LLM News and Articles
Saturday, 2024-08-10 | ||||
19:19 | From Context to Code: A Reflection on Instruction Tuning and Its Application https://medium.com/@miguelangel.kjh/from-context-to-code-a-reflection-on-instruction-tuning-and-its-application-9a3d59463e96 | |||
18:49 | HALVA: A Framework for Minimizing Hallucinations in Multimodal Language Models with Contrastive… https://readqvick.medium.com/halva-a-framework-for-minimizing-hallucinations-in-multimodal-language-models-with-contrastive-d81006baa742 | |||
18:27 | BGE M3 Embedding — BAAI https://medium.com/@aravindhoff19/bge-m3-embedding-baai-6d994b05b5ac | |||
18:18 | How Wikipedia is surviving in the age of ChatGPT https://english.elpais.com/technology/2024-08-10/how-wikipedia-is-surviving-in-the-age-of-chatgpt.html | |||
18:17 | Latest & Under-the-Radar: 11 AI & Tech Tools You Need to Know — #InsTech’s 1st Edition https://medium.com/@wallikhan76/latest-under-the-radar-11-ai-tech-tools-you-need-to-know-instechs-1st-edition-ccd9be34e67a | |||
18:10 | Unlocking the Power of Synthetic Data Generation with LLM https://medium.com/@sibanimlintern.siam/unlocking-the-power-of-synthetic-data-generation-with-llm-470b7f8e3f2e | |||
17:29 | Announcing My New Book: Building an LLMOps Pipeline Using Hugging Face https://devopslearning.medium.com/announcing-my-new-book-building-an-llmops-pipeline-using-hugging-face-eb29049bb364 | |||
17:20 | Conversational Agents with Crew AI https://riteshshergill.medium.com/conversational-agents-with-crew-ai-5b7d72c5b830 | |||
17:01 | The Art of Prompt Engineering https://pub.towardsai.net/the-art-of-prompt-engineering-f277abca629a | |||
16:53 | Don’t Trust Retrieval Augmented Generation Products! https://medium.com/@Lorenzo_Pozzi/dont-trust-retrieval-augmented-generation-products-8e738a7e4b6b | |||
14:29 | SQLPilot — Text2SQL application with RAG https://shobhitb.medium.com/sqlpilot-text2sql-application-with-rag-87a4d72e3438 | |||
14:27 | Show HN: I created a self-typing typewriter (and connected it to an LLM) https://notes.bayesup.date/Projects/The+Self-Typing+Typewriter | |||
14:00 | UX for Agents, Part 3: Spreadsheet, Generative, and Collaborative UI/UX https://blog.langchain.dev/ux-for-agents-part-3/ | |||
13:40 | A Estranheza do Familiar: Jamais Vu e IA https://rdarrudas.medium.com/a-estranheza-do-familiar-jamais-vu-e-ia-d548476c0ec6 | |||
13:34 | Master RAG Architecture (from Zero to Hero) https://medium.com/@wriath18/master-rag-architecture-from-zero-to-hero-d3919440f790 | |||
13:30 | Scalable MatMul-free Language Modeling https://medium.com/@EleventhHourEnthusiast/scalable-matmul-free-language-modeling-cda71720dc33 | |||
13:29 | LangChain : LLM ile çalışma kapısının anahtarı https://medium.com/@eskaya64/langchain-llm-ile-%C3%A7al%C4%B1%C5%9Fma-kap%C4%B1s%C4%B1n%C4%B1n-anahtar%C4%B1-15638a7a1166 | |||
12:58 | PHI 3 128K using Hugging Face in Azure Machine Learning — Run Local https://towardsdev.com/phi-3-128k-using-hugging-face-in-azure-machine-learning-run-local-1480a2b5088c | |||
12:48 | Beyond Bytes: How Large Language Models Reason and Remember https://medium.com/@santhosraj14/beyond-bytes-how-large-language-models-reason-and-remember-a17608cbe1ab | |||
12:28 | Temperature and Top-P Sampling in LLMs https://medium.com/@noufalsamsudin/temperature-and-top-p-sampling-in-llms-453bcd888f13 | |||
12:13 | The Psychology Prompt Model: A Powerful Tool for Analyzing Behavior and Improving Mental Health https://medium.com/@a.sale/the-psychology-prompt-model-a-powerful-tool-for-analyzing-behavior-and-improving-mental-health-e6cf21de865c | |||
