LLM News and Articles
Friday, 2024-08-09 | ||||
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 | |||
09:44 | How to install PyTorch with Cuda on Windows 11. https://medium.com/@aniketworkofficial/a-guide-to-setting-up-cuda-and-pytorch-dd7f7ceb9d3e | |||
09:30 | Balancing Act: The Impact of Format Restrictions on Reasoning in Large Language Models https://www.marktechpost.com/2024/08/09/balancing-act-the-impact-of-format-restrictions-on-reasoning-in-large-language-models/ | |||
07:53 | RAGEval: An AI Framework for Automatically Generating Evaluation Datasets to Evaluate the Knowledge Usage Ability of Different LLMs in Different Scenarios https://www.marktechpost.com/2024/08/09/rageval-an-ai-framework-for-automatically-generating-evaluation-datasets-to-evaluate-the-knowledge-usage-ability-of-different-llms-in-different-scenarios/ | |||
07:50 | Gemma 2B — Compact and performant LLM that runs on your computer https://medium.com/@simeon.emanuilov/gemma-2b-compact-and-performant-llm-that-runs-on-your-computer-6374cfd792e7 | |||
07:47 | Dialogue with Claude 10 — Two types of global optimization https://medium.com/@chatc3po/dialogue-with-claude-10-two-types-of-global-optimization-d66bd2ae2cbb | |||
06:54 | How AI VC funding in the 1st half of 2024 can guide your AI startup strategy https://medium.com/ai-business-asia/how-ai-vc-funding-in-the-1st-half-of-2024-can-guide-your-ai-startup-strategy-660c61099504 | |||
06:16 | Hugging Face and Python in Natural Language Processing https://medium.com/@ccpythonprogramming/hugging-face-and-python-in-natural-language-processing-7a5c24fa52a7 | |||
06:07 | Developing and Deploying LLM-Powered APIs with Spring AI and OpenAI on WSO2 Choreo https://medium.com/choreo-tech-blog/developing-and-deploying-llm-powered-apis-with-spring-ai-and-openapi-on-wso2-choreo-d5e30f255c56 | |||
05:54 | What’s the Best LLM to Use for RAG? https://medium.com/@naman1011/whats-the-best-llm-to-use-for-rag-476bec1bfa97 | |||
05:42 | Running local LLM on a Gaming PC https://medium.com/@tugrul_acikgoz/running-local-llm-on-a-gaming-pc-7408e7805c49 | |||
04:37 | Can your potato PC run AI models locally https://haztechycontent.medium.com/can-your-potato-pc-run-ai-models-locally-model-like-mistral-and-phi3-6bb36ede2cca | |||
03:57 | Use Mistral AI to build generative AI applications with Go https://itnext.io/use-mistral-ai-to-build-generative-ai-applications-with-go-2a8fa685bffb | |||
03:56 | Exploring Futuristic Visions of Peru Through AI Image Generation https://pub.towardsai.net/exploring-futuristic-visions-of-peru-through-ai-image-generation-b2e2848b48a3 | |||
03:53 | Qwen2-Math-1.5B/7B/72B https://medium.com/@modelbox/qwen2-math-1-5b-7b-72b-58aeb9e84229 | |||
03:09 | Social Media: The Gift that Keeps On Giving (to Big Tech) https://medium.com/@twostalks/social-media-the-gift-that-keeps-on-giving-to-big-tech-7fea4e48f690 | |||
02:48 | RAG and LLM Evaluation Metrics https://medium.com/@bavalpreetsinghh/rag-and-llm-evaluation-metrics-9cfe004d5bc3 | |||
02:14 | ChatGPT is WORSE Than You Think! https://ai.plainenglish.io/chatgpt-is-worse-than-you-think-a844203b24fd | |||
00:45 | RLHF — Refinando os Outputs de LLMs usando Feedback Humano https://medium.com/@ian.barreiro/rlhf-refinando-os-outputs-de-llms-usando-feedback-humano-afab781079cc | |||
Thursday, 2024-08-08 | ||||
23:37 | Is the great reckoning with GenAI finally here? https://medium.com/@chrislele/is-the-great-reckoning-with-genai-finally-here-02cbd1c5587d | |||
