LLM News and Articles
Sunday, 2024-10-13 | ||||
18:12 | Entropix - New insights on entropy-based language model reasoning https://medium.com/@michael_79773/entropix-new-insights-on-entropy-based-language-model-reasoning-fd06f2f5ce89 | |||
17:36 | The Evolution of Deep Reinforcement Learning: Past, Present, and Future https://medium.com/@virendrak.isme09/the-evolution-of-deep-reinforcement-learning-past-present-and-future-605d0d43527f | |||
16:48 | How AI is Transforming the Banking and Financial Sector: Recent Developments and Future Directions https://medium.com/@anup7970hm/how-ai-is-transforming-the-banking-and-financial-sector-recent-developments-and-future-directions-880733fd6bde | |||
16:42 | Attention mechanism in small language models https://medium.com/@gopi.subramanian/attention-mechanism-in-small-language-models-cb462ac1d991 | |||
16:37 | Generative AI On Android — Gemini Nano | Part I https://medium.com/@omeraksu/generative-ai-on-android-gemini-nano-part-i-aca3f53bc936 | |||
16:20 | Build a simple RAG-based LLM Application using llama 3.2 for production: https://medium.com/@hasanshujaat4/build-a-simple-rag-based-llm-application-using-llama-3-2-for-production-ee4c5bbaf34d | |||
15:43 | Wow, AI Just Gave Learning a Serious Makeover! https://staceyrivers13.medium.com/wow-ai-just-gave-learning-a-serious-makeover-2ec0491c7371 | |||
15:38 | Shuhain https://medium.com/@shuhain/shuhain-5364425ae973 | |||
15:36 | How to Run Your Own Local LLM: Updated for 2024 — Version 2 https://medium.com/technology-hits/how-to-run-your-own-local-llm-updated-for-2024-version-2-619f00dd5b6a | |||
15:35 | Show HN: Smell – A framework for aligning LLM evaluators to human feedback https://www.quotientai.co/post/subject-matter-expert-language-liaison-smell-a-framework-for-aligning-llm-evaluators-to-human-feedback | |||
15:28 | ChatGPT Can’t Think! — New SHOCKING Discovery https://ai.plainenglish.io/chatgpt-cant-think-new-shocking-discovery-46b62e664fa3 | |||
15:24 | Accelerating Hugging Face Pre-trained Models on Apple Silicon Using MLX-LM and MPS https://ai.gopubby.com/accelerating-hugging-face-pre-trained-models-on-apple-silicon-using-mlx-lm-and-mps-eb7465e4f502 | |||
15:04 | Day 5 of — 7 Days of agent framework anatomy from first principles https://medium.com/@mrsirsh/day-5-of-7-days-of-agent-framework-anatomy-from-first-principles-7d79eee48064 | |||
14:50 | BIRBAL series: Chapter 1: Coding Custom LLMs specific to a domain or task. https://ravi-manjunatha.medium.com/birbal-series-chapter-1-coding-custom-llms-specific-to-a-domain-or-task-d6efb4647c27 | |||
14:40 | Code Generation with ChatGPT o1-preview as a Story of Human-AI Collaboration https://ai.gopubby.com/code-generation-with-chatgpt-o1-preview-as-a-story-of-human-ai-collaboration-c80ecd9737ec | |||
14:21 | AI-Powered Problem Generation Technology: Collegenie.AI’s Approach https://medium.com/@kyle_99701/ai-powered-problem-generation-technology-collegenie-ais-approach-aa71bb143b8a | |||
12:40 | Problems and Challenges I faced while working with LLMs https://medium.com/@anilcogalan/problems-and-challenges-i-faced-while-working-with-llms-d617bbb22c37 | |||
11:08 | Apple researchers find Large Language Models lack robust mathematical reasoning abilities https://medium.com/@rajat01kapoor/apple-researchers-find-large-language-models-lack-robust-mathematical-reasoning-abilities-9a24cb695b53 | |||
11:03 | AI Hallucination: A Boon in Disguise? https://medium.com/@nithin.sreeram2002/ai-hallucination-a-boon-in-disguise-8dcaccffa200 | |||
10:57 | Making life easier in the Command Line: AI assistance. https://drew2a.medium.com/making-life-easier-in-the-command-line-ai-assistance-285ee8416adf | |||
