LLM News and Articles
Tuesday, 2024-08-27 | ||||
16:36 | Influencing a Large Language Model response with in-context learning. https://levelup.gitconnected.com/influencing-a-large-language-model-response-with-in-context-learning-b212f0eaa113 | |||
16:34 | Half of AGI safety researchers have left OpenAI https://archive.is/2024.08.26-203127/https://fortune.com/2024/08/26/openai-agi-safety-researchers-exodus/ | |||
16:33 | Cerebras Launches the Fastest AI Inference https://inference.cerebras.ai/ | |||
16:31 | LLM Study Diary: Decoding LangChain’s Official Multimodal RAG Sample https://medium.com/llm-study-diary-a-beginners-path-through-ai/llm-study-diary-decoding-langchains-official-multimodal-rag-sample-b4a645bdabe2 | |||
16:24 | Counting Tokens in OpenAI API Requests Using tiktoken https://kshitijkutumbe.medium.com/counting-tokens-in-openai-api-requests-using-tiktoken-da72f880e0bb | |||
16:15 | Case Study: How Salomatic Used Langtrace to Build a Reliable Medical Report Generation System https://medium.com/@Langtrace/case-study-how-salomatic-used-langtrace-to-build-a-reliable-medical-report-generation-system-0068660ae7c7 | |||
16:10 | cerebras: 450 tokens/sec llama 3.1 70B https://www.theregister.com/2024/08/27/cerebras_ai_inference/ | |||
16:10 | Hyperparameter Tuning: https://blog.devops.dev/hyperparameter-tuning-62bdf135248f | |||
16:09 | AI against AI ? https://medium.com/@ameya.naik/ai-against-ai-e0d81289efcc | |||
16:01 | RAG app with uploads on Cloudflare workers https://pub.towardsai.net/rag-app-with-uploads-on-cloudflare-workers-48987f9f0818 | |||
16:01 | Anthropic: Artifacts are now generally available https://www.anthropic.com/news/artifacts | |||
16:01 | Generative AI Certification Test: Our New Launch With Activeloop https://pub.towardsai.net/generative-ai-certification-test-our-new-launch-with-activeloop-12fa5ebdee46 | |||
15:51 | TAI #114: Two Paths to Small LMs? https://pub.towardsai.net/tai-114-two-paths-to-small-lms-83e3d75455ab | |||
15:31 | Exploring the Depths of AI Story writing in the Prompt Engineering Hackathon https://ztrimus.medium.com/exploring-the-depths-of-ai-story-writing-in-the-prompt-engineering-hackathon-2cc2ae451d9f | |||
15:18 | Evaluating the Limits of Generative AI Models https://umair-iftikhar.medium.com/evaluating-the-limits-of-generative-ai-models-04ea711639df | |||
15:16 | Impact of Apple’s Buybacks on Average Stock Returns https://scalarfield.medium.com/impact-of-apples-buybacks-on-average-stock-returns-8af152ea75fe | |||
15:13 | Combating Deepfakes: Does It More Than Just a Matter of Willpower https://guillaume-blaquiere.medium.com/combating-deepfakes-does-it-more-than-just-a-matter-of-willpower-00cf98f970f1 | |||
14:52 | The Best NVIDIA GPUs for LLM Inference: A Comprehensive Guide https://medium.com/@mahernaija/the-best-nvidia-gpus-for-llm-inference-a-comprehensive-guide-e093c9d914e5 | |||
14:31 | From ELIZA to GPT-3: Tracing the Remarkable Evolution of Large Language Models https://medium.com/@seekmeai/from-eliza-to-gpt-3-tracing-the-remarkable-evolution-of-large-language-models-bffcce75da75 | |||
14:21 | Tonic Textual: An easy way to prepare your documents for enterprise AI on Snowflake https://medium.com/snowflake/tonic-textual-an-easy-way-to-prepare-your-documents-for-enterprise-ai-on-snowflake-5545e3992b6e | |||
14:18 | The GPT Influence on Our Writing: Why Detection Tools Are Struggling? https://medium.com/@husseinmaatouk506/the-gpt-influence-on-our-writing-why-detection-tools-are-struggling-d5b20d5b8abe | |||
14:17 | Llama 3.1 Context Window, Tokens, Explained https://towards-agi.medium.com/llama-3-1-context-window-tokens-explained-e4a2f42479f8 | |||