12:11 | AI’nt That Easy #8: RAG for Excel Data Using Pandas and Llama Parse https://aint-that-easy.medium.com/aint-that-easy-8-rag-for-spreadsheet-data-using-pandas-and-llama-parse-8475295e913a | |||
11:32 | My First Implementation of A RAG using Graph Database. https://medium.com/@pathakmanish7275/my-first-implementation-of-a-rag-using-graph-database-d4632e8acfbb | |||
11:19 | OLLAMA — Your Local LLM Friend: Installation Tutorial ️ https://gurneet-singh.medium.com/ollama-your-local-llm-friend-installation-tutorial-%EF%B8%8F-23eb135b097d | |||
11:05 | LLM Evaluation Metrics https://girishkurup21.medium.com/concise-summary-of-the-key-points-from-unveiling-llm-evaluation-focused-on-metrics-challenges-and-e6dfacd3a78d | |||
10:29 | The AI Evolution: Generative Intelligence in 2024 https://medium.com/@yskarthik/the-ai-evolution-generative-intelligence-in-2024-df2206d51a12 | |||
10:12 | Think Beyond the Norm: Overcoming Limits with Advanced Language Models for Data Anonymization. https://medium.com/@purnima.msb/think-beyond-the-norm-overcoming-limits-with-advanced-language-models-for-data-anonymization-42333d605ee6 | |||
09:45 | Generative AI vs Predictive AI: What Makes A Difference? https://medium.com/@agarapuramesh/generative-ai-vs-predictive-ai-what-makes-a-difference-6eb4597391e9 | |||
08:57 | Multimodal AI: Transforming Data Interpretation Across Various Formats https://thomaselton-73327.medium.com/multimodal-ai-transforming-data-interpretation-across-various-formats-7030ab2802dc | |||
08:28 | Where we are in the AI revolution? https://medium.com/@willitheowl/where-we-are-in-the-ai-revolution-fe448c4006da | |||
07:28 | Small and Large Language Models: Balancing Precision, Efficiency, and Power in the Evolving Landscape of Natural Language Processing https://www.marktechpost.com/2024/08/10/small-and-large-language-models-balancing-precision-efficiency-and-power-in-the-evolving-landscape-of-natural-language-processing/ | |||
07:14 | DynamoLLM: An Energy-Management Framework for Sustainable Artificial Intelligence Performance and Optimized Energy Efficiency in Large Language Model (LLM) Inference https://www.marktechpost.com/2024/08/10/dynamollm-an-energy-management-framework-for-sustainable-artificial-intelligence-performance-and-optimized-energy-efficiency-in-large-language-model-llm-inference/ | |||
06:38 | Trinity-2-Codestral-22B and Tess-3-Mistral-Large-2-123B Released: Pioneering Open Source Advances in Computational Power and AI Integration https://www.marktechpost.com/2024/08/09/trinity-2-codestral-22b-and-tess-3-mistral-large-2-123b-released-pioneering-open-source-advances-in-computational-power-and-ai-integration/ | |||
06:15 | The Death of SaaS: A New Era in Software Delivery https://medium.com/@rs4528090/the-death-of-saas-a-new-era-in-software-delivery-35564fa25a51 | |||
05:04 | Abacus AI Introduces LiveBench AI: A Super Strong LLM Benchmark that Tests all the LLMs on Reasoning, Math, Coding and more https://www.marktechpost.com/2024/08/09/abacus-ai-introduces-livebench-ai-a-super-strong-llm-benchmark-that-tests-all-the-llms-on-reasoning-math-coding-and-more/ | |||
04:19 | Understanding Reinforcement Learning from Human Feedback (RLHF): Theory and the Mechanism. https://medium.com/@2468086464/understanding-reinforcement-learning-from-human-feedback-rlhf-theory-and-the-mechanism-ef45485a5070 | |||
03:01 | Digitalizando tus Finanzas. De imágenes (o PDFs) a datos estructurados: LLMs https://medium.com/@jddam/digitalizando-tus-finanzas-de-im%C3%A1genes-o-pdfs-a-datos-estructurados-llms-e0460d50b200 | |||
Friday, 2024-08-09 | ||||
