LLM News and Articles
Friday, 2024-09-06 | ||||
07:48 | Taming and training LLM Tokenization with BPE https://manu1992.medium.com/taming-and-training-llm-tokenization-with-bpe-fc11f774d2e8 | |||
07:37 | OLMoE-1B-7B and OLMoE-1B-7B-INSTRUCT Released: A Fully Open-Sourced Mixture-of-Experts LLM with 1B Active and 7B Total Parameters https://www.marktechpost.com/2024/09/06/olmoe-1b-7b-and-olmoe-1b-7b-instruct-released-a-fully-open-sourced-mixture-of-experts-llm-with-1b-active-and-7b-total-parameters/ | |||
07:28 | Successfully Replacing 34% of User Inquiries with GPT-4 AI Chat https://medium.com/@takamasa1222/successfully-replacing-34-of-user-inquiries-with-gpt-4-ai-chat-bfbfa79d6d85 | |||
07:28 | Beyond Chatbots: My Journey Automating Document Processing with AWS and LLMs https://medium.com/@alex-stolz/beyond-chatbots-my-journey-automating-document-processing-with-aws-and-llms-40b1005c8188 | |||
07:26 | A Review of LLM Cybersecurity Risks and How to Mitigate them https://medium.com/@AhmedF/a-review-of-llm-cybersecurity-risks-and-how-to-mitigate-them-5b5ec0c130dd | |||
07:26 | Comparative Analysis of LLM and Traditional Text Augmentation: Accuracy, Efficiency, and Cost-Effectiveness https://www.marktechpost.com/2024/09/06/comparative-analysis-of-llm-and-traditional-text-augmentation-accuracy-efficiency-and-cost-effectiveness/ | |||
07:18 | How to Install Airbyte Using Docker: A Step-by-Step Guide https://medium.com/@asakisakamoto02/how-to-install-airbyte-using-docker-a-step-by-step-guide-d0135368908c | |||
07:17 | Why Your Chatbot Is Underperforming: The Ultimate RAG Tier List https://medium.com/@lbq999/why-your-chatbot-is-underperforming-the-ultimate-rag-tier-list-01b4bfd3ae71 | |||
07:17 | Read this before you spend money on GenAI https://medium.com/@amir.alsbih/read-this-before-you-spend-money-on-genai-e748cae3d44e | |||
06:54 | Show HN: NFactorial AI – Perplexity for researching 240 companies from YC S24 https://ycs24.nfactorial.dev/ | |||
06:24 | How to Use Chat GPT 4.0 for Free: A Complete Guide 2024 https://medium.com/@isabelwashington_49837/how-to-use-chat-gpt-4-0-for-free-a-complete-guide-2024-b349b1b429f9 | |||
06:23 | Unlocking the Power of LangChain: Building Smarter Applications with Large Language Models https://pantheonmle.medium.com/unlocking-the-power-of-langchain-building-smarter-applications-with-large-language-models-ab38ca310d31 | |||
05:57 | Building a Database-Driven Chatbot with LangChain and OpenAI: A Practical Approach (Part 4… https://blog.gopenai.com/building-a-database-driven-chatbot-with-langchain-and-openai-a-practical-approach-part-4-e11355bbf345 | |||
05:45 | Claude 3 vs GPT 3.5: Features, Pricing, and Use Cases Review https://medium.com/@getanakin/claude-3-vs-gpt-3-5-features-pricing-and-use-cases-review-32b2c3cb4a50 | |||
05:39 | Investing with LLMs: Does it make cents? https://medium.com/mitb-for-all/investing-with-llms-does-it-make-cents-496ed6c87458 | |||
05:35 | How to Use Chat GPT API for Enhanced Conversational AI https://medium.com/@lisakim01/how-to-use-chat-gpt-api-for-enhanced-conversational-ai-a009c0fc1f88 | |||
05:29 | Reflection 70B: When Open Source 70B Model Beats Claude 3.5 Sonnet https://medium.com/@sebastianpetrus_65943/reflection-70b-when-open-source-70b-model-beats-claude-3-5-sonnet-cea6f9467ae5 | |||
04:44 | The Evolution of Llama: From Llama 1 to Llama 3.1 https://towardsdatascience.com/the-evolution-of-llama-from-llama-1-to-llama-3-1-13c4ebe96258 | |||