10:37 | Exploring LLMs: From Transformer Architecture to Task Alignment https://medium.com/@NouhaBHY/exploring-llms-from-transformer-architecture-to-task-alignment-4b9ecb1474f8 | |||
10:23 | How I Built an AI-Powered Chess Teacher in Minutes: The Future of AI-Assisted Development https://chrismiaskowski.medium.com/how-i-built-an-ai-powered-chess-teacher-in-minutes-the-future-of-ai-assisted-development-3d2afc235aa4 | |||
09:12 | How to Build a Local Conversational AI Web Step-by-Step with OpenAI and Chainlit https://blog.gopenai.com/how-to-build-a-local-conversational-ai-web-step-by-step-with-openai-and-chainlit-80508d2b3f6d | |||
09:11 | Boosting My Development Workflow with Generative AI with a simple Script https://medium.com/@tl_99311/boosting-my-development-workflow-with-generative-ai-with-a-simple-script-c7f3d5ac127c | |||
08:57 | Pipeline cơ bản cho bài toán Text Clustering trong BERTopi https://medium.com/@nguyenlecattuong93/pipeline-c%C6%A1-b%E1%BA%A3n-cho-b%C3%A0i-to%C3%A1n-text-clustering-trong-bertopi-0786b5560945 | |||
08:40 | Understanding different RAG Techniques https://medium.com/the-hack-weekly-ai-tech-community/understanding-different-rag-techniques-0186ea5b9a13 | |||
08:26 | Quantum Computing and Multi-Agent Systems: Unlocking the Future of Intelligent Orchestration https://thomasjmartin.medium.com/quantum-computing-and-multi-agent-systems-unlocking-the-future-of-intelligent-orchestration-3f28da830e06 | |||
08:11 | Unmasking the Mathematical Minds of AI: Are LLMs Really Reasoning or Just Imitating? https://medium.com/@martin.treiber/unmasking-the-mathematical-minds-of-ai-are-llms-really-reasoning-or-just-imitating-9eba62529e24 | |||
07:49 | Optimizing Chunking Strategies for Efficient Knowledge Retrieval in RAG Architectures https://n-ahamed36.medium.com/optimizing-chunking-strategies-for-efficient-knowledge-retrieval-in-rag-architectures-92cc2cfe9481 | |||
07:49 | Optimizing Chunking Strategies for Efficient Knowledge Retrieval in RAG Architectures https://blog.devgenius.io/optimizing-chunking-strategies-for-efficient-knowledge-retrieval-in-rag-architectures-92cc2cfe9481 | |||
07:39 | Automating Customer Support with LLaMA: Building a Real-World AI-Powered Ticket Manager https://japangor.medium.com/automating-customer-support-with-llama-building-a-real-world-ai-powered-ticket-manager-5a161a18d854 | |||
07:20 | OpenAI Releases Swarm : What is it? https://thomasjmartin.medium.com/openai-releases-swarm-what-is-it-b61ecb88d67e | |||
07:03 | Today My DS Friend Explained how the Transformer works in LLM https://iorilan.medium.com/today-my-ds-friend-explained-how-the-transformer-works-in-llm-3c20746c6589 | |||
06:46 | Understanding the Attention Mechanism in Language Models https://kosett1356.medium.com/understanding-the-attention-mechanism-in-language-models-270b44adf52e | |||
06:36 | Beginner’s Guide to Building an Advanced Sentiment Analysis Dashboard with Streamlit and Ollama https://pub.towardsai.net/beginners-guide-to-building-an-advanced-sentiment-analysis-dashboard-with-streamlit-and-ollama-ba09023a91fa | |||
06:05 | Comparing Graph DB for RAG usecases https://saurabhk30.medium.com/comparing-graph-db-for-rag-usecases-f34fdb3450fd | |||
05:35 | A Comprehensive Overview of GPT o1 Preview and GPT o1 Mini https://medium.com/wetheitguys/a-comprehensive-overview-of-gpt-o1-preview-and-gpt-o1-mini-5108745c2555 | |||
05:07 | Introducing AgentCraft: Build Your Own AI Agent with Ease https://medium.com/gjam/introducing-agentcraft-build-your-own-ai-agent-with-ease-9d7c76317d83 | |||
04:08 | Unpacking Chat Models with LangChain https://medium.com/donato-story/unpacking-chat-models-with-langchain-f99a17082655 | |||
03:58 | Why Your Cat Is Smarter Than Today’s Most Advanced AI’s: The Roadblock to AGI https://medium.com/@teendifferent/why-your-cat-is-smarter-than-todays-most-advanced-ais-the-roadblock-to-agi-be284bf4a44f | |||
