LLM News and Articles
| Thursday, 2024-10-31 | ||||
| 09:17 | Are “Character Settings” in Prompts Useful for Large Models? https://wshuyi.medium.com/are-character-settings-in-prompts-useful-for-large-models-ffeb80d2e036 | |||
| 09:14 | Powering KNAI: The Role of Knowledge Graph — Neo4j as backbone of KNAI — Part 2 https://medium.com/knowledge-nexus-ai/powering-knai-the-role-of-knowledge-graph-neo4j-as-backbone-of-knai-part-2-13871673b934 | |||
| 08:53 | DSPy: Move Beyond Prompt Hacking with Language Model Programming https://agimentat.medium.com/dspy-move-beyond-prompt-hacking-with-language-model-programming-82f88b340b0a | |||
| 08:31 | Introduction to Large Language Models (LLMs) https://phuongthunee.medium.com/introduction-to-large-language-models-llms-bc17d3cef377 | |||
| 08:17 | Construction et fonctionnement des LLMs : un aperçu non technique https://medium.com/@mhtgoudjemi/construction-et-fonctionnement-des-llms-un-aper%C3%A7u-non-technique-7a898a621192 | |||
| 08:11 | How I fixed my coffee machine using a RAG System https://ficiverson.medium.com/how-i-fixed-my-coffee-machine-using-a-rag-system-a2090c50140f | |||
| 08:00 | Previously, I introduced a method proposed by the Anthropic research team that significantly… https://ullyer.medium.com/previously-i-introduced-a-method-proposed-by-the-anthropic-research-team-that-significantly-00c68d352be8 | |||
| 07:41 | Why play with LLMs? https://martinzachthomas.medium.com/why-play-with-llms-abef0a82f2ef | |||
| 07:41 | AI-Interviewer bot (V1) https://martinzachthomas.medium.com/ai-interviewer-bot-v1-ea5504809858 | |||
| 07:17 | Evaluating LLM-based chatbots: A comprehensive guide to performance metrics https://medium.com/data-science-at-microsoft/evaluating-llm-based-chatbots-a-comprehensive-guide-to-performance-metrics-9c2388556d3e | |||
| 07:12 | LangChain https://python.plainenglish.io/langchain-85e5899185ed | |||
| 06:59 | RAG: The Game-Changer in LLM Applications — What’s Your Take? https://medium.com/@gunkurnia/rag-the-game-changer-in-llm-applications-whats-your-take-34f8352a1e6b | |||
| 06:43 | Exploring CrewAI: Empowering Multi-Agent Systems — Ollama using LLama3.2 https://falexm.medium.com/exploring-crewai-empowering-multi-agent-systems-ollama-using-llama3-2-f3ea266b9149 | |||
| 06:06 | Fine-Tuning Language Models for Specialized Tasks: A Step-by-Step Guide https://medium.com/data-and-beyond/fine-tuning-language-models-for-specialized-tasks-a-step-by-step-guide-7a6d82e1f824 | |||
| 05:40 | Stop Worrying About Basic Data Breaches! The Real LLM Security Threat is… https://generativeai.pub/stop-worrying-about-basic-data-breaches-the-real-llm-security-threat-is-e41038406a3a | |||
| 05:04 | Build an Intelligent Document Processing with Confidence Scores with GPT-4o https://djajafer.medium.com/build-an-intelligent-document-processing-with-confidence-scores-with-gpt-4o-ff93083e4ce5 | |||
| 04:57 | Staying Irreplaceable in an AI-Driven World: A Developer’s Guide https://iamshobhitagarwal.medium.com/staying-irreplaceable-in-an-ai-driven-world-a-developers-guide-7cbf512b0bbc | |||
| 04:44 | LLM GUI: Custom Python Gradio Interface https://admantium.medium.com/llm-gui-custom-python-gradio-interface-518d11bb2135 | |||
| 04:35 | Faux Data, Real Insights: Generating Synthetic Data From Scratch with LLMs in Snowflake https://medium.com/snowflake/faux-data-real-insights-generating-synthetic-data-from-scratch-with-llms-in-snowflake-e6657dedffaf | |||
| 04:32 | Microsoft’s GitHub isn’tall-in on OpenAI https://digitizingpolaris.com/microsofts-github-isn-tall-in-on-openai-3bb8344872a5 | |||