04:44 | Day 5: Ethical Considerations and Bias in LLMs https://medium.com/@nikhil16kulkarni/day-5-ethical-considerations-and-bias-in-llms-d3fc0139015e | |||
04:44 | Day 5: Ethical Considerations and Bias in LLMs https://blog.gopenai.com/day-5-ethical-considerations-and-bias-in-llms-d3fc0139015e | |||
04:25 | How to Leverage Chroma DB as a Vector Store in Langchain https://medium.com/@garysvenson09/how-to-leverage-chroma-db-as-a-vector-store-in-langchain-51bbd57a2fab | |||
04:22 | WDTA Releases an International Standard on LLM Security for Supply Chain https://medium.com/@wdtacademy/wdta-releases-an-international-standard-on-llm-security-for-supply-chain-18d26f08f5b0 | |||
04:03 | Web Crawling Capabilities with LLMs and Open-Source Python Library https://sahajgodhani777.medium.com/web-crawling-capabilities-with-llms-and-open-source-python-library-78cbd3b56f1a | |||
04:03 | Web Crawling Capabilities with LLMs and Open-Source Python Library https://ai.gopubby.com/web-crawling-capabilities-with-llms-and-open-source-python-library-78cbd3b56f1a | |||
03:40 | I dialed into the Princeton Workshop on Useful and Reliable Agents last week and absolutely loved… https://medium.com/@tonyqin/i-dialed-into-the-princeton-workshop-on-useful-and-reliable-agents-last-week-and-absolutely-loved-d5f17e2e01ce | |||
03:25 | A New Era in LLM Security: Understanding the Risks in Real-World LLM AI Systems https://medium.com/@jimwang3589/a-new-era-in-llm-security-understanding-the-risks-in-real-world-llm-ai-systems-f7eff25b54d1 | |||
03:18 | How to Determine Airbyte Cloud Pricing for Your Needs https://medium.com/@asakisakamoto02/how-to-determine-airbyte-cloud-pricing-for-your-needs-e426b830c0d5 | |||
03:11 | Friendli Container Part 2: Monitoring with Grafana https://medium.com/friendliai/friendli-container-part-2-monitoring-with-grafana-db8a9c4fc3f7 | |||
03:05 | Cracking the Code: How LLMs Are Changing the Way We Understand Code https://medium.com/@jimwang3589/cracking-the-code-how-llms-are-changing-the-way-we-understand-code-76ae69d1b12a | |||
02:58 | Friendli Container Part 1: Efficiently Serving LLMs On-Premise https://medium.com/friendliai/friendli-container-part-1-efficiently-serving-llms-on-premise-e8995a0f631c | |||
02:52 | LLM: How to balance the need for better accuracy without sacrificing computational efficiency? https://medium.com/@jimwang3589/llm-how-to-balance-the-need-for-better-accuracy-without-sacrificing-computational-efficiency-1f9bb69d2393 | |||
02:25 | Automating Prompt Engineering for LLM Workloads https://medium.com/@bijit211987/automating-prompt-engineering-for-llm-workloads-f4ea6295aa6b | |||
02:24 | How to Use ChatGPT-4 for Free: A Complete Guide 2024 https://medium.com/@isabelwashington_49837/how-to-use-chatgpt-4-for-free-a-complete-guide-2024-c8d370c76490 | |||
02:02 | How to make Generative AI reliable https://pub.towardsai.net/how-to-make-generative-ai-reliable-92ff23b0dc85 | |||
01:59 | Strategy and Roadmap to Improve or Rebuilt a Enterprises LLM https://medium.com/@jimwang3589/what-should-i-do-if-my-companys-llm-is-not-good-fa930260b5e1 | |||
01:45 | Claude 3 Opus vs GPT-4: A Comprehensive LLM Review https://medium.com/@getanakin/claude-3-opus-vs-gpt-4-a-comprehensive-llm-review-a83eb27e04dc | |||
01:38 | Yi-Coder Released by 01.AI: A Powerful Small-Scale Code LLM Series, Delivering Exceptional Performance in Code Generation, Editing, and Long-Context Comprehension https://www.marktechpost.com/2024/09/05/yi-coder-released-by-01-ai-a-powerful-small-scale-code-llm-series-delivering-exceptional-performance-in-code-generation-editing-and-long-context-comprehension/ | |||
