LLM News and Articles
Thursday, 2024-09-26 | ||||
08:42 | Why Scaling RAGs For Production Is So Hard? https://medium.com/aiguys/why-scaling-rags-for-production-is-so-hard-a2f540785e97 | |||
08:34 | OpenAI to Become For-Profit Company https://www.wsj.com/tech/ai/openai-chief-technology-officer-resigns-7a8b4639 | |||
08:34 | OpenAI to become for-profit company https://www.reuters.com/technology/artificial-intelligence/openai-remove-non-profit-control-give-sam-altman-equity-sources-say-2024-09-25/ | |||
08:26 | Exploring RAG-Fusion: A New Approach to Retrieval-Augmented Generation and Implementation https://medium.com/@mexasol/exploring-rag-fusion-a-new-approach-to-retrieval-augmented-generation-and-implementation-0bdf3d978752 | |||
08:25 | How to Use RecursiveCharacterTextSplitter in LangChain https://medium.com/@garysvenson09/how-to-use-recursivecharactertextsplitter-in-langchain-23bcb0448fca | |||
07:41 | A new Llama-based model for efficient large-scale voice generation https://github.com/OpenT2S/LlamaVoice | |||
07:31 | Using AI in your IDE to work with open-source code bases https://ai.gopubby.com/using-ai-in-your-ide-to-work-with-open-source-code-bases-75a098010182 | |||
07:18 | How to Find Your Supabase Database URL Easily https://medium.com/@asakisakamoto02/how-to-find-your-supabase-database-url-easily-9170b5b0b203 | |||
07:16 | AI at Meta Connect 2024 https://augmentedstartups.medium.com/ai-at-meta-connect-2024-9c31b168b578 | |||
07:16 | How to Develop Powerful AI Models for Successful Marketing Campaigns https://angila.medium.com/how-to-develop-powerful-ai-models-for-successful-marketing-campaigns-d2857249deb5 | |||
06:51 | Building the Byte Pair Encoding Algorithm: A Hands-On Implementation Guide https://prachi-gopalani.medium.com/building-the-byte-pair-encoding-algorithm-a-hands-on-implementation-guide-7f212f033353 | |||
06:51 | Building the Byte Pair Encoding Algorithm: A Hands-On Implementation Guide https://medium.com/analytics-vidhya/building-the-byte-pair-encoding-algorithm-a-hands-on-implementation-guide-7f212f033353 | |||
06:36 | Evaluating Large Language Models: Techniques, Challenges, and Best Practices https://medium.com/@prag-matic/evaluating-large-language-models-techniques-challenges-and-best-practices-8b3f15f13253 | |||
06:36 | Large Action Models(LAM): Ushering in a New Era of AI Autonomy https://priyalwalpita.medium.com/large-action-models-lam-ushering-in-a-new-era-of-ai-autonomy-97014374eae5 | |||
06:25 | HUGE NEWS! …Llama 3.2 is here! https://medium.com/@shravankoninti/huge-news-llama-3-2-is-here-eb241b83bd23 | |||
06:16 | How to Use API Led Integration for Seamless Connectivity https://medium.com/@tayloroakley/how-to-use-api-led-integration-for-seamless-connectivity-fac0657b520b | |||
06:13 | Meta Llama 3.2: Everything you need to know https://medium.com/@shirleyhan3/meta-llama-3-2-everything-you-need-to-know-13c47729475c | |||
05:59 | Sharaku Style: New System Prompt for Advanced Voice Mode https://medium.com/@sharakusatoh/sharaku-style-new-system-prompt-for-advanced-voice-mode-22f2bcab7e4b | |||
05:53 | Limitations of text embeddings in RAG applications https://medium.com/neo4j/limitations-of-text-embeddings-in-rag-applications-b060020b543b | |||
05:50 | Use Llama 3.1 as Your Private LLM https://awstip.com/use-llama-3-1-as-your-private-llm-c2330b0435b5 | |||
05:45 | DALL-E Pricing, Benchmarks, and Usage: A Comprehensive Review https://medium.com/@getanakin/dall-e-pricing-benchmarks-and-usage-a-comprehensive-review-6ca387cc8e8b | |||
05:01 | Small Language Model (SLM) Efficiency, Performance & Potential https://cobusgreyling.medium.com/small-language-model-slm-efficiency-performance-potential-ed59c4d48ce9 | |||
04:31 | Build Your First Intelligent Agent: A Simple Q&A Bot https://arsanatl.medium.com/build-your-first-intelligent-agent-a-simple-q-a-bot-b41113d12155 | |||