| 03:12 | 31 Days of Learning (1 Day 1 Course): Embracing a Data-Centric Approach in AI Development https://solomonsoh.medium.com/31-days-of-learning-1-day-1-course-embracing-a-data-centric-approach-in-ai-development-49244ba626b4 | |||
| 03:01 | In-Depth Report: Seven Peaks AI Event https://y-consulting.medium.com/in-depth-report-seven-peaks-ai-event-013cd0f823d7 | |||
| 02:16 | LLM Interview Questions(Large Language Models): Top Interview Questions and Answers https://medium.com/@iambeniwal12/llm-interview-questions-large-language-models-top-interview-questions-and-answers-da9ce56d3d39 | |||
| 01:51 | Fine-Tuning Foundational Models: A Guide to Customizing AI for Specific Needs https://consultkora.medium.com/fine-tuning-foundational-models-a-guide-to-customizing-ai-for-specific-needs-295c8a6222e6 | |||
| 01:42 | Harnessing the Power of AI Memory: Use Cases for Mem0 in Real-World Applications https://timothy-urista.medium.com/harnessing-the-power-of-ai-memory-use-cases-for-mem0-in-real-world-applications-4114653fb282 | |||
| 01:31 | Fine-Tuning Large Language Models (BERT, RoBERTa, SBERT) https://dhirajkumarblog.medium.com/fine-tuning-large-language-models-bert-roberta-sbert-a457182ba8bf | |||
| 01:23 | Do LLMs “reason” or display cognitive capabilities as it has been lately suggested? https://medium.com/about-ai/do-llms-reason-or-display-cognitive-capabilities-as-it-has-been-lately-suggested-fbb034c16274 | |||
| 00:01 | The new technology wave and the potential of AI agents. https://medium.com/@samuelakanz/the-new-technology-wave-and-the-potential-of-ai-agents-4cf61af30414 | |||
| Wednesday, 2024-10-30 | ||||
| 23:57 | Rise of the AI tools https://medium.com/@aiml_58187/rise-of-the-ai-tools-ca8c9de69ff3 | |||
| 23:52 | I will introduce LLM SFT (Supervised Fine-Tuning) from building the training data to training. https://blog.stackademic.com/i-will-introduce-llm-sft-supervised-fine-tuning-from-building-the-training-data-to-training-4799128d51ef | |||
| 23:46 | Pre-trained Language Models: Generative vs. https://medium.com/@prasanNH/pre-trained-language-models-generative-vs-01007b8749a6 | |||
| 23:43 | Building a Knowledge-Powered LLM Chatbot with Retrieval-Augmented Generation (RAG) https://medium.com/@yxinli92/building-a-knowledge-powered-llm-chatbot-with-retrieval-augmented-generation-rag-c6193097cbec | |||
| 23:41 | GitHub Copilot moves beyond OpenAI models to support Claude 3.5, Gemini https://arstechnica.com/ai/2024/10/github-copilot-moves-beyond-openai-models-to-support-claude-3-5-gemini/ | |||
| 23:32 | Micro Soft https://medium.com/@mexim0905/micro-soft-ae7643908957 | |||
| 23:28 | Fine-Tuning Models with Amazon Bedrock: A Step-by-Step Guide https://medium.com/@yxinli92/fine-tuning-models-with-amazon-bedrock-a-step-by-step-guide-34122f91ea9c | |||
| 23:04 | Getting Started with LLaMA: LangChain and the Basics of RAG https://medium.com/@alessandro.a.pagliaro/getting-started-with-llama-langchain-and-the-basics-of-rag-967f06a3fbc1 | |||
| 22:05 | What I learned about LangChain framework this week? https://medium.com/@f20200812/what-i-learned-about-langchain-framework-this-week-6c75dcbd03db | |||
| 21:51 | Lifelong Learning: The Key to Surviving in an AI-Driven Development Environment https://timothy-urista.medium.com/lifelong-learning-the-key-to-surviving-in-an-ai-driven-development-environment-be1fa11b217e | |||
| 21:32 | OpenAI’s New QA Benchmark: SimpleQA https://aiintransit.medium.com/openais-new-qa-benchmark-simpleqa-ed70ee304517 | |||
| 21:29 | Smarter AI for Leaner Operations: The Hybrid LLM Advantage https://medium.com/awarity-ai-blog/smarter-ai-for-leaner-operations-the-hybrid-llm-advantage-6da798d7ae86 | |||
| 21:20 | Show HN: Costco for LLM Tokens https://inference.net/ | |||