23:33 | Aloha Protocol and Masa: Enhancing AI Accuracy Together https://medium.com/@aloha_protocol/aloha-protocol-and-masa-enhancing-ai-accuracy-together-710a4721f79b | |||
23:02 | Token Sampling Methods — Greedy Decoding https://medium.com/@chitrakumarsai/token-sampling-methods-greedy-decoding-f755d31890c2 | |||
22:40 | Re-Ranking for Better Answers! https://medium.com/@hardikgodara/re-ranking-for-better-answers-2fcbce89ad2c | |||
22:29 | Major shifts at OpenAI spark skepticism about impending AGI timelines https://arstechnica.com/information-technology/2024/08/major-shifts-at-openai-spark-skepticism-about-impending-agi-timelines/ | |||
21:22 | L’intelligenza dei grandi modelli linguistici: illusione statistica o realtà emergente? https://robertoanglani.medium.com/lintelligenza-dei-grandi-modelli-linguistici-illusione-statistica-o-realt%C3%A0-emergente-e81bcfe6f09e | |||
21:15 | Human-like Conversational AI: Combining Semantic Search with Large Language Models for Enriched… https://engineering.miko.ai/human-like-conversational-ai-combining-semantic-search-with-large-language-models-for-enriched-bfea17e5a015 | |||
20:46 | Inverting Language Model:Key Takeaways from an NLP Seminar https://ppujari.medium.com/inverting-language-model-key-takeaways-from-an-nlp-seminar-cebb4a4691d7 | |||
20:21 | Zuckerberg’s AI Push: Llama 3.1 and Open-Source Innovations https://parvaneshafiei.medium.com/zuckerbergs-ai-push-llama-3-1-and-open-source-innovations-627feafa7688 | |||
20:11 | Introducing OpenVINO 2024.3: Enhanced LLM Performance https://medium.com/openvino-toolkit/introducing-openvino-2024-3-enhanced-llm-performance-a5ab3a635fb7 | |||
20:01 | The Best Practices of RAG https://pub.towardsai.net/the-best-practices-of-rag-300e313322e6 | |||
19:01 | Zico Kolter Joins OpenAI's Board of Directors https://openai.com/index/zico-kolter-joins-openais-board-of-directors/ | |||
18:45 | The Role of Data Engineers in Building Large Language Models for Effective Developer Marketing https://medium.com/@singhdikku/the-role-of-data-engineers-in-building-large-language-models-for-effective-developer-marketing-2f8592cc1796 | |||
18:17 | UK regulator to examine B Amazon investment in AI startup Anthropic https://www.theguardian.com/technology/article/2024/aug/08/anthropic-ai-startup-uk-regulator-cma-amazon-investment | |||
18:09 | Ask Not What AI Can Do for You — Ask What You Can Achieve with AI https://towardsdatascience.com/ask-not-what-ai-can-do-for-you-ask-what-you-can-achieve-with-ai-36814f622849 | |||
18:01 | Paper review: Learning to Model the World with Language https://medium.com/@dataism/paper-review-learning-to-model-the-world-with-language-ac33c67a8353 | |||
17:17 | OpenAI — Yeni Özelliği: Yapılandırılmış Çıktılar ile Güvenilir AI Yanıtları https://medium.com/nane-limon/openai-yeni-%C3%B6zelli%C4%9Fi-yap%C4%B1land%C4%B1r%C4%B1lm%C4%B1%C5%9F-%C3%A7%C4%B1kt%C4%B1lar-ile-g%C3%BCvenilir-ai-yan%C4%B1tlar%C4%B1-17a580c72df6 | |||
17:12 | GPT-4o System Card https://openai.com/index/gpt-4o-system-card/ | |||
17:11 | Mastering LLM Custom Data Training: How to Train Your Own Large Language Model with Personal Text… https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-how-to-train-your-own-large-language-model-with-personal-text-f3dfaf42994f | |||
17:02 | Top 5 Open Source AI Agents that Transform Your Life https://medium.com/@dataoorts/top-5-open-source-ai-agents-that-transform-your-life-3a38a2e527b7 | |||