01:35 | How to Use Calude API for Enhanced Data Management https://medium.com/@lisakim01/how-to-use-calude-api-for-enhanced-data-management-722a81609a75 | |||
00:36 | A Word, Please: Coffee-shop prompt stirs ChatGPT to brew up bland copy https://www.latimes.com/socal/daily-pilot/opinion/story/2024-04-09/a-word-please-coffee-shop-prompt-stirs-chatgpt-to-brew-up-bland-copy | |||
00:34 | LlamaIndex: A Revolution in Connected Knowledge https://medium.com/@yjg30737/llamaindex-a-revolution-in-connected-knowledge-9b821d66568f | |||
00:26 | How to Integrate ChatGLM3 with Langchain for Seamless AI https://medium.com/@garysvenson09/how-to-integrate-chatglm3-with-langchain-for-seamless-ai-000e425ad903 | |||
00:12 | Chains in LLM Deployment https://ogre51.medium.com/chains-in-llm-deployment-069684d6c8f5 | |||
Thursday, 2024-09-05 | ||||
23:35 | My Take On Large Language Models (LLMs) https://medium.com/@product.mgmt.blog/my-take-on-large-language-models-llms-c15d239bbcbe | |||
23:18 | How to Master AI Infrastructure and Operations Fundamentals https://medium.com/@asakisakamoto02/how-to-master-ai-infrastructure-and-operations-fundamentals-e1d889db4924 | |||
23:01 | What are the different transformers for LLMs like Bert, ChatGPT, and Google Flan T5? https://medium.com/@jimwang3589/what-are-the-different-transformers-for-llms-like-bert-chatgpt-and-google-flan-t5-2a52f4dd132f | |||
22:44 | What are the KPIs for LLM model training? https://medium.com/@jimwang3589/what-are-the-kpis-for-a-llm-model-training-7553e66d990c | |||
22:30 | On the ease of use for niche new languages https://agam.medium.com/on-the-ease-of-use-for-niche-new-languages-2754de7ea04c | |||
22:24 | Best 10 Free Coding GPT Tools for Developers in 2024 https://medium.com/@isabelwashington_49837/best-10-free-coding-gpt-tools-for-developers-in-2024-935bfff94722 | |||
22:23 | LongCite: training LLM models to generate fine-grained citations in Long-Context Question Answering https://medium.com/@techsachin/longcite-training-llm-models-to-generate-fine-grained-citations-in-long-context-question-answering-0575cc9ca4b2 | |||
22:18 | Agentic Framework for Enterprise Java Applications https://medium.com/@visrow/agentic-framework-for-enterprise-java-applications-2c74b60f3598 | |||
22:09 | OpenAI, Still Haunted by Its Chaotic Past, Is Trying to Grow Up https://www.nytimes.com/2024/09/03/technology/openai-chatgpt-revenue.html | |||
22:09 | What is RLHF and how to use it to train an LLM — Part 4 https://medium.com/@jimwang3589/what-is-rlhf-and-how-to-use-it-to-train-an-llm-part-4-1146228b74ef | |||
22:05 | Why RAG and LLMs Are the Future of Cloud Security and Compliance https://securends.medium.com/why-rag-and-llms-are-the-future-of-cloud-security-and-compliance-068e13d29e2b | |||
22:03 | CodeAssist AI https://medium.com/@girishwangikar/codeassist-ai-59984dcc3b40 | |||
22:00 | What is RLHF and how to use it to train an LLM — Part 3 https://medium.com/@jimwang3589/what-is-rlhf-and-how-to-use-it-to-train-an-llm-part-3-2be5c1e9e743 | |||
21:55 | Exploring GPT4All and Langchain: A Step-by-Step Guide to Building an AI Assistant bot locally or… https://medium.com/@monsuralirana/exploring-gpt4all-and-langchain-a-step-by-step-guide-to-building-an-ai-assistant-bot-locally-or-571a54fda1ce | |||
21:45 | Claude 3 Opus vs GPT-4: In-Depth Review and Comparison https://medium.com/@getanakin/claude-3-opus-vs-gpt-4-in-depth-review-and-comparison-1107cc82e856 | |||
