ai-chatbot-using-one-api-to-access-multiple-llms-78e667f6cc77 | |||
20:16 | Understanding Transformers: A Simplified Guide with Easy-to-Understand Examples https://medium.com/@asimsultan2/understanding-transformers-a-simplified-guide-with-easy-to-understand-examples-227fd8d31848 | |||
20:09 | 1. NPUs and On-Device AI — The LLM Hardware Series. https://medium.com/@alfredruhara/1-npus-and-on-device-ai-the-llm-hardware-series-1dafd5e9b86e | |||
19:29 | Membangun Model Bahasa LLM Spesifik Domain:
Solusi Efektif Untuk Kebutuhan Industri https://medium.com/@deddy.ratnanto/membangun-model-bahasa-llm-spesifik-domain-solusi-efektif-untuk-kebutuhan-industri-b55ad7a3292a | |||
19:05 | Turn Boring RSS Feeds into Captivating Podcasts in Just 5 Steps https://medium.com/@paulelliotco/turn-boring-rss-feeds-into-captivating-podcasts-in-just-5-steps-3f92f293692b | |||
18:47 | What is Embeddings ? https://medium.com/@nirbhaysingh281/what-is-embeddings-a1f031041a61 | |||
18:37 | Agent & Tools — ReAct DocStore https://medium.com/@shravankoninti/agent-tools-react-docstore-0c26cc5adf19 | |||
18:36 | Exploring the Untapped Aspect of Defeasibility in Causal Reasoning https://medium.com/@scepfl/exploring-the-untapped-aspect-of-defeasibility-in-causal-reasoning-1d06032dfa94 | |||
18:31 | Revolutionize Your Workflow with These Free AI Tools: A Comprehensive Guide https://medium.com/@marocsofiane20/revolutionize-your-workflow-with-these-free-ai-tools-a-comprehensive-guide-16511193bb34 | |||
18:24 | Show HN: Geppetto v0.2.5 Claude, ChatGPT, and Gemini OSS Companion in Your Slack https://deeptechia.io/blog/geppetto-v0-2-5/ | |||
18:22 | What is Generative AI and why is everyone talking about it? https://medium.com/@khushibhoj/what-is-generative-ai-and-why-is-everyone-talking-about-it-89e610483e1d | |||
18:13 | Apple in talks to invest in OpenAI as ChatGPT comes to iOS 18 https://9to5mac.com/2024/08/29/apple-openai-investment-ios-18-chatgpt/ | |||
17:47 | Apple in Talks to Join New OpenAI Funding Round https://www.wsj.com/tech/ai/openai-apple-funding-chatgpt-50754cd6 | |||
17:47 | From Text to Networks: The Revolutionary Impact of LLMs on Knowledge Graphs https://towardsdatascience.com/from-text-to-networks-the-revolutionary-impact-of-llms-on-knowledge-graphs-67551b5b76e6 | |||
17:43 | From SAS to Python: Navigating the AI-Powered Migration Journey https://medium.com/@annadu01/from-sas-to-python-navigating-the-ai-powered-migration-journey-9e71a325dc2c | |||
17:20 | The Smarter Way of Using AI in Programming https://towardsdatascience.com/the-smarter-way-of-using-ai-in-programming-0492ac610385 | |||
16:43 | What is the Best Platform for Learning How to Build ML Models and Implement LLMs https://unicornmobile.medium.com/what-is-the-best-platform-for-learning-how-to-build-ml-models-and-implement-llms-16e2d7c1b0f7 | |||
16:37 | Generation Sampling in LLMs: Implementation and Explanation https://medium.com/@parulsharma_8357/generation-sampling-in-llms-implementation-and-explanation-69415edddc8c | |||
16:30 | How to become a great LLM engineer https://blog.floworks.ai/how-to-become-a-star-llm-engineer/ | |||
16:26 | 6 Hard-learned Lessons from My First Project as a Freelance AI Engineer. https://ai.gopubby.com/6-hard-learned-lessons-from-my-first-project-as-a-freelance-ai-engineer-9519e6edee90 | |||
16:22 | RagBuilder: A Toolkit that Automatically Finds the Best Performing RAG Pipeline for Your Data and Use-Case https://www.marktechpost.com/2024/08/29/ragbuilder-a-toolkit-that-automatically-finds-the-best-performing-rag-pipeline-for-your-data-and-use-case/ | |||
16:20 | OpenAI and Anthropic will share their models with the US government https://www.theverge.com/2024/8/29/24231395/openai-anthropic-share-models-us-ai-safety-institute | |||
16:03 | What is a Tokenizer ? https://medium.com/@francesco.cozzolino/what-is-a-tokenizer-a1b7215ebd92 | |||
16:02 | A visual explanation of LLM hyperparameters https://towardsdatascience.com/a-visual-explanation-of-llm-hyperparameters-daf61d3b006e | |||
15:45 | Making our own code interpreter: Part 1, making of a sandbox https://medium.com/@Shrishml/making-our-own-code-interpreter-part-1-making-of-a-sandbox-382da3339eaa | |||
15:42 | Supercharging AI with Multi Agent Systems https://medium.com/catiotech/supercharging-ai-with-multi-agent-systems-ea13fa363ab7 | |||
15:04 | The System Prompts Behind Claude’s Artifacts https://medium.com/@MohammedSAHLI/the-system-prompts-behind-claudes-artifacts-64e4c32d4fd4 | |||