14:12 | Inference is free and instant https://fume.substack.com/p/inference-is-free-and-instant | |||
14:04 | Understanding AI and Chatbot Language Models: The Future of Human-Like Conversations https://fomo52.medium.com/understanding-ai-and-chatbot-language-models-the-future-of-human-like-conversations-f242ca50d632 | |||
12:28 | Open source Large Language Models in production on AWS https://medium.com/@mirzasamaddanat/open-source-large-language-models-in-production-on-aws-115c41680360 | |||
12:03 | Federating Agents for Fantastic Applications: Exploring Agentification https://medium.com/@kushhanskumaragarwal/federating-agents-for-fantastic-applications-exploring-agentification-8a3a754971e4 | |||
11:55 | MiniCPM-V: Unlocking a New Era of Mobile AI with Flutter Integration https://medium.com/@kram254/minicpm-v-unlocking-a-new-era-of-mobile-ai-with-flutter-integration-d9a58501186f | |||
11:48 | Run an LLM directly in your browser. No external APIs are needed! https://ai.gopubby.com/run-an-llm-directly-in-your-browser-no-external-apis-are-needed-5459fb283c52 | |||
11:05 | Prompt Chaining https://medium.com/@simple0314/prompt-chaining-6758819cdb73 | |||
10:59 | Cracking AI’s Black Boxes https://blog.pelles.ai/cracking-ais-black-boxes-5617f778a1b0 | |||
10:52 | Hands-on Experience with AnythingLLM: RAG Tools Seem Superficial and Too Rigid https://medium.com/@pamperherself/hands-on-experience-with-anythingllm-rag-tools-seem-superficial-and-too-rigid-e904e3ceab4c | |||
10:42 | Haystack: the new LLM framework that is shaking its competitors https://ai.plainenglish.io/haystack-the-new-llm-framework-that-is-shaking-its-competitors-1a083a153fd9 | |||
10:36 | The Future of Software Engineering: AI’s Impact on Coding Jobs https://medium.com/@AshJai/the-future-of-software-engineering-ais-impact-on-coding-jobs-9d63917338b6 | |||
10:34 | Must-Try Headcanon Generators: Example and Development Guide https://medium.com/@marketing_novita.ai/must-try-headcanon-generators-example-and-development-guide-034e6f3d6617 | |||
10:28 | I rewrote the System Prompt from @AnthropicAI ’s Claude 3.5 Sonnet in Sharaku-style. https://medium.com/@sharakusatoh/i-rewrote-the-system-prompt-from-anthropicai-s-claude-3-5-sonnet-in-sharaku-style-67acf0b15835 | |||
10:23 | Simple Chunking Strategies for RAG Applications (Part 1) https://medium.com/@ayoubkirouane3/simple-chunking-strategies-for-rag-applications-part-1-d56903b167c5 | |||
10:09 | Data Scientists: Endangered Species or Evolving Superheroes? https://medium.com/@jcrsch/data-scientists-endangered-species-or-evolving-superheroes-20e8f618ab60 | |||
10:07 | Hugging Face Speech-to-Speech Library: A Modular and Efficient Solution for Real-Time Voice Processing https://www.marktechpost.com/2024/08/27/hugging-face-speech-to-speech-library-a-modular-and-efficient-solution-for-real-time-voice-processing/ | |||
09:24 | Mastering Language Models: A Beginner’s Guide to Fine-Tuning and Pretraining https://python.plainenglish.io/mastering-language-models-a-beginners-guide-to-fine-tuning-and-pretraining-59ba3d953ac4 | |||
08:46 | The Convergence of Large Language Models and Brain Computing: A New Frontier in AI https://medium.com/@cognidownunder/the-convergence-of-large-language-models-and-brain-computing-a-new-frontier-in-ai-6c3f4cb68bbb | |||
08:31 | in Generative AI https://medium.com/@shreyakhandelwalofficial/in-generative-ai-a8d0e6fb584b | |||
08:17 | OpenAI is in favour of the California AI bill that mandates “watermarking” of artificial content. https://mdbconsultant.medium.com/openai-is-in-favour-of-the-california-ai-bill-that-mandates-watermarking-of-artificial-content-f8a018e61e81 | |||
