LLM News and Articles
Sunday, 2024-08-18 | ||||
04:20 | RLHF vs. DPO: Choosing the Method for LLMs Alignment Tuning https://medium.com/@baicenxiao/rlhf-vs-dpo-choosing-the-method-for-llm-alignment-tuning-66f45ef3d4b5 | |||
03:00 | Massive Energy for Massive GPU Empowering AI https://geozhang.medium.com/massive-energy-for-massive-gpu-empowering-ai-dff59ae1da44 | |||
02:43 | Maximizing LLM Accuracy for Production: A Practical Guide https://angelina-yang.medium.com/maximizing-llm-accuracy-for-production-a-practical-guide-2cb2b886e91c | |||
02:41 | Let’s debate AGI: Can a Turing machine simulate the human brain? https://medium.com/@sharvanath/lets-debate-agi-can-a-turing-machine-simulate-the-human-brain-086ea643c443 | |||
01:31 | A Beginner’s Guide to LLMs — What’s a Large-Language Model and How Does it Work? https://medium.com/@be_likedeep/a-beginners-guide-to-llms-what-s-a-large-language-model-and-how-does-it-work-d768638132c3 | |||
00:54 | Qwen2 — Alibaba’s New Powerhouse Multimodal AI https://medium.com/@researchgraph/qwen2-alibabas-new-powerhouse-multimodal-ai-9c3f7cbf4ae8 | |||
Saturday, 2024-08-17 | ||||
23:32 | Educational Material to Knowledge Graph Conversion: A Methodology to Enhance Digital Education https://medium.com/@EleventhHourEnthusiast/educational-material-to-knowledge-graph-conversion-a-methodology-to-enhance-digital-education-7817cd6ea1a5 | |||
23:19 | Cracking the Code of AI Alignment: This AI Paper from the University of Washington and Meta FAIR Unveils Better Alignment with Instruction Back-and-Forth Translation https://www.marktechpost.com/2024/08/17/cracking-the-code-of-ai-alignment-this-ai-paper-from-the-university-of-washington-and-meta-fair-unveils-better-alignment-with-instruction-back-and-forth-translation/ | |||
22:43 | Working Around LLM Drawbacks Can Get You a Lot — Research Review #3 https://medium.com/@mkuthalam/working-around-llm-drawbacks-can-get-you-a-lot-research-review-3-abe9fa1b4289 | |||
21:52 | Understanding Transformers: A Glimpse into the Tech That’s Changing Everything https://medium.com/@joesank10/understanding-transformers-a-glimpse-into-the-tech-thats-changing-everything-908abc875a2c | |||
21:50 | Create Your Own AI Assistants: A Step-by-Step Guide with OpenAI Playground and Assistants API https://medium.com/@ahmetmnirkocaman/openai-assistants-api-161a91400583 | |||
21:29 | GraphRAG: From Local to Global https://medium.com/@shashankvats/graphrag-from-local-to-global-031c8a4156c9 | |||
21:19 | Unlock the Potential of Bittensor ($TAO) with Liquid Restaking Programs https://medium.com/@fenrircrypto/unlock-the-potential-of-bittensor-tao-with-liquid-restaking-programs-8421fff1dd95 | |||
20:39 | What is RAG? (1/3) https://medium.com/@nimeeshsharma/what-is-rag-1-3-6d9a60de6bb2 | |||
20:33 | Build Your Local AI Chatbot with Ollama, Llama 3, and Streamlit: A Beginner Tutorial. https://ai.gopubby.com/build-your-local-ai-chatbot-with-ollama-llama-3-and-streamlit-a-beginner-tutorial-f2225e1d4ca5 | |||
20:08 | Como Gerar FAQs Automatizados com Python, Langchain e a OpenAI API? https://medium.com/@mrpaiva/como-gerar-faqs-automatizados-com-python-langchain-e-a-openai-api-e26c30a921b1 | |||
19:40 | Large Language Models Don’t Think in Ways That Humans Do https://medium.com/@iancheung0202/large-language-models-dont-think-in-ways-that-humans-do-d16dd6d5d5ee | |||
19:21 | Are you better than a language model at predicting the next word? https://joel.tools/smarter/ | |||
19:17 | Claude Sonnet 3.5: Secret Tricks & Tips Revealed https://medium.com/@tomskiecke/claude-sonnet-3-5-secret-tricks-tips-revealed-c9753b74b572 | |||
