LLM News and Articles
Tuesday, 2024-08-06 | ||||
18:31 | Add SALT to Your AI Prompts https://will-s-curran.medium.com/add-salt-to-your-ai-prompts-453564218670 | |||
18:28 | AlphaProof: When AI Crashed the Math Party https://medium.com/@cognidownunder/alphaproof-when-ai-crashed-the-math-party-cbe2c3cad562 | |||
18:19 | How to Use RouteAgent: A Guide to Intelligent AI Task Routing https://blog.stackademic.com/how-to-use-routeagent-a-guide-to-intelligent-ai-task-routing-33be8b6ec9f9 | |||
18:15 | Building Intelligent Agents from Scratch: A Journey into LLM-Powered Autonomy https://pub.towardsai.net/building-intelligent-agents-from-scratch-a-journey-into-llm-powered-autonomy-e998bb9e34ae | |||
18:15 | Comparing Chroma and FAISS involves examining their features, use cases, and performance. https://medium.com/@jh.baek.sd/comparing-chroma-and-faiss-involves-examining-their-features-use-cases-and-performance-f54997632cd6 | |||
17:30 | Beat GPT-4o at Python by searching with 100 dumb LLaMAs https://modal.com/blog/llama-human-eval | |||
17:23 | Elon Musk Revives Lawsuit Against OpenAI and Sam Altman https://www.nytimes.com/2024/08/05/technology/elon-musk-openai-lawsuit.html | |||
16:35 | Large Language Models, Productivity, and Profits: An Essay https://medium.com/thoughts-on-machine-learning/large-language-models-productivity-and-profits-an-essay-f07cfb911dfc | |||
16:15 | Generative AI Frameworks https://medium.com/@ankur.goel_34001/generative-ai-frameworks-25c32bcfb710 | |||
16:05 | Advanced NLP Techniques: Identifying Named Entities in Medical Text with Zero-Shot Learning https://medium.com/john-snow-labs/advanced-nlp-techniques-identifying-named-entities-in-medical-text-with-zero-shot-learning-d511e0c3c28d | |||
16:01 | Bringing LLMs Back to Your Local Machine https://odsc.medium.com/bringing-llms-back-to-your-local-machine-71d69c3abfae | |||
16:00 | Dynamic few-shot examples with LangSmith datasets https://blog.langchain.dev/dynamic-few-shot-examples-langsmith-datasets/ | |||
15:58 | LLM: Warm and cozy https://medium.com/@reshetnikpn/llm-warm-and-cozy-93efff818723 | |||
15:54 | Musk vs. Altman, et al. [pdf] https://s3.documentcloud.org/documents/25031741/elon-vs-openai-again.pdf | |||
15:49 | Learn Anything with AI and the Feynman Technique. https://feminn.medium.com/learn-anything-with-ai-and-the-feynman-technique-c5a5b2d5b132 | |||
15:44 | Writer Releases Palmyra-Med and Palmyra-Fin Models: Outperforming Other Comparable Models, like GPT-4, Med-PaLM-2, and Claude 3.5 Sonnet https://www.marktechpost.com/2024/08/06/writer-releases-palmyra-med-and-palmyra-fin-models-outperforming-other-comparable-models-like-gpt-4-med-palm-2-and-claude-3-5-sonnet/ | |||
15:41 | Understanding LangChain Chains: Explanations and Sample Codes https://chrisyandata.medium.com/understanding-langchain-chains-explanations-and-sample-codes-d4c4c7d9134a | |||
15:34 | Killing Putin: Fun with LLMs https://blog.gopenai.com/killing-putin-fun-with-llms-fde69299b46e | |||
15:32 | Market Research on Healthcare Gen-AI Startups https://cellstrat.medium.com/market-research-on-healthcare-gen-ai-startups-5328ea8b6f64 | |||
15:30 | How We Instrumented Tracing for Vercel AI SDK In Langtrace https://medium.com/langtrace/how-we-instrumented-tracing-for-vercel-ai-sdk-in-langtrace-55de27505378 | |||