| 21:04 | LLMs: Training vs. Inference https://medium.com/@Mangusta/llms-training-vs-inference-97b02337cabb | |||
| 20:37 | The SALT : Revolutionizing Large Language Model (LLM) Training with Small Language Models (SLMs) https://medium.com/@hrithikraisaxena97/the-salt-revolutionizing-large-language-model-llm-training-with-small-language-models-slms-5fd1c6c4cb86 | |||
| 20:06 | Artificial Atman (Soul) is All you need! https://medium.com/@vellalamanohar2k/artificial-atman-soul-is-all-you-need-caee23ee6fa6 | |||
| 19:40 | LLMO School Part 5: Leveraging User Intent andSearch Intent for AI Optimization https://medium.com/@johnnydiggz/llmo-school-part-5-leveraging-user-intent-andsearch-intent-for-ai-optimization-6e106b5d235e | |||
| 19:24 | OpenAI’s New Realtime API: Transforming Voice Experiences in Apps https://medium.com/@abdelkarimbsalah/openais-new-realtime-api-transforming-voice-experiences-in-apps-513ec199a2b8 | |||
| 19:24 | DeepSeek v2.5 – open-source LLM comparable to GPT-4, but 95% less expensive https://www.deepseek.com/ | |||
| 19:12 | U.S. military makes first confirmed OpenAI purchase for war-fighting forces https://theintercept.com/2024/10/25/africom-microsoft-openai-military/ | |||
| 18:59 | QuizGenie https://medium.com/@sudarshanasrao/quizgenie-e3f375287f7e | |||
| 18:37 | MultiTok: Making LLM Training Faster, Cheaper and Smarter https://ai.gopubby.com/multitok-making-llm-training-faster-cheaper-and-smarter-8cbf5119d5b5 | |||
| 18:11 | Running Large Language Models Privately: A Comparison of Frameworks, Models and Costs https://medium.com/@robert.corwin/running-large-language-models-privately-a-comparison-of-frameworks-models-and-costs-ac33cfe3a462 | |||
| 18:01 | Stream of Search: Teaching Language Models the Language of Search https://www.llmwatch.com/p/stream-of-search-teaching-language | |||
| 17:47 | Model Merging in Large Language Models: A Guide to Implementation and Use Cases https://iamshobhitagarwal.medium.com/model-merging-in-large-language-models-a-guide-to-implementation-and-use-cases-22cb4c0ebe28 | |||
| 17:44 | Research Topics in Pattern Formation part5(Artificial Intelligence X Machine Learning ) https://medium.com/@thekingventer99/research-topics-in-pattern-formation-part5-artificial-intelligence-x-machine-learning-b9f14244b342 | |||
| 17:36 | Show HN: LLGTRT: TensorRT-LLM+Rust server w/ OpenAI-compat and Structured Output https://github.com/guidance-ai/llgtrt | |||
| 17:29 | QLORA — Fine-tuning of Falcon 7B for Medical Chatbot https://blog.gopenai.com/qlora-fine-tuning-of-falcon-7b-for-medical-chatbot-b3bdc75ffcd2 | |||
| 17:01 | LLM Frameworks — LangChain, LangGraph, and LangFlow: Building with Large Language Models Made Easy https://michal-artur-marciniak.medium.com/llm-frameworks-langchain-langgraph-and-langflow-building-with-large-language-models-made-easy-4644fe2317c9 | |||
| 16:34 | Bridging the Language Gap: Launching the First Hindi Multimodal Language Model Stack https://medium.com/ai-insights-cobet/bridging-the-language-gap-launching-the-first-hindi-multimodal-language-model-stack-37850c4ac31a | |||
| 16:29 | The “200b Parameter Cruncher Macbook Pro” Exploring the M4 Max LLM Performance https://seanvosler.medium.com/the-200b-parameter-cruncher-macbook-pro-exploring-the-m4-max-llm-performance-8fd571a94783 | |||
| 16:26 | A Practical Guide to Implementing Claude Projects with Company Docs https://gcmori.medium.com/a-practical-guide-to-implementing-claude-projects-with-company-docs-1037197eb923 | |||
| 16:06 | RAG — Three Python libraries for Pipeline-based PDF parsing https://medium.com/@AIBites/rag-three-python-libraries-for-pipeline-based-pdf-parsing-cee894eb2967 | |||