03:48 | AGENTBANK: 50000+ Interaction Trajectories for creating Generalized LLM Agents via Fine-Tuning https://medium.com/@techsachin/agentbank-50000-interaction-trajectories-for-creating-generalized-llm-agents-via-fine-tuning-c606c6b6c38d | |||
01:56 | Adding Chat History into Langchain CSV Agent https://ai.gopubby.com/adding-chat-history-into-langchain-csv-agent-1324ce03fd72 | |||
01:47 | Apple is wrong: LLM has reasoning ability. https://medium.com/@sharakusatoh/apple-is-wrong-llm-has-reasoning-ability-8feb3db0af8e | |||
01:26 | What is Dialog Engineering? https://medium.com/@fabioc/what-is-dialog-engineering-6ba30a8e36ad | |||
00:12 | 6 Human Superpowers AI Lacks https://medium.com/@magicwants/6-human-superpowers-ai-lacks-419a7a978626 | |||
Saturday, 2024-10-12 | ||||
23:50 | Apple study proves LLM-based AI models are flawed because they cannot reason https://appleinsider.com/articles/24/10/12/apples-study-proves-that-llm-based-ai-models-are-flawed-because-they-cannot-reason | |||
23:44 | Levenshtein Distance Algorithm: Why every Data Analyst and Data Engineer should know it ? https://medium.com/@rahulmax2586/levenshtein-distance-algorithm-why-every-data-analyst-and-data-engineer-should-know-it-88eadb6197ab | |||
23:35 | How to Use ARIA Multimodal: A Practical Guide to Multimodal AI Capabilities https://ai.gopubby.com/how-to-use-aria-multimodal-a-practical-guide-to-multimodal-ai-capabilities-788aeac83433 | |||
23:21 | Behavior Cloning with RLBench https://divyanshu-raj.medium.com/behavior-cloning-with-rlbench-b3e59950a9b8 | |||
22:13 | My ChatGPT prompts for productivity https://medium.com/@moises.trejo0/my-chatgpt-prompts-for-productivity-1704bee74cc2 | |||
21:51 | Understanding the Modern LLM — Part 3: Using PyTorch Built-In Function to Build an Autoregressive… https://medium.com/@ikim1994914/understanding-the-modern-llm-part-3-using-pytorch-built-in-function-to-build-an-autoregressive-3feeb14496e9 | |||
21:25 | Let’s Talk About AI and SEO Again https://medium.com/@ferreradaniel/lets-talk-about-ai-and-seo-again-c503d5f71b99 | |||
20:32 | Ranking in AI Search-Practical Guide https://medium.com/@MasterDai/ranking-in-ai-search-practical-guide-510f4be4ddba | |||
20:22 | Mastering Retrieval-Augmented Generation (RAG): A Comprehensive Guide for AI Developers https://medium.com/@phaneendraganji3/mastering-retrieval-augmented-generation-rag-a-comprehensive-guide-for-ai-developers-662916774ef3 | |||
20:08 | Supreme Court Style and How LLMs Can Help Shape Your Writing and Improve Clarity https://medium.com/@ingvargrijs/supreme-court-style-and-how-llms-can-help-shape-your-writing-and-improve-clarity-e8600e83649f | |||
20:08 | Supreme Court Style and How LLMs Can Help Shape Your Writing and Improve Clarity https://medium.com/pluribus-veritas-scribendi-synveritas/supreme-court-style-and-how-llms-can-help-shape-your-writing-and-improve-clarity-e8600e83649f | |||
20:03 | Email Generation with Meta Llama, HuggingFace, and LangChain for Personalized Customer Updates https://medium.com/@mengzhang_63241/email-generation-with-meta-llama-huggingface-and-langchain-for-personalized-customer-updates-0e25f68ebd75 | |||
19:26 | Anthropic’s Approach to Reducing AI Bias & Fairness https://medium.com/@tomskiecke/anthropics-approach-to-reducing-ai-bias-fairness-431bbe236a6c | |||
19:02 | Astute RAG: Google’s Novel Approach to Overcome Imperfect Retrieval in LLMs https://medium.com/@zamalbabar/astute-rag-googles-novel-approach-to-overcome-imperfect-retrieval-in-llms-0f754a0f3f6f | |||
18:55 | Prompt Engineering — Easiest getting started guide to code prompts via LangChain. https://nipundavid.medium.com/prompt-engineering-easiest-getting-started-guide-to-code-prompts-via-langchain-9522ccc0c68c | |||