21:35 | How to Use AssemblyAI API for Accurate Transcription https://medium.com/@lisakim01/how-to-use-assemblyai-api-for-accurate-transcription-42075c015ffc | |||
21:31 | Small Language Models (SLMs) vs. Large Language Models (LLMs): Which AI is Better for Education? https://medium.com/kinomoto-mag/small-language-models-slms-vs-large-language-models-llms-which-ai-is-better-for-education-4c831169a4f3 | |||
21:17 | Social Media Manipulation in the Era of AI https://medium.com/rand-corporation/social-media-manipulation-in-the-era-of-ai-e8d5ab15f0e6 | |||
20:41 | The AI Awakening https://medium.com/@aleksmilanov/the-ai-awakening-ab87546abd06 | |||
20:30 | RaspberryPI, make me a coffee! https://medium.com/illumination/raspberrypi-make-me-a-coffee-11ecc3792ce7 | |||
20:25 | How to Master Character Splitting Techniques in LangChain https://medium.com/@garysvenson09/how-to-master-character-splitting-techniques-in-langchain-843cd50aa479 | |||
20:23 | Why Rig? 5 Compelling Reasons to Use Rig for Your Next LLM Project https://medium.com/@0thTachi/why-rig-5-compelling-reasons-to-use-rig-for-your-next-llm-project-9d4889b16bd3 | |||
20:01 | Reliable Agentic RAG with LLM Trustworthiness Estimates https://pub.towardsai.net/reliable-agentic-rag-with-llm-trustworthiness-estimates-c488fb1bd116 | |||
19:35 | AI cognition: Do LLMs think fast or slow? https://medium.com/@alisontomail/ai-cognition-do-llms-think-fast-or-slow-1fd3f1ab1f0f | |||
19:26 | Looking for a Prompt Engineer https://medium.com/@soeren.bey/looking-for-a-prompt-engineer-9066f60bdc6b | |||
19:25 | Suche Prompt-Engineerin https://medium.com/@soeren.bey/suche-prompt-engineerin-d13da17d88f5 | |||
19:18 | How to Navigate the Agent Universe for Maximum Success https://medium.com/@asakisakamoto02/how-to-navigate-the-agent-universe-for-maximum-success-737e99c26d24 | |||
19:17 | Running Phi-3/Mistral 7B LLMs on Raspberry Pi 5: A Step-by-Step Guide https://medium.com/@vadikus/running-phi-3-mistral-7b-llms-on-raspberry-pi-5-a-step-by-step-guide-185e8102e35b | |||
19:10 | A Llama 70B finetune that has reflection baked into it's weights https://huggingface.co/mattshumer/Reflection-70B | |||
19:09 | World’s first convincing AI https://amitnikhade.medium.com/worlds-first-convincing-ai-c6c08cb10e0b | |||
18:51 | An Iterative Approach to Generative Prompts: Fostering Creativity and Collaboration in AI… https://medium.com/@steve.szatkowski/an-iterative-approach-to-generative-prompts-fostering-creativity-and-collaboration-in-ai-13c05910aa23 | |||
18:25 | How to Use AI Without Limitations Like ChatGPT for Free https://medium.com/@isabelwashington_49837/how-to-use-ai-without-limitations-like-chatgpt-for-free-100abe94187e | |||
18:06 | How we can build AI calling agent with latency 500 ms — 1000 ms https://medium.com/@mexasol/how-we-can-build-ai-calling-agent-with-latency-500-ms-1000-ms-9b6f93f95d83 | |||
18:02 | How to Develop an AI Summarizer and Chatbot Platform with Streamlit https://pub.towardsai.net/how-to-develop-an-ai-summarizer-and-chatbot-platform-with-streamlit-5dc0f5a3b089 | |||
18:02 | The Rise of Fast Language: How LLMs will tell our stories https://k-woodard.medium.com/the-rise-of-fast-language-how-llms-will-tell-our-stories-056994688f40 | |||
18:01 | AI: Your Best Friend or Worst Enemy https://medium.com/@steve.szatkowski/ai-your-best-friend-or-worst-enemy-1c4c0ad6cb50 | |||
18:00 | How I built my own Copilot on VSCode for FREE? https://ai.gopubby.com/how-i-built-my-own-copilot-on-vscode-for-free-e59e20a95b6f | |||