08:03 | Building a GenAI Career Assistant: A Multi-Agent Approach with LangGraph and Streamlit https://medium.com/@amanvaryani1910/building-a-genai-career-assistant-a-multi-agent-approach-with-langgraph-and-streamlit-0ff9410e8d39 | |||
08:03 | Generative AI Prioritization Framework https://medium.com/futurum-strategia/generative-ai-prioritization-framework-c283a991e9e1 | |||
07:41 | How we are thinking about generative AI: costs and abilities https://medium.com/mantisnlp/how-we-are-thinking-about-generative-ai-costs-and-abilities-7533d349a79b | |||
07:40 | From Static Files to Smart Conversations: Introduction to RAG https://medium.com/@theprajuktadey/from-static-files-to-smart-conversations-introduction-to-rag-39cb66d3f08c | |||
07:25 | ATS Resume Expert: Enhance Your Resume with Streamlit and Gemini Pro https://medium.com/@sarita_68521/ats-resume-expert-enhance-your-resume-with-streamlit-and-gemini-pro-49f85036f214 | |||
07:14 | What direction should AI practitioners take in the era of Super Large Models? https://medium.com/@_betterversion/what-direction-should-ai-practitioners-take-in-the-era-of-super-large-models-4bc3fd07c658 | |||
06:48 | Tired of ChatGPT Hallucinating on Your Favorite Programming Package? https://medium.com/@shreyasagrawal2000/tired-of-chatgpt-hallucinating-on-your-favorite-programming-package-403eefe4e74d | |||
06:05 | Advancing Medical Abstractive Summarization with uMedSum https://medium.com/@aishiknagar/advancing-medical-abstractive-summarization-with-umedsum-d5afc5020b91 | |||
05:46 | Discord AI Bot with Cohere LLM Integration https://clubwritter.medium.com/discord-ai-bot-with-cohere-llm-integration-0685debe6f75 | |||
05:43 | How to Train Your LLM : Unleashing the Beast of AI That Remembers Everything! — Part 2 https://kshirsagar-arvind.medium.com/how-to-train-your-llm-unleashing-the-beast-of-ai-that-remembers-everything-part-2-ff8705bf5317 | |||
05:31 | Exciting News: Sonic Partners with ELNA.ai for Enhanced User Support! https://elna-ai.medium.com/exciting-news-sonic-partners-with-elna-ai-for-enhanced-user-support-7252996c0b59 | |||
05:28 | Text Generation Strategies for Large Language Models https://medium.com/state-of-the-art-technology/text-generation-strategies-for-large-language-models-23745910ed1f | |||
05:26 | StructuredRAG Released by Weaviate: A Comprehensive Benchmark to Evaluate Large Language Models’ Ability to Generate Reliable JSON Outputs for Complex AI Systems https://www.marktechpost.com/2024/08/26/structuredrag-released-by-weaviate-a-comprehensive-benchmark-to-evaluate-large-language-models-ability-to-generate-reliable-json-outputs-for-complex-ai-systems/ | |||
05:17 | Proven Techniques For Incredibly Useful LLM Responses https://medium.com/@ImpactInsider/proven-techniques-for-incredibly-useful-llm-responses-2403ad961db4 | |||
04:45 | Anthropic publishes the 'system prompts' that make Claude tick https://techcrunch.com/2024/08/26/anthropic-publishes-the-system-prompt-that-makes-claude-tick/ | |||
04:35 | Beyond the Filter: Mitigating False Positives in Large Language Models https://medium.com/@abhi.hrs/beyond-the-filter-mitigating-false-positives-in-large-language-models-81743f3b08de | |||
04:05 | From Words to Worlds: Revolutionizing the Metaverse with Neuro-Symbolic Systems https://medium.com/@zouheir.tricha/from-words-to-worlds-revolutionizing-the-metaverse-with-neuro-symbolic-systems-8c2243265bb2 | |||
03:54 | Getting Started with GitHub Actions: A Beginner’s Guide https://gohilriddhi.medium.com/getting-started-with-github-actions-a-beginners-guide-0fc98bffff69 | |||
03:15 | Organizing Prompts Efficiently for Improved Response Management https://medium.com/@connor.m.bell13/organizing-prompts-efficiently-for-improved-response-management-3f79e573a327 | |||