18:44 | How well do large language models (LLMs) actually handle multi-step reasoning? https://medium.com/about-ai/how-well-do-large-language-models-llms-actually-handle-multi-step-reasoning-83ce37f7fc32 | |||
18:21 | OpenAI Swarm on Llama3 // Multi-agent framework https://sbagency.medium.com/openai-swarm-on-llama3-multi-agent-framework-aa8750cfdd94 | |||
18:21 | A Quick Summary Of Several Limitations In The Current Evaluations Of Llms’ Mathematical Reasoning… https://murat-durmus.medium.com/a-quick-summary-of-several-limitations-in-the-current-evaluations-of-llms-mathematical-reasoning-52b2eb357043 | |||
18:15 | Turbocharge Your GenAI: Performance Optimization Hacks https://ayushkhamrui.medium.com/turbocharge-your-genai-performance-optimization-hacks-e991d03814c6 | |||
18:13 | An AI-powered invention to achieve technical supremacy https://capjmk.medium.com/an-ai-powered-invention-to-achieve-technical-supremacy-39d42d14c761 | |||
18:11 | Migrating Open WebUI SQLite Database to Postgresql https://ciodave.medium.com/migrating-open-webui-sqlite-database-to-postgresql-8efe7b2e4156 | |||
18:01 | Instruction Fine-Tuning LLM using SFT for Financial Sentiment: A Step-by-Step Guide https://pub.towardsai.net/instruction-fine-tuning-llm-using-sft-for-financial-sentiment-a-step-by-step-guide-f93c4aa0153a | |||
17:37 | Controlling Large Language Model Outputs by Providing Examples https://medium.com/@bragadeeshs/controlling-large-language-model-outputs-by-providing-examples-2995dcfb3331 | |||
17:31 | How to Build Your Own AI Fitness Coach Using Open-Source LLMs and Gradio: https://pub.towardsai.net/how-to-build-your-own-ai-fitness-coach-using-open-source-llms-and-gradio-3151e429692f | |||
17:17 | How do Large Language Models(ChatGPT, google Bard, etc.) read? https://medium.com/@fakeavangchhia/how-do-large-language-models-chatgpt-google-bard-etc-read-7669a6cfff03 | |||
16:51 | OpenAI confirms threat actors use ChatGPT to write malware https://www.bleepingcomputer.com/news/security/openai-confirms-threat-actors-use-chatgpt-to-write-malware/ | |||
16:36 | Beyond Autocomplete: Guiding LLMs to Deeper Reasoning https://ai.plainenglish.io/beyond-autocomplete-guiding-llms-to-deeper-reasoning-c9df39c6c5a8 | |||
16:36 | Let's implement Differential Transformer Paper. https://medium.com/@AykutCayir34/lets-implement-differential-transformer-paper-0e4499659604 | |||
16:35 | Will AI Agents replace humans? https://clouddon.ai/will-ai-agents-replace-humans-in-jobs-0559f8257a9e | |||
16:21 | Exploring OpenAI’s Swarm: An experimental framework for multi-agent systems https://medium.com/@michael_79773/exploring-openais-swarm-an-experimental-framework-for-multi-agent-systems-5ba09964ca18 | |||
15:56 | ✨ Unlocking AI Magic: 10 Ways to Supercharge Your Node.js Apps with OpenAI https://medium.com/@ananthu0000/unlocking-ai-magic-10-ways-to-supercharge-your-node-js-apps-with-openai-6ce77516e380 | |||
15:18 | 01. Introduction to Generative AI: What’s All the Buzz About? https://prasad97.medium.com/01-introduction-to-generative-ai-whats-all-the-buzz-about-c3186eccd1cb | |||
15:11 | LLMs and the Reliability Riddle: Navigating the Hallucination Highway https://medium.com/@haveainicedayy/llms-and-the-reliability-riddle-navigating-the-hallucination-highway-4b94b2f47169 | |||
15:01 | Building Your Own Generative Search Engine for Local Files Using Open-Source Models https://pub.towardsai.net/building-your-own-generative-search-engine-for-local-files-using-open-source-models-b09af871751c | |||
15:01 | LLM vs LLM: Codenames Tournament https://towardsdatascience.com/llm-vs-llm-codenames-tournament-f8170dd1c8fb | |||