15:01 | #38 Back to Basics — RAG, Transformers, ML Optimization, and LLM Evaluation. https://pub.towardsai.net/38-back-to-basics-rag-transformers-ml-optimization-and-llm-evaluation-41acdbfc923c | |||
15:01 | NVIDIA’s Minitron: Compressing Llama 3.1 https://medium.com/syncedreview/nvidias-minitron-compressing-llama-3-1-1671ee500b52 | |||
14:56 | Private Data, Powerful Insights: Building an Offline LLM Application https://medium.com/@dominique.heer/private-data-powerful-insights-building-an-offline-llm-application-6a5542bc1342 | |||
14:38 | Update on Llama adoption https://ai.meta.com/blog/llama-usage-doubled-may-through-july-2024/ | |||
14:15 | Has Science gone too far? https://medium.com/@caspervancoesant/has-science-gone-too-far-a3a5cdb6db33 | |||
14:08 | Model Collapse is a Fake Problem https://dustinwehr.medium.com/model-collapse-is-a-fake-problem-4c467f0f4ebf | |||
14:02 | System 2 Distillation https://medium.com/@simple0314/system-2-distillation-03073c613fc5 | |||
13:55 | Understanding the Linear (Identity) Activation Function in Neural Networks https://medium.com/@punya8147_26846/understanding-the-linear-identity-activation-function-in-neural-networks-60c425725820 | |||
13:49 | OpenAI’s Project Orion and Strawberry AI: The Next Frontier in Language Models https://medium.com/@AshJai/openais-project-orion-and-strawberry-ai-the-next-frontier-in-language-models-048641fdf0f6 | |||
13:33 | Large Language Model https://deepakbalmiki.medium.com/large-language-model-0100a9ddc31a | |||
13:22 | Understanding and Mitigating Security Risks in Large Language Model Applications https://medium.com/@srini.hebbar/understanding-and-mitigating-security-risks-in-large-language-model-applications-71043f9f5a4b | |||
13:11 | OpenAI and Anthropic sign safety agreement with US Government https://www.nist.gov/news-events/news/2024/08/us-ai-safety-institute-signs-agreements-regarding-ai-safety-research | |||
13:11 | Do you need a multiagent setup or just an LLM-calling tool? https://medium.com/motleycrew-ai/do-you-need-a-multiagent-setup-or-just-an-llm-calling-tool-ca1268be49d6 | |||
13:08 | AI and the Future of Strategic Mastery: Outpacing Human Genius https://medium.com/@olserra/ai-and-the-future-of-strategic-mastery-outpacing-human-genius-a88f4cb0fca2 | |||
12:50 | BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts — A discussion https://medium.com/@dhruvansh26/bam-just-like-that-simple-and-efficient-parameter-upcycling-for-mixture-of-experts-a-discussion-fcb0845e4410 | |||
12:38 | Feedback Collection Mechanisms for RAG and Prompt-Engineered Systems in Production https://medium.com/feedback-intelligence/feedback-collection-mechanisms-for-rag-and-prompt-engineered-systems-in-production-e88316b1fa9b | |||
12:25 | Local RAG Implementation in Core Python: A Comprehensive Guide https://levelup.gitconnected.com/local-rag-implementation-in-core-python-a-comprehensive-guide-99826208dd67 | |||
12:16 | Anthropic Claude – The Future of AI Language Models https://medium.com/@dreamschaser612/anthropic-claude-the-future-of-ai-language-models-301d98efc439 | |||
12:12 | Let’s Quit ChatGPT and Copilot — How to Install Your Own LLM for Privacy and Security https://medium.com/@chloe.lavrat/lets-quit-chatgpt-and-copilot-how-to-install-your-own-llm-for-privacy-and-security-fa491b7d414c | |||
11:55 | Multi-Agent-as-a-Service — A Senior Engineer’s Overview https://medium.com/binome/multi-agent-as-a-service-a-senior-engineers-overview-4e4a020cde44 | |||
11:19 | Show HN: KTransformers–236B Model and 1M Context LLM Inference on Local Machines https://github.com/kvcache-ai/ktransformers | |||
11:17 | Tame the GenAI Models https://medium.com/@kalyana.bedhu/tame-the-genai-models-021482ca75ee | |||
10:49 | AI Chatbot: ChatGPT, LLM, OpenAI, LangChain, Pinecone https://medium.com/@asfandyar5144/ai-chatbot-chatgpt-llm-openai-langchain-pinecone-a5dccc9f628c | |||
10:35 | Solving Math Problems with LLMs: https://medium.com/@arturgrygorian3/solving-math-problems-with-llms-fed77f4cf4ec | |||
10:22 | OpenAI in talks to raise funding that would value it at more than 0B https://www.cnbc.com/2024/08/28/openai-in-talks-to-raise-funding-that-would-value-it-at-more-than-100-billion.html | |||
10:14 | OpenAI is good at unminifying code https://glama.ai/blog/2024-08-29-reverse-engineering-minified-code-using-openai |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803