04:27 | Teacher caught students using ChatGPT on their first assignment. Debate ensues https://www.businessinsider.com/students-caught-using-chatgpt-ai-assignment-teachers-debate-2024-9 | |||
04:25 | How to Serve Langchain Applications with Ray Tutorial https://medium.com/@garysvenson09/how-to-serve-langchain-applications-with-ray-tutorial-78fa136c712a | |||
03:32 | OpenAI's chief research officer has left following CTO Mira Murati's exit https://techcrunch.com/2024/09/25/openais-chief-research-officer-has-left/ | |||
03:18 | How to Handle Airflow Queue Timeout Issues Effectively https://medium.com/@asakisakamoto02/how-to-handle-airflow-queue-timeout-issues-effectively-c707a5a4deb5 | |||
03:18 | Meta has launched the large language model Llama 3.2 https://rafaelrisala.medium.com/meta-has-launched-the-large-language-model-llama-3-2-9f91fc6f71c8 | |||
03:13 | How Generative AI is Revolutionising Film and Music https://medium.com/@researchgraph/how-generative-ai-is-revolutionising-film-and-music-2a622bd14fad | |||
03:07 | LLM Fine-tuning — FAQs https://towardsdatascience.com/llm-fine-tuning-faqs-200442827c99 | |||
02:30 | How To Efficiently Serve Today’s Large Language Models https://medium.com/openvino-toolkit/how-to-efficiently-serve-todays-large-language-models-b3f1e8d33fdf | |||
02:16 | How to Use Allwhere for Your Startup Success https://medium.com/@tayloroakley/how-to-use-allwhere-for-your-startup-success-4b8638ff1682 | |||
02:12 | OpenAI to Become For-Profit Company https://www.theverge.com/2024/9/25/24254535/openai-non-profit-for-profit-sam-altman-investment | |||
01:49 | LLM-interpolate: Interpolate between embedding points with LLM https://github.com/vagos/llm-interpolate | |||
01:45 | Comprehensive Review of DALL-E 3 Pricing and Usage Options https://medium.com/@getanakin/comprehensive-review-of-dall-e-3-pricing-and-usage-options-f508ab83865c | |||
01:43 | Revealing ChatGPT: The Not-So-Mysterious Inner Workings of an AI Chatbot https://medium.com/@arya.amarnath/revealing-chatgpt-the-not-so-mysterious-inner-workings-of-an-ai-chatbot-7b4e3943edc6 | |||
01:37 | Barret Zoph, OpenAI VP (Post-Training), Resigns https://twitter.com/barret_zoph/status/1839095143397515452 | |||
01:27 | OpenAI to remove non-profit control and give Sam Altman equity https://finance.yahoo.com/news/exclusive-openai-remove-non-profit-201413475.html | |||
01:26 | OpenAI Discusses Giving Altman 7% Stake in For-Profit Shift https://www.bloomberg.com/news/articles/2024-09-25/openai-cto-mira-murati-says-she-will-leave-the-company | |||
01:16 | HN Rankings for OpenAI's Restructuring https://hnrankings.info/41651548/ | |||
00:56 | Chief Research Officer at OpenAI Quits https://twitter.com/bobmcgrewai/status/1839099787423134051 | |||
00:25 | How to Build a RAGApp Using LangChain in Simple Steps https://medium.com/@garysvenson09/how-to-build-a-ragapp-using-langchain-in-simple-steps-f0e8deabd0f2 | |||
00:08 | Sam Altman's response to Mira leaving OpenAI https://twitter.com/sama/status/1839093415226524114 | |||
00:05 | How to run Llama 3.2 1B and 3B on your device? https://medium.com/@best_AI/how-to-run-llama-3-2-1b-and-3b-on-your-device-f5ab82cedea4 | |||
Wednesday, 2024-09-25 | ||||
23:50 | Statistical Fallacies and Large Language Models: A Case Study with Simpson’s Paradox https://medium.com/@joshuabroyde/statistical-fallacies-and-large-language-models-a-case-study-with-simpsons-paradox-fd07cd3552c4 | |||
23:48 | Unlocking Customer Insights: LLM Function Calling for Data Transformation https://jmlbeaujour.medium.com/unlocking-customer-insights-llm-function-calling-for-data-transformation-ece58301015d | |||
23:46 | Google NotebookLM, AI discussing AI with itself. https://pub.aimind.so/google-notebooklm-ai-discussing-ai-with-itself-d3f6b19250d1 | |||
23:45 | Analyzing Tesla Customer Reviews: Insights Unlocked https://jmlbeaujour.medium.com/analyzing-tesla-customer-reviews-insights-unlocked-1d4db6c1816d | |||