| 16:06 | RAG — Three Python libraries for Pipeline-based PDF parsing https://levelup.gitconnected.com/rag-three-python-libraries-for-pipeline-based-pdf-parsing-cee894eb2967 | |||
| 16:01 | Smaller Models, Bigger Impact: Why AI Service Providers Should Embrace Niche Models https://medium.com/@shubham_3306/smaller-models-bigger-impact-why-ai-service-providers-should-embrace-niche-models-97321298ed05 | |||
| 15:45 | Quick and Simple Text Classification with OpenAI’s API https://code.likeagirl.io/quick-and-simple-text-classification-with-openais-api-73d27b5ae514 | |||
| 15:44 | Compressing LLMs with AWQ: Activation-Aware Quantization Explained https://medium.com/@mvpraveenvijayakumar/compressing-llms-with-awq-activation-aware-quantization-explained-55a4b5b4f738 | |||
| 15:24 | Temperature scaling and top-k sampling https://cafecompequi.medium.com/temperature-scaling-and-top-k-sampling-5a42db922842 | |||
| 15:16 | Interesting insights/excerpts from “How AI is Rewriting the SaaS Playbook” https://medium.com/@prashanthrai/interesting-insights-excerpts-from-how-ai-is-rewriting-the-saas-playbook-2e28ab4c6f9a | |||
| 14:55 | Mismatches between Pre-training and Fine-tuning Stages during Large Language Models’ Construction https://medium.com/@citronxu/mismatches-between-pre-training-and-fine-tuning-stages-during-large-language-models-construction-8674ee380868 | |||
| 14:25 | Creating a LLM-as-a-Judge That Drives Business Results https://hamel.dev/blog/posts/llm-judge/ | |||
| 14:20 | Independent Study Week 9 https://medium.com/@lukehenriquez/independent-study-week-9-2fae0faf0423 | |||
| 14:02 | [Digital MATSUMOTO] “Is this the correct understanding of AI?” 08: Prompt bias that affects context https://medium.com/@digitalmatsumoto/digital-matsumoto-is-this-the-correct-understanding-of-ai-08-prompt-bias-that-affects-context-5973429b368f | |||
| 14:01 | Demystifying AI Decisions: Bridging Machine Learning and Knowledge Graphs for Explainable Credit… https://medium.com/@luca.bianchi0110/demystifying-ai-decisions-bridging-machine-learning-and-knowledge-graphs-for-explainable-credit-2605a32931fa | |||
| 13:43 | OPEN-RAG: Enhancing Complex Reasoning in Retrieval-Augmented Generation with Open-Source Sparse… https://blog.gopenai.com/open-rag-enhancing-complex-reasoning-in-retrieval-augmented-generation-with-open-source-sparse-e2190c0b62d1 | |||
| 13:42 | Unlocking the Black Box: TokenSHAP — Peek Inside LLMs https://medium.com/@ronigoldsmid/unlocking-the-black-box-tokenshap-peek-inside-llms-0515c570917b | |||
| 13:25 | Mastering Sentiment Analysis Using Python https://medium.com/@palestine098888/mastering-sentiment-analysis-using-python-6236dd0e6a9a | |||
| 12:52 | Evaluating OpenAI Whisper's Hallucinations on Different Silences https://www.sabrina.dev/p/evaluating-openai-whisper-s-hallucinations-on-different-silences | |||
| 12:29 | Decoding Tokenization Strategies for Large Language Models (LLMs) https://medium.com/@sahin.samia/decoding-tokenization-strategies-for-large-language-models-llms-ffc3fa51aff6 | |||
| 12:16 | Language Learning in the age of LLMs https://medium.com/@mendesh/language-learning-in-the-age-of-llms-d0db351272da | |||
| 12:01 | Computer Use and AI Agents: A New Paradigm for Screen Interaction https://towardsdatascience.com/computer-use-and-ai-agents-a-new-paradigm-for-screen-interaction-b2dcbea0df5b | |||
| 11:50 | Beyond Vanilla RAG: Mastering Advanced Techniques for Pre-Retrieval, Retrieval, and Post-Retrieval… https://medium.com/@asimadnan/beyond-vanilla-rag-mastering-advanced-techniques-for-pre-retrieval-retrieval-and-post-retrieval-5ac2a12beff0 | |||