02:13 | OpenAI exits SF HQ after Elon Musk stops paying their rent https://therealdeal.com/sanfrancisco/2024/08/26/openai-exits-san-francisco-hq-after-split-with-elon-musk/ | |||
00:55 | What is the Best Open Source LLM Right Now? https://medium.com/@aifusion.contact/what-is-the-best-open-source-llm-right-now-830de061e910 | |||
00:13 | Exploring the Strategic Capabilities of LLMs in a Risk Game Setting https://towardsdatascience.com/exploring-the-strategic-capabilities-of-llms-in-a-risk-game-setting-43c868d83c3b | |||
Monday, 2024-08-26 | ||||
23:57 | LongWriter: Now LLM can generate output of 20,000 words https://generativeai.pub/longwriter-now-llm-can-generate-output-of-20-000-words-7bf6f6945652 | |||
23:56 | ScrapeGraphAI #1: Leveraging the Power of LLMs to Solve Data Collection and Processing Challenges… https://generativeai.pub/scrapegraphai-1-leveraging-the-power-of-llms-to-solve-data-collection-and-processing-challenges-00127c3b1cc6 | |||
23:54 | What is the Cost of Training LLM Models? https://medium.com/@aifusion.contact/what-is-the-cost-of-training-llm-models-c71692f7d91a | |||
23:52 | Spotting AI Fakes Just Got Easier, Thanks to H2O Danube3 https://generativeai.pub/spotting-ai-fakes-just-got-easier-thanks-to-h2o-danube3-a622b5ae9908 | |||
23:38 | What is Natural Language Generation? https://medium.com/@martingaida.mg/what-is-natural-language-generation-5735c5522f38 | |||
23:06 | Gen AI — Building Adoption through a Common Platform instead of enabling ‘be-spoke’ use cases. https://medium.com/@nayan.j.paul/gen-ai-building-adoption-through-a-common-platform-instead-of-enabling-be-spoke-use-cases-b0cbc2e185a8 | |||
22:49 | Nearly half of OpenAI's Safety Researchers have left https://fortune.com/2024/08/26/openai-agi-safety-researchers-exodus/ | |||
21:57 | AI vs. Humans: The Epic Showdown for Creative Supremacy (Spoiler: We Might Need to Learn… https://medium.com/@mindmachina/ai-vs-humans-the-epic-showdown-for-creative-supremacy-spoiler-we-might-need-to-learn-ef97691649d9 | |||
21:31 | Boost Running with RXT4080: GPU Cloud Tips https://medium.com/@agi_63938/boost-running-with-rxt4080-gpu-cloud-tips-4ca0e4727a08 | |||
21:23 | How to Run and Use Open Source Models on Your Computer https://medium.com/@minadev/how-to-run-and-use-open-source-models-on-your-computer-b1e040b6922a | |||
21:23 | 7 questions to know if your AI startup will make it (according to Peter Thiel) https://medium.com/@enricdomingo/7-questions-to-know-if-your-ai-startup-will-make-it-according-to-peter-thiel-7df661c50bc6 | |||
20:39 | No Baseline? No Benchmarks? No Biggie! An Experimental Approach to Agile Chatbot Development https://towardsdatascience.com/lessons-from-agile-experimental-chatbot-development-73ea515ba762 | |||
20:38 | uMedSum: A Novel AI Framework for Accurate and Informative Medical Summarization https://www.marktechpost.com/2024/08/26/umedsum-a-novel-ai-framework-for-accurate-and-informative-medical-summarization/ | |||
20:37 | Inference is FREE and INSTANT https://medium.com/@emre_24905/inference-is-free-and-instant-1041e585d2bb | |||
20:31 | Prompt engineering as a new kind of user interface https://medium.com/tr-labs-ml-engineering-blog/prompt-engineering-as-a-new-kind-of-user-interface-44fa76dd09e9 | |||
20:27 | How to Build Reliable Human Annotation Guidelines with LLMs https://medium.com/tr-labs-ml-engineering-blog/how-to-build-reliable-human-annotation-guidelines-with-llms-2cd8bbeff2a2 | |||
19:54 | FuriosaAI unveils RNGD inference NPU: 512 TOPS (FP8) 150W TDP https://www.eetimes.com/furiosa-targets-llm-inference-with-second-gen-chip/ | |||