23:42 | Sam Altman reportedly poised to get equity in OpenAI https://techcrunch.com/2024/09/25/sam-altman-reportedly-poised-to-get-equity-in-openai-for-the-first-time/ | |||
23:19 | How to Specify Properties to Return in Weaviate https://medium.com/@asakisakamoto02/how-to-specify-properties-to-return-in-weaviate-8c3a6e789999 | |||
22:57 | Attacks, Defenses, and Evaluations for LLMs: A Comprehensive Overview https://medium.com/@evog/attacks-defenses-and-evaluations-for-llms-a-comprehensive-overview-8b06a1d75f70 | |||
22:45 | AI on AI https://medium.com/@osandvik/ai-on-ai-a14848763663 | |||
22:34 | Your GenAI Project is BLIND Without a Performance Evaluation Framework https://medium.com/the-business-of-ai/your-genai-project-is-blind-without-a-performance-evaluation-framework-dfe944d10919 | |||
22:29 | Incorporating LLMs with data visualizations https://medium.com/@pYdeas/incorporating-llms-with-data-visualizations-dc469486607b | |||
22:23 | Llama 3.2: The Next Generation of Lightweight, Instruction-Tuned Language Models: A Hands-On… https://medium.com/@monsuralirana/llama-3-2-the-next-generation-of-lightweight-instruction-tuned-language-models-a-hands-on-9bca07c8af1d | |||
22:17 | How to Use Unified API Examples for Seamless Integration https://medium.com/@tayloroakley/how-to-use-unified-api-examples-for-seamless-integration-adf14140e9b7 | |||
22:07 | Supercharging Discovery in Search with LLMs https://tech.instacart.com/supercharging-discovery-in-search-with-llms-556c585d4720 | |||
22:04 | OpenAI CTO Mira Murati Resigns https://thehill.com/policy/technology/4899500-openai-cto-resigns-miramurati/ | |||
22:01 | Tracing a LLM Agent with LangSmith https://pub.towardsai.net/tracing-a-llm-agent-with-langsmith-a81975634555 | |||
21:59 | Recommended Reading: How I Use “AI” by Nicholas Carlini https://lfomendes.medium.com/recommended-reading-how-i-use-ai-by-nicholas-carlini-83d959744b19 | |||
21:57 | Gemma 2 2B learns how to tutor in AI/ML https://medium.com/@lucamassaron/gemma-2-2b-learns-how-to-tutor-in-ai-ml-0b149a6e48ae | |||
21:51 | LLM Neuroplasticity or Transfer Learning https://alagraphy.medium.com/llm-neuroplasticity-or-transfer-learning-b43a32155041 | |||
21:45 | Comprehensive Review of DALL·E 2 Pricing and Usage Options https://medium.com/@getanakin/comprehensive-review-of-dall-e-2-pricing-and-usage-options-c3fd200ebcea | |||
21:05 | Install llama3.2 on your computer https://medium.com/@mahernaija/install-llama3-2-on-your-computer-0e8413ab0270 | |||
20:55 | Run web services on HPC? Stupid? https://dirk-petersen.medium.com/run-web-services-on-hpc-stupid-63e208008da8 | |||
20:33 | LLAMA 3.2 Models: 1B is the New 8B https://ankitnitjsr13.medium.com/llama-3-2-models-1b-is-the-new-8b-42734a19872b | |||
20:26 | How to Create a RAG Jupyter Notebook with LangChain https://medium.com/@garysvenson09/how-to-create-a-rag-jupyter-notebook-with-langchain-e5f48c2e4ecf | |||
20:20 | Prompt Engineering : Communication with AI https://medium.com/illumination/what-is-prompt-engineering-49b537fffb5a | |||
20:18 | Some things to know about Large scale language Model https://earthkhan.medium.com/some-things-to-know-about-large-scale-language-model-e6ce747a8803 | |||
20:13 | Altman reportedly asks Biden to back a slew of multi-gigawatt AI datacenters https://www.theregister.com/2024/09/25/altman_5gw_dc/ | |||
20:09 | Llama 3.2: Pushing the Boundaries of Visual-Language AI https://ankitnitjsr13.medium.com/llama-3-2-pushing-the-boundaries-of-visual-language-ai-c2b7849b894e | |||
20:05 | Molmo https://blog.victorgevers.com/molmo-95b41ae7b5aa | |||
20:05 | From Articles to Podcast: Powered by AI! https://medium.com/@joacod/from-articles-to-podcast-powered-by-ai-4195e066177b | |||
20:02 | Claude AI: Natural Language Understanding & Gen https://medium.com/@tomskiecke/claude-ai-natural-language-understanding-gen-30f40f1e77dc | |||