23:53 | Getting Started with LLMs: A Beginner’s Handbook https://medium.com/@sidd.ghosh9/getting-started-with-llms-a-beginners-handbook-3bfa91754aac | |||
23:20 | Idefics3: Open multimodal model based on Llama-3.1-8B https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3 | |||
23:10 | Layman view: LLM, Transformer, Attention model https://medium.com/@schandra_93485/layman-view-llm-transformer-attention-model-08cb92ee836d | |||
22:55 | Instruction back-and-forth translation: technique to generate high-quality synthetic data for… https://medium.com/@techsachin/instruction-back-and-forth-translation-technique-to-generate-high-quality-synthetic-data-for-4dbb601214a3 | |||
22:45 | Youtube Script Generator: LLM Project https://medium.com/@khananns24/youtube-script-generator-llm-project-575c3c116a25 | |||
22:07 | Llama 3.1 Deep Dive: Beyond the Hype https://ai.gopubby.com/llama-3-1-deep-dive-beyond-the-hype-68af405c4ec1 | |||
22:01 | Unlocking the Power of Local LLM Inference using Ollama running on Groq with Open WebUI https://medium.com/@kram254/unlocking-the-power-of-local-llm-inference-using-ollama-running-on-groq-with-open-webui-702672e8e83f | |||
21:37 | Data Quality is All You Need: Synthetic Data and Model Collapse https://strategycredit.co/data-quality-is-all-you-need-synthetic-data-and-model-collapse-d99dd05eb3a1 | |||
21:17 | Running a SOTA 7B Parameter Embedding Model on a Single GPU https://medium.com/@paluchasz/running-a-sota-7b-parameter-embedding-model-on-a-single-gpu-bb9b071e2238 | |||
21:14 | Leveraging LLMs to Analyze Engineering Escalations https://medium.com/@dharmikthakkar16/leveraging-llms-to-analyze-engineering-escalations-4101651dce13 | |||
20:20 | LLM Review Analyzer : Public Application with Private Models on Hugging Face https://medium.com/neural-engineer/llm-performance-review-analyzer-234886cf70d9 | |||
19:41 | Overview of LLaMA https://medium.com/@engr.tanveersultan53/overview-of-llama-0f7141c83d9e | |||
19:38 | LLM Extraction Prompts vs. Embedding-Based Semantic Search for Retrieval Agents https://medium.com/@shriyandey/llm-extraction-prompts-vs-embedding-based-semantic-search-for-retrieval-agents-e698585e6426 | |||
19:08 | Turning Words into SQL: Leveraging Streamlit and OpenAI’s Structured Output for Accurate Query… https://medium.com/@ryanklapper/turning-words-into-sql-leveraging-streamlit-and-openais-structured-output-for-accurate-query-df5c3ab8fce6 | |||
18:45 | Perplexity's popularity surges as AI search startup takes on Google https://www.ft.com/content/87af3340-2611-4650-9ae3-036927e9f65c | |||
18:37 | The New Google-Acquired Tool Revolutionizing LLM Prompt Engineering https://medium.com/@topbosstalk/the-new-google-acquired-tool-revolutionizing-llm-prompt-engineering-145eeb36b1ca | |||
18:27 | The architecture of today's LLM applications https://github.blog/ai-and-ml/llms/the-architecture-of-todays-llm-applications/ | |||
18:25 | InstrucTurca: An open source instruction tuning dataset for Turkish https://medium.com/google-developer-experts/instructurca-an-open-source-instruction-tuning-dataset-for-turkish-18c37b0e99b9 | |||
18:16 | Rewriting Nepal’s Past: My Adventure with RAG, Mistral AI, and Forgotten Chronicles https://medium.com/@sapkotabinit2002/rewriting-nepals-past-my-adventure-with-rag-mistral-ai-and-forgotten-chronicles-94865b9670ab | |||
18:01 | 😮 The Downsides of Structured Outputs https://www.llmwatch.com/p/the-downsides-of-structured-outputs | |||
17:36 | An Introduction to Mitigating Toxicity in LLMs - Pt. 2 https://blog.kensho.com/an-introduction-to-mitigating-toxicity-in-llms-pt-2-fc67d70c8acb | |||