19:43 | ** & : - … https://medium.com/@verma.himanshu0912/-38a7b726c1c6 | |||
19:43 | Mastering Retrieval-Augmented Generation (RAG): A Practical Guide for New Developers https://medium.com/@sergio1101102/mastering-retrieval-augmented-generation-rag-a-practical-guide-for-new-developers-624be24ca516 | |||
19:37 | The Future of Mobile Apps: Embracing AI and Addressing Privacy https://medium.com/@tarang0510/the-future-of-mobile-apps-embracing-ai-and-addressing-privacy-60205657afcd | |||
18:51 | Mastering Prompt Structure for ChatGPT-4o Success https://medium.com/@tomskiecke/mastering-prompt-structure-for-chatgpt-4o-success-5fc84735809f | |||
18:15 | AppAgent v2 With Advanced Agent for Flexible Mobile Interactions https://cobusgreyling.medium.com/appagent-v2-with-advanced-agent-for-flexible-mobile-interactions-e58e9c6abc6c | |||
18:10 | Benchmarking Large Language Models in Biomedical Classification and Named Entity Recognition: Evaluating the Impact of Prompting Techniques and Domain Knowledge https://www.marktechpost.com/2024/08/26/benchmarking-large-language-models-in-biomedical-classification-and-named-entity-recognition-evaluating-the-impact-of-prompting-techniques-and-domain-knowledge/ | |||
18:09 | Tackle Complex LLM Decision-Making with Language Agent Tree Search (LATS) & GPT-4O https://343544.medium.com/tackle-complex-llm-decision-making-with-language-agent-tree-search-lats-gpt4-o-0bc648c46ea4 | |||
18:06 | Advanced Retrieval Techniques in a World of 2M Token Context Windows: Part 2 on Re-rankers https://towardsdatascience.com/advanced-retrieval-techniques-in-a-world-of-2m-token-context-windows-part-2-on-re-rankers-a0dfa03ba325 | |||
17:54 | Microsoft Autogen: Your AI Helper for Coding and Beyond(PART-1) https://pub.towardsai.net/microsoft-autogen-your-ai-helper-for-coding-and-beyond-part-1-dd1fb17eeab4 | |||
16:42 | Empower Your Business with Next-Generation Solutions https://medium.com/oracledevs/empower-your-business-with-next-generation-solutions-46ff661c6cd0 | |||
16:12 | Google Summer of Code 2024 Red Hen Lab Final evaluation https://medium.com/@jaintarun7/google-summer-of-code-2024-red-hen-lab-final-evaluation-9b8d25d8dd62 | |||
16:12 | Show HN: BatchWizard – A CLI tool for managing OpenAI batch processing jobs https://github.com/cmakafui/batchwizard | |||
16:05 | Understanding Autoregressive vs. Autoencoding Language Models https://python.plainenglish.io/understanding-autoregressive-vs-autoencoding-language-models-1203508794fa | |||
16:01 | Running LLMs Locally: Because Life’s Too Short for Cloud Computing https://medium.com/@dwikifkurniawan/running-llms-locally-because-lifes-too-short-for-cloud-computing-6327eb1eac03 | |||
15:53 | Benchmarking LLAMA 2 on Android: A Tale of Two Implementations https://medium.com/@srivastavahardik/benchmarking-llama-2-on-android-a-tale-of-two-implementations-35228d6ede9e | |||
15:08 | Can Private LLM Help You Solve Kubernetes Problems on the First Try? https://itnext.io/can-private-llm-help-you-solve-kubernetes-problems-on-the-first-try-346f185eb954 | |||
15:02 | Understanding Self-Attention: A Mathematical Perspective for Image Analysis https://medium.com/@dineshbafila/understanding-self-attention-a-mathematical-perspective-for-image-analysis-0862b30818de | |||
14:26 | What are LLMs and Explore the key differences between RAG and fine-tuning with examples https://medium.com/@uzairadamjee/what-are-llms-and-explore-the-key-differences-between-rag-and-fine-tuning-with-examples-4af3445c008c | |||
14:24 | Automating git diff, commit, and push https://medium.com/@csv610/automating-git-diff-commit-and-push-f06262b35509 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803