14:46 | RAG: Supercharging Large Language Models with Retrieval-Augmented Generation https://medium.com/@swapnilshekade/rag-supercharging-large-language-models-with-retrieval-augmented-generation-8a9f4e586ece | |||
14:26 | Introduction to Generative AI https://medium.com/@srikarkandagatla/introduction-to-generative-ai-11bed6340ea0 | |||
14:09 | Day 4 of — 7 Days of agent framework anatomy from first principles https://medium.com/@mrsirsh/day-4-of-7-days-of-agent-framework-anatomy-from-first-principles-a9de23e3d76a | |||
13:55 | Dissecting AutoGen: AI Agentic Design Patterns example https://medium.com/codex/dissecting-autogen-ai-agentic-design-patterns-example-8706c8b4efb4 | |||
13:44 | Why LLM Patterns Are the Key to Enterprise Success — And Why Ignoring Them is a Mistake https://pub.towardsai.net/why-llm-patterns-are-the-key-to-enterprise-success-and-why-ignoring-them-is-a-mistake-18efdfb8c31e | |||
13:11 | Why we have to use LLM locally ? https://muhammad-husnain-ali.medium.com/why-we-have-to-use-llm-locally-2c1bb9351565 | |||
12:41 | The AI streamer experiment https://medium.com/@adrien_morvan/the-ai-streamer-experiment-6de678a0ed6d | |||
12:29 | Anthropic's Claude vulnerable to 'emotional manipulation' https://www.theregister.com/2024/10/12/anthropics_claude_vulnerable_to_emotional/ | |||
11:45 | Revolutionising NLP: The Power of Transformers, PEFT Fine-tuning, and LoRA Techniques — Part 1 https://medium.com/@mustangs007/revolutionising-nlp-the-power-of-transformers-peft-fine-tuning-and-lora-techniques-part-1-eb7286975983 | |||
11:04 | Unveiling the Fragility of Large Language Models in Mathematical Reasoning: The Case of… https://timpryme.medium.com/unveiling-the-fragility-of-large-language-models-in-mathematical-reasoning-the-case-of-0f9a562bff8f | |||
10:13 | LLM-Chatbots — An introduction to the new world of bots https://sophiehundertmark.medium.com/llm-chatbots-an-introduction-to-the-new-world-of-bots-485db17da7b2 | |||
10:00 | Maximizing LLM Performance: A Guide to Advanced Prompt Engineering https://medium.com/@nrmnbabalik/maximizing-llm-performance-a-guide-to-advanced-prompt-engineering-92a593293419 | |||
09:13 | Why Prompt Engineering Is the New Copywriting (And How to Master It) https://medium.com/@AIMom/why-prompt-engineering-is-the-new-copywriting-and-how-to-master-it-912d7fdd6391 | |||
09:10 | “Unleashing the Power of Mistral 7B”: An Overview and Efficient Fine-Tuning for Medical QA https://medium.com/@anicomanesh/unleashing-the-power-of-mistral-7b-efficient-fine-tuning-for-medical-qa-fb3afaaa36e4 | |||
09:07 | Gradio for Simple AI Web Apps https://medium.com/@niall.mcnulty/gradio-for-simple-ai-web-apps-108f1ee9ace5 | |||
08:58 | OpenAI Canvas and DevDay: Advancing AI Collaboration with Voice Realtime API, Model Distillation… https://medium.com/@researchgraph/openai-canvas-and-devday-advancing-ai-collaboration-with-voice-realtime-api-model-distillation-a140e4d65486 | |||
08:58 | Prompt Power Week 0:A Simple Guide to Getting the Most Out of AI https://medium.com/@ajayvardhan2001/prompt-power-week-0-a-simple-guide-to-getting-the-most-out-of-ai-3c2b2a9326dd | |||
07:21 | Mastering Generative AI in 2025: A Comprehensive Guide https://ai.plainenglish.io/mastering-generative-ai-in-2025-a-comprehensive-guide-20e109998188 | |||
07:20 | Do You Know ChatGPT’s Water Consumption for Every Question You Ask? https://medium.com/@vignesh_19500/do-you-know-chatgpts-water-consumption-for-every-question-you-ask-75d6409abb28 | |||
06:48 | [Machine Learning Paper Reading]VILA: OnPre-training for Visual Language Models https://henry870603.medium.com/machine-learning-paper-reading-vila-onpre-training-for-visual-language-models-3f3e313b10b8 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803