15:22 | OpenAI co-founder Schulman leaves for Anthropic, Brockman takes extended leave https://techcrunch.com/2024/08/05/openai-co-founder-leaves-for-anthropic/ | |||
15:20 | Agentic RAG Architecture: A Technical Deep Dive https://medium.com/@rupeshit/agentic-rag-architecture-a-technical-deep-dive-3ec32a2bb4df | |||
15:19 | In the Era of LLM: A Critical Look at Large Language Models https://medium.com/@krupagaliya/in-the-era-of-llm-a-critical-look-at-large-language-models-a1ec24eb4b0a | |||
15:14 | OpenAI and Generative AI Are at a Crossroads https://www.ai-supremacy.com/p/openai-and-generative-ai-are-at-a | |||
14:32 | TAI #111; What Does Deepseek’s 10x Cheaper Reused LLM Input Tokens Unlock? https://pub.towardsai.net/tai-111-what-does-deepseeks-10x-cheaper-reused-llm-input-tokens-unlock-d723662010c6 | |||
14:20 | July 24 GenAI VC Investment Highlights https://343544.medium.com/july-24-genai-vc-investment-highlights-3a416b7de277 | |||
14:19 | Getting Started with Retrieval-Augmented Generation https://medium.com/infinitgraph/getting-started-with-retrieval-augmented-generation-208f123efd3f | |||
14:16 | The LLM Triangle Principles to Architect Reliable AI Apps https://blog.stackademic.com/the-llm-triangle-principles-to-architect-reliable-ai-apps-ad8cea0997e2 | |||
14:11 | Generative AI Made Simple: A Non-Technical Approach https://medium.com/@chenwingu/generative-ai-made-simple-a-non-technical-approach-4ebacd39709f | |||
13:48 | Revolutionizing Spreadsheet Analysis with Large Language Models https://medium.com/@asimsultan2/revolutionizing-spreadsheet-analysis-with-large-language-models-51f2d9add5d7 | |||
13:31 | Basic to Advanced RAG using LlamaIndex (Estimating optimal chunk size)~ 2 https://medium.com/@imabhi1216/basic-to-advanced-rag-using-llamaindex-estimating-optimal-chunk-size-2-4935bdb0ef4a | |||
12:47 | Llama's Legal Labyrinth https://merlijn.sebrechts.be/blog/2024-08-06-problematic-meta-llama-3-1-license/ | |||
12:36 | Gemma vs. Llama vs. Mistral: Exploring Smaller AI Models https://towardsdatascience.com/gemma-vs-llama-vs-mistral-exploring-smaller-ai-models-672a95f4b9b7 | |||
12:29 | Create your very own Jarvis! https://medium.com/@mhmtcndmr01/create-your-very-own-jarvis-c7643d03734b | |||
12:26 | Two new models: Arcee-Spark and Arcee-Agent https://julsimon.medium.com/two-new-models-arcee-spark-and-arcee-agent-e555f479d8cc | |||
12:23 | Adding Memory & Agent interaction into the “Auto-Analyst” https://medium.com/firebird-technologies/adding-memory-agent-interaction-into-the-auto-analyst-01aa7a2d3614 | |||
12:15 | OpenAI Is Doomed? – Et Tu, Microsoft? https://www.semianalysis.com/p/openai-is-doomed-et-tu-microsoft | |||
12:07 | Understanding AI Anomaly Detection: The Key to Modern Data Insights https://deltabytes.medium.com/understanding-ai-anomaly-detection-the-key-to-modern-data-insights-363dfefb45f9 | |||
11:31 | Develop YouTube to Blog Post AI Tools: Ultimate Guide https://medium.com/@marketing_novita.ai/develop-youtube-to-blog-post-ai-tools-ultimate-guide-e7d4ca3c334e | |||
11:23 | Part 7 of Building My First Chatbot: Can You Hear Me? https://medium.com/@aleksmilanov/part-7-of-building-my-first-chatbot-can-you-hear-me-3c8a69752b5c | |||
11:20 | Has AI become mainstream now and are we ready for that? https://medium.com/innovantage-podcast/has-ai-become-mainstream-now-and-are-we-ready-for-that-9dcd6a255033 | |||