19:15 | Running LLMs locally using Ollama. Step-by-step guide. https://rameshnavi.medium.com/running-llms-locally-using-ollama-step-by-step-guide-8f55249705d6 | |||
19:08 | RAGEval: A Novel Framework for Domain-Specific Evaluation of Large Language Models in Finance… https://readqvick.medium.com/rageval-a-novel-framework-for-domain-specific-evaluation-of-large-language-models-in-finance-85acc03920dd | |||
19:03 | A New Era of Interaction: OpenAI’s Advanced Voice Mode Transforms Communication with AI https://medium.com/@seekmeai/a-new-era-of-interaction-openais-advanced-voice-mode-transforms-communication-with-ai-1c159929f6ac | |||
19:02 | The History and Evolution of Generative AI: From GAN to GPT https://medium.com/@ibtissam.essadik/the-history-and-evolution-of-generative-ai-from-gan-to-gpt-4-96c1fa69f4e7 | |||
18:45 | AI Agents 101 https://medium.com/@someshpulikanti/ai-agents-101-23d2cee00efd | |||
18:37 | Every Leading Large Language Model Leans Left Politically https://realclearwire.com/articles/2024/08/14/every_leading_large_language_model_leans_left_politically_1051145.html | |||
18:36 | Using Ollama, Llama3.1, and Langchain retriever chain in Python https://medium.com/@natickphys/using-ollama-llama3-1-and-langchain-retriever-chain-f7f9447fb405 | |||
18:24 | Flux-1 vs ImageFX(Imagen 3)— Google’s First AI Product that Doesn’t Suck https://generativeai.pub/flux-1-vs-imagefx-imagen-3-googles-first-ai-product-that-doesn-t-suck-c272fa5d2abc | |||
18:23 | Unveiling RAG: A Powerful Fusion of Retrieval and Generation https://medium.com/@rishabh.vyas2003/unveiling-rag-a-powerful-fusion-of-retrieval-and-generation-4c546644ccc2 | |||
17:30 | AI-Powered Calendar Automation: Simplifying Event Management with Nylas and GPT https://github.com/Brandon-c-tech/AI-Calendar-Automation | |||
16:14 | Why SQL Is Under Attack: The Evolving Threats to LLM Systems https://heegyukim.medium.com/why-sql-is-under-attack-the-evolving-threats-to-llm-systems-969f10e7e690 | |||
15:56 | Llama Agent https://medium.com/@zzyszc/llama-agent-54fa4c6a9dee | |||
15:41 | aiXplain Researchers Develop Innovative Approaches for Arabic Prompt Instruction Following with LLMs https://www.marktechpost.com/2024/08/17/aixplain-researchers-develop-innovative-approaches-for-arabic-prompt-instruction-following-with-llms/ | |||
15:05 | Exploring Hybrid RAG Search https://medium.com/@mansoor711/exploring-hybrid-rag-search-2e0f43e9f994 | |||
14:50 | Ontology-guided Knowledge Graph Construction from Maintenance Short Texts https://medium.com/@EleventhHourEnthusiast/ontology-guided-knowledge-graph-construction-from-maintenance-short-texts-66854cd40187 | |||
14:45 | imaged SDK: Expanding AI Capabilities with Gemma https://medium.com/@adel_32174/imaged-sdk-expanding-ai-capabilities-with-gemma-72092ff020c3 | |||
14:35 | Lost in the Middle: How Language Models Use Long Contexts https://vivekpandit.medium.com/lost-in-the-middle-42ad929f2ac4 | |||
14:28 | The AI Bubble: Is It Popping or Just Inflating More Hot Air? https://medium.com/@jaycruz/the-ai-bubble-is-it-popping-or-just-inflating-more-hot-air-ca3084663878 | |||
14:26 | LangChain Showdown: LLMs VS Chat Models https://medium.com/@ihamzakhan89/langchain-showdown-llms-vs-chat-models-ebf044e6827d | |||
14:22 | Unlocking Enterprise Data Potential with InsightCopilot: Your AI-Powered Data Copilot https://verticalserve.medium.com/unlocking-enterprise-data-potential-with-insightcopilot-your-ai-powered-data-copilot-2da9146cd4ad | |||
14:21 | Data-Centric AI in Action: Boosting Model Performance with Synthetic Data from Large Language… https://medium.com/@rajdeep.jzs/data-centric-ai-in-action-boosting-model-performance-with-synthetic-data-from-large-language-8340b902719f | |||