16:53 | A Comprehensive Guide to Using Large Language Models (LLMs) with AI: Implementing Sensor and Camera… https://medium.com/@pranshu.singh765/a-comprehensive-guide-to-using-large-language-models-llms-with-ai-implementing-sensor-and-camera-ca55c1bc1a15 | |||
16:40 | Scaling human LLM Evals with open source crowdlab https://cleanlab.ai/blog/team-llm-evals/ | |||
16:20 | Product Recommendation with Machine Learning https://medium.com/@asimsultan2/product-recommendations-with-machine-learning-aa643d71b8e9 | |||
16:11 | How to Estimate Chatbot Costs https://medium.com/@tom_83889/how-to-estimate-chatbot-costs-664de743155a | |||
16:02 | Can Mixture of Experts (MoE) Models Push GenAI to the Next Level? https://pub.towardsai.net/can-mixture-of-experts-moe-models-push-genai-to-the-next-level-8951d2f85283 | |||
15:45 | Data Engineer 2.0. Part III: Boosting Customer Satisfaction with RAG over Adevinta’s GenAI Platform https://boroju.medium.com/data-engineer-2-0-part-iii-boosting-customer-satisfaction-with-rag-over-adevintas-genai-platform-7c3d6e3704fc | |||
15:39 | MoA (Multi-model Aggregation) with Python https://alberto98fx.medium.com/moa-multi-model-aggregation-with-python-1f1590676a42 | |||
15:39 | HuggingFace Acquires XetHub to Version Datasets and Models https://www.forbes.com/sites/richardnieva/2024/08/08/hugging-face-xethub-acquisition/ | |||
15:20 | Sales Forecast using LLM’s https://medium.com/@ravindarmadishetty/sales-forecast-using-llms-a3571f275403 | |||
14:31 | #35 Advanced prompting techniques are a myth…it’s all about good communication! https://pub.towardsai.net/35-advanced-prompting-techniques-are-a-myth-its-all-about-good-communication-c1222116126a | |||
14:29 | Exploring the World of Large Language Models: A Comprehensive Guide https://saurabhharak.medium.com/exploring-the-world-of-large-language-models-a-comprehensive-guide-44cce08594c5 | |||
14:26 | How to Convince Your Boss or Client of AI’s Value https://medium.com/@myaskai/how-to-convince-your-boss-or-client-of-ais-value-7e3e158d78be | |||
14:11 | Guide to Next-Gen Multi-PDF Chatbot: A Dive into LLAMA3, LangGraph, and Adaptive RAG https://medium.com/@jyeshthawork/guide-to-next-gen-multi-pdf-chatbot-a-dive-into-llama3-langgraph-and-adaptive-rag-4f1eadbe4a2e | |||
14:08 | Large Language Model Reasoning Process and Prompting techniques Part 2 https://billtcheng2013.medium.com/large-language-model-reasoning-process-and-prompting-techniques-part-2-f048d6e7e76f | |||
13:14 | Function Calling in Generative AI https://ugurozker.medium.com/function-calling-in-generative-ai-7c44a82ee956 | |||
13:14 | Supercharge Your Customer Data with AI https://blog.getwren.ai/supercharge-your-customer-data-with-ai-dd3822f42954 | |||
13:06 | A Modern Approach to Customer Risk Assessment with LLMs https://medium.com/@j.m.olivera08/a-modern-approach-to-customer-risk-assessment-with-llms-5fa4d1548c63 | |||
12:45 | How to Change Node ID and Port on a Gaianet Node LLM https://medium.com/@zulfanbaswedan/how-to-change-node-id-and-port-on-a-gaianet-node-llm-98a80a5a2886 | |||
12:27 | Zamba2–2.7B hybrid attention and state space model https://ai.plainenglish.io/zamba2-2-7b-hybrid-attention-and-state-space-model-aa5634dadad6 | |||
12:27 | Create a simple Chatbot with OpenAI and Gradio. https://ai.plainenglish.io/create-a-simple-chatbot-with-openai-and-gradio-202684d18f35 | |||