11:15 | Agentic AI Recipe Part 2: Build a Router Engine with Watsonx https://medium.com/@madalina.lupu.d/agentic-ai-recipe-part-2-build-a-router-engine-with-watsonx-c141896e1e49 | |||
11:02 | Ai’nt That Easy #7: Build a Trip Planner with CrewAI https://aint-that-easy.medium.com/aint-that-easy-7-build-a-trip-planner-with-crewai-d353d81dcdd9 | |||
11:00 | Chat GPT usage falling off a cliff? https://medium.com/@thomas_reid/chat-gpt-usage-falling-off-a-cliff-2a2afeb8b3c5 | |||
10:55 | Vector Databases : The Powerhouse of Modern Data https://medium.com/@adeenaasif789/vector-databases-the-powerhouse-of-modern-data-c5cf7047dd87 | |||
10:31 | Enhancing ETL and Data Governance Efficiency with Google BigQuery and Vertex AI https://medium.com/the-whispers-of-a-data-analyst/enhancing-etl-and-data-governance-efficiency-with-google-bigquery-and-vertex-ai-e5e28a2ebb44 | |||
10:26 | Life Cycle of Intelligent Conversational Systems powered by Foundational Models — Part 1 https://medium.com/@mangalore.vikash/life-cycle-of-intelligent-conversational-systems-powered-by-foundational-models-part-1-68ed073db9a1 | |||
10:19 | OpenAI 2024 Dev Day Announced https://medium.com/@thomas_reid/openai-2024-dev-day-announced-95a1ba200a16 | |||
10:01 | Understanding the Transformer Model: A Beginner’s Guide — Part 1: Encoder Architecture https://medium.com/@karthiyayini.muthuraj/understanding-the-transformer-model-a-beginners-guide-part-1-encoder-architecture-002af6c69734 | |||
09:12 | Llama Coder AI Code Generator Llama 3.1 405B https://augmentedstartups.medium.com/llama-coder-ai-code-generator-llama-3-1-405b-4cb09948748d | |||
09:12 | Llama Coder AI Code Generator Llama 3.1 405B https://medium.com/augmented-startups/llama-coder-ai-code-generator-llama-3-1-405b-4cb09948748d | |||
08:41 | InstructLAB and Synthethic data generation with llama3 models — extending to Thai language https://medium.com/@mewleenutaphong/instructlab-and-synthethic-data-generation-with-llama3-models-extending-to-thai-language-5ebca73a371c | |||
08:39 | OpenAI co-founder John Schulman says he will leave and join rival Anthropic https://www.cnbc.com/2024/08/06/openai-co-founder-john-schulman-says-he-will-join-rival-anthropic.html | |||
08:20 | Use COT to enhance your prompt https://medium.com/@aq1774533360/use-cot-to-enhance-your-prompt-a7295b486ccb | |||
08:02 | 5 Top Large Language Models & Generative AI Books https://pub.towardsai.net/5-top-large-language-models-generative-ai-books-fdca173b67a8 | |||
07:53 | Free Inference Is All I Need: How to Run Large Language Models for Free Using Google Colab https://medium.com/@lorenzoantonino946/free-inference-is-all-i-need-how-to-run-large-language-models-for-free-using-google-colab-fe961e86503b | |||
07:51 | Llama 3.1 on iOS Siri using Groq https://mukulpatech.medium.com/llama-3-1-on-ios-siri-using-groq-7f89b93d051d | |||
07:49 | Unlocking the Power of Information: A Beginner’s Guide to Retrieval Augmented Generation (RAG) https://medium.com/@rishik.8102001/unlocking-the-power-of-information-a-beginners-guide-to-retrieval-augmented-generation-rag-e45615d6c66d | |||
07:14 | Fine-Tuning vs RAG (Part-2) https://medium.com/@siddheshraw/fine-tuning-vs-rag-part-2-ba8229117641 | |||
07:10 | Tutorial on Using AutoGen with Local LLMs via FastChat https://medium.com/@a.asgharpoor1993/tutorial-on-using-autogen-with-local-llms-via-fastchat-5f7fe29ec72d | |||