13:30 | Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters https://medium.com/@EleventhHourEnthusiast/adapting-multilingual-llms-to-low-resource-languages-with-knowledge-graphs-via-adapters-0a8773382349 | |||
13:11 | Comprehensive Guide to Marketing Attribution https://lucia-protocol.medium.com/comprehensive-guide-to-marketing-attribution-775551206f4f | |||
13:05 | How Much GPU Memory is Needed to Serve a Large Language Model (LLM)? https://masteringllm.medium.com/how-much-gpu-memory-is-needed-to-serve-a-large-languagemodel-llm-b1899bb2ab5d | |||
12:55 | New LLM Pre-Training and Post-Training Paradigms: How Modern LLMs Are Trained https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training | |||
12:53 | Developers’ Guide to Unlocking the Power of Open Source LLMs https://medium.com/@paulolatunde/developers-guide-to-unlocking-the-power-of-open-source-llms-da6a51a57422 | |||
12:20 | Top 5 Open-Source Large Language Models Shaping AI Today https://medium.com/@engineer-hard/top-5-open-source-large-language-models-shaping-ai-today-7d3703106f71 | |||
12:18 | StepByStep: Understanding RAG Basics, its patterns and its stages — Introduction https://medium.com/@ignacioperezzv/stepbystep-understanding-rag-basics-its-patterns-and-its-stages-6a173869ae64 | |||
12:11 | Iranian group used ChatGPT to try to influence US election, OpenAI says https://www.theguardian.com/technology/article/2024/aug/16/open-ai-chatgpt-iran | |||
11:39 | The Genesis of an AI Story Bot https://medium.com/@aleksmilanov/the-genesis-of-an-ai-story-bot-2a85e3e27b59 | |||
11:00 | DeepSeek-AI Open-Sources DeepSeek-Prover-V1.5: A Language Model with 7 Billion Parameters that Outperforms all Open-Source Models in Formal Theorem Proving in Lean 4 https://www.marktechpost.com/2024/08/17/deepseek-ai-open-sources-deepseek-prover-v1-5-a-language-model-with-7-billion-parameters-that-outperforms-all-open-source-models-in-formal-theorem-proving-in-lean-4/ | |||
10:33 | Every domain needs a Sqlite, even LLMs https://medium.com/@rashaddism/every-domain-needs-a-sqlite-even-llms-07ef5a5f80cc | |||
10:31 | Retrieval Augmented Generation with Weaviate & Mistral AI https://blog.gopenai.com/retrieval-augmented-generation-with-weaviate-mistral-ai-3cb8b35b8fa0 | |||
10:19 | Building an RAG Application with Vanilla Python: No Langchain, LlamaIndex, etc. (Part 1) https://medium.com/@rezkyws/building-an-rag-application-with-vanilla-python-no-langchain-llamaindex-etc-e60f47ad23d8 | |||
10:04 | Structured Outputs Effectively with GPT-4o Function Calling on Financial Calculations https://itnext.io/structured-outputs-effectively-with-gpt-4o-function-calling-on-financial-calculations-f12d4ae78620 | |||
09:53 | LLM-Enhanced Clipboard on macOS: Streamlining Your Writing Process https://medium.com/@mpuig/llm-enhanced-clipboard-on-macos-streamlining-your-writing-process-52efb2eb56dc | |||
09:49 | Lilygo T-Deck Plus is a handheld with GPS, LoRa, and a BlackBerry keyboard https://liliputing.com/lilygo-t-deck-plus-is-a-70-handheld-with-gps-lora-and-a-blackberry-keyboard/ | |||
09:48 | AI Weekly Buzz: Innovations, Insights, and Industry Trends August 11th — 16th https://medium.com/artificial-synapse-media/ai-weekly-buzz-innovations-insights-and-industry-trends-august-11th-16th-16018e2a31cf | |||
09:44 | Text Generation Using LSTMs and GPT-2 In PyTorch https://medium.com/@MalikSaadAhmed/text-generation-using-lstms-and-gpt-2-in-pytorch-8097c948ccd8 | |||
09:09 | Using a jury of LLMs instead of a single judge to evaluate LLM generations https://medium.com/@getmaximai/using-a-jury-of-llms-instead-of-a-single-judge-to-evaluate-llm-generations-d6eca32721b5 | |||