19:54 | Understanding and Attacking Meta’s Chameleon Model https://medium.com/@maxwbuckley/understanding-and-attacking-metas-chameleon-model-bdcc4a4192d7 | |||
19:51 | OpenAI CTO Mira Murati is leaving https://www.theverge.com/2024/9/25/24254431/openai-cto-mira-murati-leaving | |||
19:49 | The Gandalf Quiz: A Look at How to Trick Language Models https://rahulrpandya.medium.com/the-gandalf-quiz-a-look-at-how-to-trick-language-models-2608f5124f0e | |||
19:48 | OpenAI CTO Mira Murati says she's leaving the company https://techcrunch.com/2024/09/25/openai-cto-mira-murati-says-shes-leaving-the-company/ | |||
19:46 | Llama 3.2 1B and 3B on-device models https://twitter.com/shishirpatil_/status/1839007216407556467 | |||
19:40 | OpenAI CTO Mira Murati announces she's leaving the company https://www.cnbc.com/2024/09/25/openai-cto-mira-murati-announces-shes-leaving-the-company.html | |||
19:39 | OpenAI's chief technology officer Mira Murati to leave https://www.ft.com/content/78b7e7a7-7428-4c5e-bfa2-0921c9d6cd25 | |||
19:35 | Mira Murati leaves OpenAI https://twitter.com/miramurati/status/1839025700009030027 | |||
19:29 | Entenda de uma vez por todas o que são Tokens em GenAI https://nelsonfrugeri-tech.medium.com/entenda-de-uma-vez-por-todas-o-que-s%C3%A3o-tokens-em-genai-d6aaa5bb9595 | |||
19:29 | PromSec: An AI Algorithm for Prompt Optimization for Secure and Functioning Code Generation Using LLM https://www.marktechpost.com/2024/09/25/promsec-an-ai-algorithm-for-prompt-optimization-for-secure-and-functioning-code-generation-using-llm/ | |||
19:28 | Understanding GPTs: A Deep Dive for Beginners https://medium.com/@toaswink/understanding-gpts-a-deep-dive-for-beginners-63c5771f73ec | |||
19:19 | How to Fetch 10 Weaviate Objects with Query in Detail https://medium.com/@asakisakamoto02/how-to-fetch-10-weaviate-objects-with-query-in-detail-86b2f09da6a3 | |||
19:10 | Efficient Distributed LLM serving https://medium.com/@sergii.ivakhno/efficient-distributed-llm-serving-9ac9506bb9c5 | |||
19:07 | Sustainable AI: Enhancing LLM Efficiency Through Sparsity https://medium.com/@karthikhubli/sustainable-ai-enhancing-llm-efficiency-through-sparsity-f42076d09ab6 | |||
18:55 | Top 30 LLM Interview Questions and Answers for 2024 https://medium.com/@girimanaskumar1998/top-30-llm-interview-questions-and-answers-for-2024-42e8744277ae | |||
18:52 | Real-Time Analytics: Weekly Roundup September 25, 2024 https://medium.com/rtinsights/real-time-analytics-weekly-roundup-september-25-2024-ee98578085f7 | |||
18:43 | 12 LLM Projects For All Levels https://medium.com/@girimanaskumar1998/12-llm-projects-for-all-levels-f48a0eeb7e85 | |||
18:38 | Reproducing GPT-2 (124M): A Deep Dive into Transformer Architecture and Optimization https://medium.com/@shenxiaoyue.study/reproducing-gpt-2-124m-a-deep-dive-into-transformer-architecture-and-optimization-12d03057c60a | |||
18:24 | Talking about anything https://medium.com/@Halfofthesky/talking-about-anything-b51fa9c17901 | |||
18:24 | Llama 3.2: Lightweight models for edge devices https://twitter.com/AIatMeta/status/1838993953502515702 | |||
18:23 | Llama 3.2 https://huggingface.co/collections/meta-llama/llama-32-66f448ffc8c32f949b04c8cf | |||
18:17 | How to Use LLM Powered Agents for Workflow Automation https://medium.com/@tayloroakley/how-to-use-llm-powered-agents-for-workflow-automation-b7f635d06bdd | |||
18:07 | Large Language Model Quantization: Does size matter? https://medium.com/@mojo885/large-language-model-quantization-does-size-matter-29e072375209 | |||
17:55 | From Rags to Rag Fusions https://medium.com/@alexhernandez_67007/from-rags-to-rag-fusions-900d967ec187 | |||
17:50 | Llama 3.2 Release https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md | |||
17:46 | DALL-E 3 Pricing, Benchmarks, and Usage Guide Insights https://medium.com/@getanakin/dall-e-3-pricing-benchmarks-and-usage-guide-insights-f3debd0ac13f |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803