06:37 | Multi-Agentic RAG: The Future of Scalable Enterprise Applications with LLMs https://medium.com/@nirajan.acharya777/multi-agentic-rag-the-future-of-scalable-enterprise-applications-with-llms-30492f3038df | |||
05:46 | New AMD ROCm 6.2 For Next-Gen AI & HPC Performance https://medium.com/@agarapuramesh/new-amd-rocm-6-2-for-next-gen-ai-hpc-performance-5d96cfac240c | |||
05:26 | Top Trends in Large Language Models (LLMs) https://medium.com/@analyticsinsightsubmissions/top-trends-in-large-language-models-llms-d1ff14963f61 | |||
05:24 | (Part 3) Mastering MiniCPM-V: Finetuning Your Model for Peak Performance https://medium.com/data-science-in-your-pocket/part-3-mastering-minicpm-v-finetuning-your-model-for-peak-performance-5cd42a697470 | |||
05:09 | Here Are the Apple Intelligence System Prompts: https://towards-agi.medium.com/here-are-the-apple-intelligence-system-prompts-e903d9d92b34 | |||
03:58 | Can AI Spot Its Own Work? The Race to Detect ChatGPT-Written Text https://digitizingpolaris.com/can-ai-spot-its-own-work-the-race-to-detect-chatgpt-written-text-58091b0ac8f1 | |||
01:46 | Elon Musk is suing OpenAI again, claims CEO Sam Altman 'betrayed' him https://www.theregister.com/2024/08/05/musk_new_lawsuit_openai/ | |||
01:29 | Bytedance Researchers Present Cross Language Agent – Simultaneous Interpretation (CLASI): A High-Quality And Human-Like Simultaneous Speech Translation (SiST) System https://www.marktechpost.com/2024/08/05/bytedance-researchers-present-cross-language-agent-simultaneous-interpretation-clasi-a-high-quality-and-human-like-simultaneous-speech-translation-sist-system/ | |||
01:23 | Greg Brockman, John Schulman and Peter Deng Leave OpenAI https://archive.ph/2024.08.06-003519/https://www.theinformation.com/articles/trio-of-leaders-leave-openai | |||
00:45 | OpenAI President Greg Brockman, Co-Founder John Schulman, & Peter Deng https://twitter.com/theinformation/status/1820619485448966282 | |||
00:44 | Trio of Leaders Leave OpenAI https://www.theinformation.com/articles/trio-of-leaders-leave-openai | |||
00:42 | Summarizing YouTube Content with LMStudio: A Step-by-Step Guide https://medium.com/@omkamal/summarizing-youtube-content-with-lmstudio-a-step-by-step-guide-b3e0b020a89a | |||
00:34 | Understanding Vector Databases: What They Are and When to Use Them https://medium.com/thedeephub/understanding-vector-databases-what-they-are-and-when-to-use-them-a3c67c9cdb11 | |||
00:33 | Lately, I have been playing with Llama 3.1, https://medium.com/@olafeezee/lately-i-have-been-playing-with-llama-3-1-754e8f78c66d | |||
00:26 | What is needed for AGI by 2029? https://medium.com/pat-inc/what-is-needed-for-agi-by-2029-b23fac7c81f3 | |||
00:18 | RAGEval: framework to automatically generate RAG Evaluation Datasets for different domains https://medium.com/@techsachin/rageval-framework-to-automatically-generate-rag-evaluation-datasets-for-different-domains-df270c9893df | |||
00:05 | OpenAI co-founder John Schulman announces he is joining Anthropic https://twitter.com/johnschulman2/status/1820610863499509855 | |||
00:00 | Introducing TextImage Augmentation for Document Images https://huggingface.co/blog/doc_aug_hf_alb | |||
00:00 | 2024 Security Feature Highlights https://huggingface.co/blog/2024-security-features | |||
Monday, 2024-08-05 | ||||