09:05 | Unlocking Creativity: How LSTM Models Can Craft Compelling Text from Scratch” https://medium.com/@albinlamichhane9/unlocking-creativity-how-lstm-models-can-craft-compelling-text-from-scratch-6b87476e028e | |||
08:49 | NousResearch’s Hermes-3-Llama-3.1–405B: A Frontier-Level Language Model https://towards-agi.medium.com/nousresearchs-hermes-3-llama-3-1-405b-a-frontier-level-language-model-cdbe2cb27a2d | |||
08:40 | Nous Research Open-Sources Hermes 3: A Series of Instruct and Tool Use Model with Strong Reasoning and Creative Abilities https://www.marktechpost.com/2024/08/17/nous-research-open-sources-hermes-3-a-series-of-instruct-and-tool-use-model-with-strong-reasoning-and-creative-abilities/ | |||
08:26 | Effortlessly Integrate Hosted LLMs with LangChain Using a Custom API Wrapper https://medium.com/@vyasharshay.hv/effortlessly-integrate-hosted-llms-with-langchain-using-a-custom-api-wrapper-cb68849b9fb9 | |||
08:23 | Scaling LLM Outputs: The Role of AgentWrite and the LongWriter-6k Dataset https://www.marktechpost.com/2024/08/17/scaling-llm-outputs-the-role-of-agentwrite-and-the-longwriter-6k-dataset/ | |||
08:19 | Why You Should Use Variables in AI Prompts https://medium.com/@andreyverbitsky/why-you-should-use-variables-in-ai-prompts-3576d7bce0bf | |||
06:46 | Keep Calm and Code On: Why LLMs Can’t Replace Programmers completely Yet. https://medium.com/@sahin.samia/keep-calm-and-code-on-why-llms-cant-replace-programmers-completely-yet-1480578126d3 | |||
05:20 | “Delving” into LangGraph https://anukriti-ranjan.medium.com/delving-into-langgraph-3b02f4d05b4c | |||
05:14 | Generative AI vs LLMs, Know the difference. https://medium.com/@advaitss11/generative-ai-vs-llms-know-the-difference-f5a2cb45fcef | |||
04:54 | Travelmate — RAG Chat with MongoDb Atlas Collection https://medium.com/@vinod.krishnan13/travelmate-rag-chat-with-mongodb-atlas-collection-8e7636207921 | |||
03:29 | I-SHEEP: Self-Alignment of LLMs from Scratch via an Iterative Self-Enhancement Paradigm https://medium.com/@techsachin/i-sheep-self-alignment-of-llms-from-scratch-via-an-iterative-self-enhancement-paradigm-a4b95bbeae25 | |||
03:29 | ColPali: The AI That Sees Documents Like You Do https://medium.com/gptalk/colpali-the-ai-that-sees-documents-like-you-do-93ede84c052e | |||
02:43 | Serve an LLM Application as an API Endpoint with FastAPI in Python. https://ai.gopubby.com/serve-an-llm-application-as-an-api-endpoint-with-fastapi-in-python-e8cc763e4cf2 | |||
02:40 | Introducing Kaka.ai: Democratizing AI for Everyone https://medium.com/@hello_50743/introducing-kaka-ai-democratizing-ai-for-everyone-a0359eb4c8ac | |||
02:34 | Answer.AI Releases answerai-colbert-small: A Proof of Concept for Smaller, Faster, Modern ColBERT Models https://www.marktechpost.com/2024/08/16/answer-ai-releases-answerai-colbert-small-a-proof-of-concept-for-smaller-faster-modern-colbert-models/ | |||
02:16 | HRGraph: Leveraging LLMs for HR Data Knowledge Graphs with Information Propagation-based Job… https://medium.com/@EleventhHourEnthusiast/hrgraph-leveraging-llms-for-hr-data-knowledge-graphs-with-information-propagation-based-job-2ab896bbca96 | |||
01:25 | Evaluating LLMs — What’s the right one for the job? https://medium.com/humaxa/evaluating-llms-whats-the-right-one-for-the-job-d43fcbd6cd64 | |||
01:20 | KGAST: From Knowledge Graphs to Annotated Synthetic Texts https://medium.com/@EleventhHourEnthusiast/kgast-from-knowledge-graphs-to-annotated-synthetic-texts-a69875ed733c | |||
01:05 | The Potential of Multitasking with LLM Chatbots and AI Memory https://medium.com/the-ai-archives/the-potential-of-multitasking-with-llm-chatbots-and-ai-memory-27f527ea8d1d | |||