17:59 | The LLM Boom: How Large Language Models Are Shaping the Future of AI https://medium.com/@heenaatta19/the-llm-boom-how-large-language-models-are-shaping-the-future-of-ai-792d49b7c866 | |||
17:45 | Claude 3 vs Sonnet: A Review of LLMs, Pricing, and Use Cases https://medium.com/@getanakin/claude-3-vs-sonnet-a-review-of-llms-pricing-and-use-cases-5bb4ac2383a5 | |||
17:36 | How to Use an API Provider for Seamless Integration https://medium.com/@lisakim01/how-to-use-an-api-provider-for-seamless-integration-d14bb25ef57b | |||
17:23 | OpenAI moved ChatGPT from Next.js to remix https://twitter.com/wesbos/status/1831485259130777795 | |||
17:17 | CUDA-Free Inference for LLMs https://pytorch.org/blog/cuda-free-inference-for-llms/ | |||
16:41 | Optimizing Market Data: How GenAI Enabled Time-Series Innovations for TICK Data in Snowflake https://medium.com/@cnaps/optimizing-market-data-how-genai-enabled-time-series-innovations-for-tick-data-in-snowflake-12f4a5557d0f | |||
16:38 | Leaked System Prompts from V0, Cursor, Claude, Perplexity, ChatGPT https://twitter.com/lucasmrdt_/status/1831278426742743118 | |||
16:27 | Supercharge Your LLM Training(30x Speed Boost) Seems Too Good to Be True, Right? https://medium.com/@nikhilsonone1234/supercharge-your-llm-training-30x-speed-boost-seems-too-good-to-be-true-right-523923393658 | |||
16:26 | How to Load TXT Files with UnstructuredFileLoader in LangChain https://medium.com/@garysvenson09/how-to-load-txt-files-with-unstructuredfileloader-in-langchain-c706d6329ec7 | |||
16:23 | From Solo to Symphony: The Art of Blending Multiple AI Models https://medium.com/@an1rudh7/from-solo-to-symphony-the-art-of-blending-multiple-ai-models-2a8ce52ee69d | |||
16:01 | Create an Instruction Dataset From scratch. https://pub.towardsai.net/create-an-instruction-dataset-from-scratch-b3bdd3c75a1a | |||
15:53 | LangChain in Chains #38: Function Calling https://towardsdev.com/langchain-in-chains-38-function-calling-b7e9de9ccab1 | |||
15:45 | Strengths And Weaknesses of Large Language Models (Short Version) https://medium.com/@2davidspeakman/strengths-and-weaknesses-of-large-language-models-97a7654a178d | |||
15:45 | LLM Selection Criteria for the Enterprise https://medium.com/@manavg/llm-selection-criteria-for-the-enterprise-8ae6b3b87193 | |||
15:19 | José Valim on ChatGPT's new UI latency woes and client-side frameworks https://twitter.com/josevalim/status/1831698927944360367 | |||
15:18 | How to Fix Activity Heartbeat Timeout Issues Easily https://medium.com/@asakisakamoto02/how-to-fix-activity-heartbeat-timeout-issues-easily-a44eb308507e | |||
15:13 | The 'Just Right' Anthropic Coincidences of Our Goldilocks Universe III (2022) https://www.magiscenter.com/blog/the-just-right-anthropic-coincidences-of-our-goldilocks-universe-part-iii | |||
15:04 | Writing fan fiction with LLMs https://medium.com/@sausheong/writing-fan-fiction-with-llms-4a76dc6744ba | |||
14:40 | What are embeddings? https://parkerrobert.medium.com/what-are-embeddings-d29dec288a73 | |||
14:38 | Logsumexp trick and Flash attention- Part 2 https://neerajku.medium.com/logsumexp-trick-and-flash-attention-part-2-9e2d55cf1610 | |||
14:36 | #39 Top 5 ML Algorithms, Graph RAG, & Tutorial for Creating an Agentic Multimodal Chatbot. https://pub.towardsai.net/39-top-5-ml-algorithms-graph-rag-tutorial-for-creating-an-agentic-multimodal-chatbot-89419d1e8ef0 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803