22:44 | Building a Personal AI Assistant to Manage Your Emails https://medium.com/@tybalex/building-a-personal-ai-assistant-to-manage-your-emails-fc1b1ff24ced | |||
22:19 | OpenAI Prompt Guide https://platform.openai.com/docs/guides/prompt-engineering/six-strategies-for-getting-better-results | |||
22:05 | SQL to React Components in seconds https://medium.com/@blokay/sql-to-react-components-in-seconds-07f58e569ee4 | |||
22:00 | OpenAI tempers expectations with less bombastic, GPT-5-less DevDay this fall https://techcrunch.com/2024/08/05/openai-tempers-expectations-with-less-bombastic-gpt-5-less-devday-this-fall/ | |||
21:50 | LLM Decoding: Balancing Quality and Latency https://medium.com/@aalokpatwa/llm-decoding-balancing-quality-and-latency-23632cc0277e | |||
21:16 | The Braindead Senior Dev Hypothesis https://medium.com/@impure/the-braindead-senior-dev-hypothesis-3b34067747ba | |||
21:12 | Will OpenAI's new AI detection tool put an end to student cheating? https://www.zdnet.com/article/will-openais-new-ai-detection-tool-put-an-end-to-student-cheating/ | |||
20:41 | Intro to LangChain https://medium.com/@swethag04/intro-to-langchain-1d2119e2fef8 | |||
20:29 | Understanding Fairness and Challenges in Scaled LLM Serving https://medium.com/@kushagramisra10/understanding-fairness-and-challenges-in-scaled-llm-serving-6f31ff3b4894 | |||
20:27 | Building AI Tools that supercharge your LLMs https://ai.gopubby.com/building-ai-tools-that-supercharge-your-llms-562eea08d23c | |||
20:24 | Announcing the ‘tool-calling-llm’ Package: Adding Tool Use to LLMs https://medium.com/@klcoder/announcing-the-tool-calling-llm-package-adding-tool-use-to-llms-4ce6b6d1d076 | |||
20:21 | Using G-Retriever For Anomaly Explanation In Graphs https://medium.com/@unshrawal/g-retriever-afor-anomaly-explanation-84edf2568d26 | |||
20:19 | Creating an Interactive AI Assistant for CSV Data with LangChain and gTTS https://medium.com/@ahsantariq0724/creating-an-interactive-ai-assistant-for-csv-data-with-langchain-and-gtts-abfd28c00fde | |||
19:55 | The Development of AI Agents: How We Deployed an Army in Our Business https://medium.com/@karl.foster/the-development-of-ai-agents-how-we-deployed-an-army-in-our-business-6c67f51e3d1d | |||
19:50 | Milvus and Pinecone comparison overview https://medium.com/@nunocarvalhodossantos/milvus-and-pinecone-comparison-overview-82875c290a2b | |||
19:48 | Elon Musk is suing OpenAI and Sam Altman again https://www.theverge.com/2024/8/5/24213557/elon-musk-openai-lawsuit-sam-altman-greg-brockman-revived | |||
19:39 | Prompt Compression — Hands on Guide for LLM Lingua-2 https://deveshsurve.medium.com/prompt-compression-hands-on-guide-for-llm-lingua-2-2baac53800d6 | |||
19:10 | Show HN: Run Mutahunter.ai LLM powered software testing on your code in browser https://replit.com/@raghuramabilash/Mutahunterai | |||
19:02 | Make Conversations with Any or Multiple Documents: A Comprehensive Guide to Building an LLM… https://medium.com/@jeslurrahman/make-conversations-with-any-or-multiple-documents-a-comprehensive-guide-to-building-an-llm-dedd3a34ac85 | |||
19:01 | Enhancing LLM Pre-training: URL-Level Data De-Duplication — Part I https://medium.com/@bhabanin/enhancing-llm-pre-training-url-level-data-de-duplication-part-i-b471d577d6c8 | |||
18:13 | CSWSH Meets LLM Chatbots https://medium.com/@r3vsh/cswsh-meets-llm-chatbots-3ab09af5ab6f |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803