17:11 | How Generative AI and Large Language Models Are Transforming Industries in 2024 https://medium.com/@itxvenom203/how-generative-ai-and-large-language-models-are-transforming-industries-in-2024-faa8e6d7d89e | |||
17:09 | Revolutionizing AI: How Retrieval Augmented Generation is Reshaping Information Processing https://medium.com/@pta.forwork/revolutionizing-ai-how-retrieval-augmented-generation-is-reshaping-information-processing-670e2c84f75b | |||
17:08 | MapInvaders https://medium.com/@cborel/mapinvaders-f661a4b3301c | |||
16:52 | Developing software with ChatGPT https://medium.com/@sausheong/developing-software-with-chatgpt-46a4bda99773 | |||
16:48 | Understanding LangGraph: Building Stateful Multi-Agent Applications https://medium.com/@soheil.mpg/understanding-langgraph-building-stateful-multi-agent-applications-2413d141a894 | |||
16:28 | Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs https://github.com/Dicklesworthstone/llm_aided_ocr | |||
16:03 | Tech’s Broken Record: When Promises Outshine Reality. https://feminn.medium.com/techs-broken-record-when-promises-outshine-reality-eb6759b48343 | |||
16:01 | Building a Custom AI Chatbot with Azure AI Studio (Mine Makes Cocktails!) https://colbyford.medium.com/building-a-custom-ai-chatbot-with-azure-ai-studio-mine-makes-cocktails-a2ce32e11479 | |||
15:43 | How are Large Multimodal Models (LMMs) Made? https://medium.com/@antonioconsiglio/how-are-large-multimodal-models-lmms-made-2b796c69fbbd | |||
15:35 | Creating a Custom GPT with RAG https://medium.com/@mikehpg/creating-a-custom-gpt-with-rag-2441fcabe40f | |||
15:34 | Efficient LLMs at Inference Time https://medium.com/@suvasism/efficient-llms-at-inference-time-a39439e1f361 | |||
15:14 | Let’s Get Weird, Generating the Craziest Scenes Possible in Midjourney https://medium.com/@freefigmatemplates/lets-get-weird-generating-the-craziest-scenes-possible-in-midjourney-be989d091bbd | |||
15:10 | Créez un bot Slack IA pour analyser vos leads (Claude 3.5, Perplexity) https://medium.com/@corentin_23152/cr%C3%A9ez-un-bot-slack-ia-pour-analyser-vos-leads-claude-3-5-perplexity-53825ed09b66 | |||
15:03 | A Complete Overview to Tokenization https://medium.com/@prathambatra19/a-complete-overview-to-tokenization-5f76a4d87bd4 | |||
15:02 | Over- or Under-Specifying Context in ChatGPT https://immodalbard.medium.com/over-or-under-specifying-context-in-chatgpt-05f7f7e27977 | |||
14:50 | Improving LLM Code Generation: My Best Practices https://medium.com/@mne/improving-llm-code-generation-my-best-practices-eb88b128303a | |||
14:41 | Arabic Jais-13b-chat Bitsandbytes 8 bit and 4 bit quantizations https://medium.com/@timo.au.laine/arabic-jais-13b-chat-bitsandbytes-8-bit-and-4-bit-quantizations-1d57603d8412 | |||
14:39 | Is tool-calling all you need? https://medium.com/motleycrew-ai/is-tool-calling-all-you-need-interaction-31a72b3028c0 | |||
14:38 | Chat GPT and Generative AI https://medium.com/@nfur/chat-gpt-and-generative-ai-d7135672f450 | |||
14:30 | Avaliação de Large Language Models (LLMs): Garantindo Desempenho e Ética na Era da IA https://medium.com/@jhonatansilvaluna/avalia%C3%A7%C3%A3o-de-large-language-models-llms-garantindo-desempenho-e-%C3%A9tica-na-era-da-ia-a5c2b77f0cb8 | |||
14:30 | Large Multimodal Models (LMMs) vs Large Language Models (LLMs) https://medium.com/@GPUnet/large-multimodal-models-lmms-vs-large-language-models-llms-5ecec908a62f | |||
14:25 | Structured Outputs and How to Use Them https://towardsdatascience.com/structured-outputs-and-how-to-use-them-40bd86881d39 | |||
14:24 | The Evolution of Neural Networks to Large Language Models https://medium.com/@amartalks25603/the-evolution-of-neural-networks-to-large-language-models-ecaa757130df | |||