12:17 | Turbo-Charging Text Classification with Question Answering Techniques https://medium.com/@sergii.ivakhno/turbo-charging-text-classification-with-question-answering-techniques-f29c9f2db98d | |||
12:11 | Deploy AI apps using Docker to containerize python-based GEN-AI Apps. https://medium.com/@aaryangupta2201/deploy-ai-apps-using-docker-to-containerize-python-based-gen-ai-apps-b29f7f716348 | |||
12:08 | Getting Started with Structured Output in Azure OpenAI https://valentinaalto.medium.com/getting-started-with-structured-output-in-azure-openai-adfbefb19867 | |||
11:45 | ECCO: A Reproducible AI Benchmark for Evaluating Program Efficiency via Two Paradigms- Natural Language (NL) based Code Generation and History-based Code Editing https://www.marktechpost.com/2024/08/08/ecco-a-reproducible-ai-benchmark-for-evaluating-program-efficiency-via-two-paradigms-natural-language-nl-based-code-generation-and-history-based-code-editing/ | |||
11:25 | Unleashing the Power of Mistral Agents: Automating Workflows for Efficiency and Productivity https://medium.com/@cognidownunder/unleashing-the-power-of-mistral-agents-automating-workflows-for-efficiency-and-productivity-5d5f4052dd00 | |||
11:22 | Is sus-column-r GPT5 in disguise? https://ai.gopubby.com/is-sus-column-r-gpt5-in-disguise-37cffc014dfd | |||
11:12 | 8 Can't-Miss GitHub Projects https://medium.com/sourcescribes/8-cant-miss-github-projects-e427eb564c31 | |||
11:11 | Outage for Anthropic's Claude 3.5 Sonnet https://status.anthropic.com/incidents/q5dvt5ph7tzx | |||
10:44 | Controllable Agent for Complex RAG Tasks https://medium.com/@nirdiamant21/controllable-agent-for-complex-rag-tasks-bf8cb652fbb3 | |||
10:10 | I made India’s first virtual fitness trainer and here’s how you can, too! https://medium.com/@nandanigupta4/i-made-indias-first-virtual-fitness-trainer-and-here-s-how-you-can-too-c693e596f1b8 | |||
10:08 | Show HN: Scraping Structured Data with OpenAI https://www.hystruct.com | |||
09:44 | The Rise of Lazy LLMs: Pushing the Boundaries of Language Model Efficiency https://medium.com/@anoop_gupta/the-rise-of-lazy-llms-pushing-the-boundaries-of-language-model-efficiency-ca8cd828f4d6 | |||
09:32 | Perchance AI Story Generator Tips: Build Your AI Narrative https://medium.com/@marketing_novita.ai/perchance-ai-story-generator-tips-build-your-ai-narrative-d731b4c5b2c2 | |||
09:16 | Torchchat — Accelerating local LLM inference across devices https://medium.com/@simeon.emanuilov/torchchat-accelerating-local-llm-inference-across-devices-9e0579644a15 | |||
08:59 | How to Talk with AI https://medium.com/@gurkan.dogan12/how-to-talk-with-ai-34a2abeb56d9 | |||
08:57 | Secure execution of code generated by Large Language Models https://medium.com/@philippkai/secure-execution-of-code-generated-by-large-language-models-625654de951a | |||
08:44 | Multi-GPU Fine-tuning for Llama 3.1 70B with FSDP and QLoRA https://towardsdatascience.com/multi-gpu-fine-tuning-for-llama-3-1-70b-with-fsdp-and-qlora-67a8a5b4f0d6 | |||
08:39 | Large Language Models: Deep Dive Into Uses, Benefits, and Insights (LLMs) https://medium.com/@sumeriamahi1906/large-language-models-deep-dive-into-uses-benefits-and-insights-llms-4a710512f329 | |||
08:19 | How to Run Llama-3.1 locally in Python using Ollama, LangChain https://emmakodes.medium.com/how-to-run-llama-3-1-locally-in-python-using-ollama-langchain-331c9984a4b5 | |||
08:01 | How Many Languages Does Your Tech Speak? Linguistic Diversity & LLMs https://medium.com/the-lumiera-loop/how-many-languages-does-your-tech-speak-linguistic-diversity-llms-8bb91edcb931 | |||