01:04 | Large Language Models (LLMs) vs. Traditional NLP Approaches https://medium.com/large-language-models/large-language-models-llms-vs-traditional-nlp-approaches-556b1e82444d | |||
00:46 | Ollama- Open-Source LLM https://medium.com/@ezeprimo/ollama-open-source-llm-4d019b400854 | |||
00:44 | Why the T in ChatGPT is AI's biggest breakthrough – and greatest risk https://www.newscientist.com/article/2444078-why-the-t-in-chatgpt-is-ais-biggest-breakthrough-and-greatest-risk/ | |||
Friday, 2024-08-16 | ||||
23:49 | From Chaos to Clarity: How I Improved LLM Output Consistency with LangChain https://ravjot03.medium.com/from-chaos-to-clarity-how-i-improved-llm-output-consistency-with-langchain-399ec53613d1 | |||
23:30 | Eric Schmidt says Google is losing out to OpenAI and Anthropic because WFH https://www.businessinsider.com/ex-google-ceo-losing-ai-race-staff-work-from-home-2024-8 | |||
22:27 | Sustainable AI Business Models https://medium.com/@tombeckenham/sustainable-ai-business-models-9aa5baa527b0 | |||
22:10 | Anthropic’s AI Revolution: Claude Models Understand the Base64 Code https://medium.com/@_jeremy_/anthropics-ai-revolution-claude-models-understand-the-base64-code-e0ed72a9f0fb | |||
21:15 | How to Easily Deploy Coze Chatbot on Your Wix Website in Just 10 Minutes https://medium.com/@garyzhen79/how-to-easily-deploy-coze-chatbot-on-your-wix-website-in-just-10-minutes-22e4c6abced1 | |||
21:04 | LangSmith: Supercharge Your LangChain Apps https://medium.com/@hamza-shafique/langsmith-supercharge-your-langchain-apps-4743142232bc | |||
21:00 | LLMs And The Decline Of Open Source https://medium.com/@impure/llms-and-the-decline-of-open-source-24f5cf419dee | |||
20:27 | The Executive’s Guide to Leading with AI Transforming Finance with Advanced Language Models https://medium.com/@j.m.olivera08/the-executives-guide-to-leading-with-ai-transforming-finance-with-advanced-language-models-1ad05e890794 | |||
19:56 | LLM and Bug Finding: Insights from a M Winning Team in the White House's AIxCC https://team-atlanta.github.io/blog/post-atl/ | |||
19:51 | Neural Magic Releases LLM Compressor: A Novel Library to Compress LLMs for Faster Inference with vLLM https://www.marktechpost.com/2024/08/16/neural-magic-releases-llm-compressor-a-novel-library-to-compress-llms-for-faster-inference-with-vllm/ | |||
19:35 | Enhancing Efficiency and Quality in AI Interactions on a Mac https://medium.com/@david03kimo/how-to-quickly-translate-chinese-questions-into-english-on-a-mac-for-asking-ai-06566590e976 | |||
19:24 | From Hype to Superintelligence: Navigating the Future of AI https://medium.com/@edmond.po/from-hype-to-superintelligence-navigating-the-future-of-ai-4452ea9ea8fd | |||
19:09 | Enterprise Standards for Fine-Tunning LLM Models https://medium.com/@kushagramisra10/enterprise-standards-for-fine-tunning-llm-models-d7136b324790 | |||
18:49 | LLM Transformers : Part 2 https://medium.com/@nishi.paul.in/llm-transformers-part-2-8bbec019fe34 | |||
18:36 | Large Language Models (LLMs) — Zero Shot & OnShot Learning https://medium.com/@ytech360/large-language-models-llms-zero-shot-onshot-learning-979ccc0a20c4 | |||
18:26 | Linguagem de Expressão LangChain (LCEL) https://medium.com/@recogna.nlp/linguagem-de-express%C3%A3o-langchain-lcel-510db2664aa2 | |||
18:14 | Can GPT generate random numbers? https://www.ashu1461.com/can-gpt-generate-random-numbers/ | |||
18:00 | 🍎 Apple's Answer to Complex LLM Evaluation https://www.llmwatch.com/p/apples-answer-to-complex-llm-evaluation | |||
17:47 | Grok 2 — How to Use for FREE https://ai.plainenglish.io/grok-2-how-to-use-for-free-f41464ea9c22 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803