| 11:41 | TAI #123; Strong Upgrade to Anthropic’s Sonnet and Haiku 3.5, but Where’s Opus? https://pub.towardsai.net/tai-123-strong-upgrade-to-anthropics-sonnet-and-haiku-3-5-but-where-s-opus-3809a9cf7091 | |||
| 11:22 | Understanding Word Vector Embeddings in NLP https://ai.gopubby.com/understanding-word-vector-embeddings-in-nlp-44cf2ace666d | |||
| 11:18 | Beyond Basic Prompts: Exploring the Nuances of Prompt Engineering in Artificial Intelligence https://medium.com/@aminajavaid30/beyond-basic-prompts-exploring-the-nuances-of-prompt-engineering-in-artificial-intelligence-0be2adfcb9b5 | |||
| 11:07 | AI Code Review for Agile Teams: Speed and Quality https://medium.com/@API4AI/ai-code-review-for-agile-teams-speed-and-quality-50881e1f3a3e | |||
| 10:28 | Why RAG is the Secret Weapon Every NLP Developer Needs to Know https://medium.com/@softwarechasers/why-rag-is-the-secret-weapon-every-nlp-developer-needs-to-know-f2289b0e731e | |||
| 10:25 | Very big text models https://medium.com/@tranthetruyen/very-big-text-models-915435ad8f0d | |||
| 10:20 | Step-by-Step Guide to Sentiment Analysis with Hugging Face in Python https://medium.com/@vikashsinghy2k/step-by-step-guide-to-sentiment-analysis-with-hugging-face-in-python-dce1afb9dc25 | |||
| 09:31 | Accelerating Your Data Platform Migration with Databricks’ Project Legion https://medium.com/@robert.whiffin_97866/accelerating-your-data-platform-migration-with-databricks-project-legion-85fe00adc0b0 | |||
| 09:23 | 5 Ways to Optimize RAG with AutoRAG and 6 Common Benchmarks for LLMs https://medium.com/@pamperherself/5-ways-to-optimize-rag-with-autorag-and-6-common-benchmarks-for-llms-d76d3bd5e288 | |||
| 09:11 | Revolutionizing Software Engineering with LLMs https://medium.com/@centizennationwide/revolutionizing-software-engineering-with-llms-29c26ff36989 | |||
| 08:52 | Langtail 1.0 – Spreadsheet-like interface for testing LLM apps https://langtail.com/blog/introducing-langtail-1-the-best-way-to-test-your-ai-apps | |||
| 08:45 | Top 15 LLM Development Trends to Explore in 2025 https://medium.com/coinmonks/top-15-llm-development-trends-to-explore-in-2025-19a1db880c40 | |||
| 08:05 | Mastering Language Representation: Techniques, Embeddings, and the Power of Word2Vec, BERT, and GPT https://medium.com/@patwariraghottam/mastering-language-representation-techniques-embeddings-and-the-power-of-word2vec-bert-and-gpt-921e3f605c65 | |||
| 07:59 | OpenAI reportedly is making its first AI chip with TSMC and Broadcom https://qz.com/openai-first-ai-chip-tsmc-broadcom-amd-nvidia-chatgpt-1851684495 | |||
| 07:43 | Revolutionizing Robotics: MIT’s Game-Changing Heterogeneous Pretrained Transformers (HPT) https://medium.com/@kaviyadharishini21/revolutionizing-robotics-mits-game-changing-heterogeneous-pretrained-transformers-hpt-eea1ed942795 | |||
| 07:20 | Stable Diffusion 3.5, la nouvelle référence pour la génération d’images ? https://guillaume-besson.medium.com/stable-diffusion-3-5-la-nouvelle-r%C3%A9f%C3%A9rence-pour-la-g%C3%A9n%C3%A9ration-dimages-29a0ef52629b | |||
| 07:01 | Friend or Foe?: How AI is Transforming Digital Content Creation https://jmorito.medium.com/friend-or-foe-how-ai-is-transforming-digital-content-creation-ae3be846773f | |||
| 06:43 | How LLMs Revolutionize Coding Efficiency https://aditya-sunjava.medium.com/how-llms-revolutionize-coding-efficiency-a7b99d32a3aa | |||
| 06:38 | Top 20 LLM Development Companies in India https://medium.com/security-token-offering/top-20-llm-development-companies-in-india-87881dd4a5fd | |||
| 06:18 | Generating contexts from PDF https://medium.com/@umasankar17l152/generating-contexts-from-pdf-087b01e518ea | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110