07:38 | GitHub Models: Your Gateway Drug to AI Engineering https://augmentedstartups.medium.com/github-models-your-gateway-drug-to-ai-engineering-e57789dd306f | |||
07:33 | Let’s build ReWOO with LangGraph and Tavily https://medium.com/@minhle_0210/lets-build-rewoo-with-langgraph-and-tavily-9fbbc43aca05 | |||
07:30 | Data Scientist Internship at GovTech AI Practice: Automated Stance Analysis of Citizen Discussions https://medium.com/dsaid-govtech/data-scientist-internship-at-govtech-ai-practice-automated-stance-analysis-of-citizen-discussions-4fd7b72c6994 | |||
06:45 | Lagent: A Lightweight Open-Source Python Framework that Allows Users to Efficiently Build Large Language Model (LLM)-Based Agents https://www.marktechpost.com/2024/08/07/lagent-a-lightweight-open-source-python-framework-that-allows-users-to-efficiently-build-large-language-model-llm-based-agents/ | |||
06:30 | Meta-Rewarding LLMs: A Self-Improving Alignment Technique Where the LLM Judges Its Own Judgements and Uses the Feedback to Improve Its Judgment Skills https://www.marktechpost.com/2024/08/07/meta-rewarding-llms-a-self-improving-alignment-technique-where-the-llm-judges-its-own-judgements-and-uses-the-feedback-to-improve-its-judgment-skills/ | |||
06:18 | So what are Program-Aided Large Language (PAL) Models? https://bobrupakroy.medium.com/so-what-are-program-aided-large-language-pal-models-e438e94c8f2e | |||
06:12 | Unlocking AI Power Without Wi-Fi: The Offline Revolution https://xpressinnovations.medium.com/unlocking-ai-power-without-wi-fi-the-offline-revolution-10f6537e9ddf | |||
05:50 | Elastic’s RAG- based AI Assistant: Analyze application issues with LLMs and private GitHub issues https://medium.com/@arvind_14116/elastics-rag-based-ai-assistant-analyze-application-issues-with-llms-and-private-github-issues-44971878c6ce | |||
05:48 | Supercharging Supply Chain Optimization with AI Magic! https://dirk-schmidt.medium.com/supercharging-supply-chain-optimization-with-ai-magic-75012bd77255 | |||
04:50 | Cybersecurity with Specialized LLM Agents — Part 2 https://medium.com/@sabarna17/cybersecurity-with-specialized-llm-agents-part-2-3108837674fc | |||
04:03 | Production RAG Must-have Trick — Generative Feedback Loops https://angelina-yang.medium.com/production-rag-must-have-trick-generative-feedback-loops-04e47104b946 | |||
04:02 | ROUGE and BLEU: Measuring Language Model Quality https://medium.datadriveninvestor.com/rouge-and-bleu-measuring-language-model-quality-0a0530640579 | |||
03:11 | HyDE: Enhancing Retrieval in RAG Systems https://medium.com/@asimadnan/hyde-enhancing-retrieval-in-rag-systems-72e8b4b3441a | |||
02:08 | Intel Labs Introduce RAG Foundry: An Open-Source Python Framework for Augmenting Large Language Models LLMs for RAG Use Cases https://www.marktechpost.com/2024/08/07/intel-labs-introduce-rag-foundry-an-open-source-framework-for-augmenting-large-language-models-llms-for-rag-use-cases/ | |||
01:18 | Google "We Have No Moat, and Neither Does OpenAI" (2023) https://www.semianalysis.com/p/google-we-have-no-moat-and-neither | |||
00:25 | Machine Learning Series: 2. Energy Efficiency in AI Accelerators https://machinelearningtech.medium.com/machine-learning-series-2-energy-efficiency-in-ai-accelerators-bc2a400acc89 | |||
00:00 | XetHub is joining Hugging Face! https://huggingface.co/blog/xethub-joins-hf |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803