13:56 | This AI Paper from OpenAI Introduces the GPT-4o System Card: A Framework for Safe and Responsible AI Development https://www.marktechpost.com/2024/08/09/this-ai-paper-from-openai-introduces-the-gpt-4o-system-card-a-framework-for-safe-and-responsible-ai-development/ | |||
13:36 | Unraveling FlashAttention https://towardsdatascience.com/unraveling-flashattention-a20e6483c793 | |||
13:24 | Fine-Tuning Large Language Models with PEFT (LoRA) and Rouge Score: A Comprehensive Hands-On Guide https://bobrupakroy.medium.com/fine-tuning-large-language-models-with-peft-lora-and-rogue-score-a-comprehensive-hands-on-guide-3d54179125f0 | |||
12:47 | Prompt Engineering Cookbook https://medium.com/@arora.ishant/prompt-engineering-cookbook-826538fc3733 | |||
12:43 | Zamba2–2.7B hybrid attention and state space model https://levelup.gitconnected.com/zamba2-2-7b-hybrid-attention-and-state-space-model-1af1edf4b0be | |||
12:41 | How to improve in-game AI when you have 1 million tokens https://fleker.medium.com/how-to-improve-in-game-ai-when-you-have-1-million-tokens-38013a3f289a | |||
12:31 | Prompt Engineering Demystified: Unleashing the Power of Language Models https://medium.com/@aseemmehrotra_151284/prompt-engineering-demystified-unleashing-the-power-of-language-models-011094cef7cd | |||
12:11 | OpenAI Warns Users Could Become Emotionally Hooked on Its Voice Mode https://www.wired.com/story/openai-voice-mode-emotional-attachment/ | |||
11:46 | Output Parsers no LangChain: Uma breve introdução https://medium.com/@recogna.nlp/output-parsers-no-langchain-uma-breve-introdu%C3%A7%C3%A3o-da6576cd6673 | |||
11:31 | The Limitations of LLMs: Causal Inference, Logical Deduction, and Self-Improvement https://medium.com/@info_24364/the-limitations-of-llms-causal-inference-logical-deduction-and-self-improvement-6fe794734651 | |||
11:31 | Mastering AI Facebook Post Generator For Developers: Market, Players and More https://medium.com/@marketing_novita.ai/mastering-ai-facebook-post-generator-for-developers-market-players-and-more-ee9cfd233dd8 | |||
11:31 | The Most Popular Goofy Ahh Pics of 2024 https://medium.com/@stablediffusion_17683/the-most-popular-goofy-ahh-pics-of-2024-3244a6805017 | |||
11:30 | ChatGPT now lets free users generate up to two images per day made by DALL-E 3 https://www.theverge.com/2024/8/8/24216348/chatgpt-free-users-dall-e-3-images | |||
11:00 | SENSE: Bridging the Gap Between Open-Source and Closed-Source LLMs for Advanced Text-to-SQL Parsing https://www.marktechpost.com/2024/08/09/sense-bridging-the-gap-between-open-source-and-closed-source-llms-for-advanced-text-to-sql-parsing/ | |||
10:35 | If LLM price cutting was an Olympic sport. Can waiting be a valid strategy? https://medium.com/@julian.burns50/if-llm-price-cutting-is-an-olympic-sport-can-waiting-be-a-valid-strategy-f1f32d78ead9 | |||
10:31 | Hey les Médias, si vous arrêtiez de vouloir nous biaser ? https://medium.com/@lydie_cd/hey-les-m%C3%A9dias-si-vous-arr%C3%AAtiez-de-vouloir-nous-biaser-c56b8681d7b0 | |||
10:22 | Ollama Tool Support and Call Interception Using MITM Proxy https://xxradar.medium.com/ollama-tool-support-and-call-interception-using-mitm-proxy-5ee646124d31 | |||
10:08 | Your AI Might Be Lying to You: Why LLMs Can Be Both Right and Wrong at the Same Time https://medium.com/vectrix-ai/your-ai-might-be-lying-to-you-why-llms-can-be-both-right-and-wrong-at-the-same-time-b1e393cdc0b2 | |||
09:50 | Prompt Engineering 101 https://medium.com/@meerakrsna/prompt-engineering-101-b65147c4bd2b |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803