LLM News and Articles
Wednesday, 2024-09-04 | ||||
10:01 | LLMs sind datenschutztechnisch wie Datenbanken zu behandeln. https://martinwelker.medium.com/llms-sind-datenschutztechnisch-wie-datenbanken-zu-behandeln-e14378cf54e4 | |||
09:43 | Is Claude 3.5 Sonnet Getting Dumber? You Might Not Be Hallucinating https://medium.com/@sebastianpetrus_65943/is-claude-3-5-sonnet-getting-dumber-you-might-not-be-hallucinating-a85cf1b9f884 | |||
09:36 | I Tried These 10 AI Content Writing Tools, and Here is My Review https://naomiclarkson0.medium.com/i-tried-these-10-ai-content-writing-tools-and-here-is-my-review-65bed94f45ac | |||
09:32 | Master 10 Top Negative Prompts: Examples and Develop Guide https://medium.com/@marketing_novita.ai/master-10-top-negative-prompts-examples-and-develop-guide-3a22791aee30 | |||
09:15 | How To Integrate Firecrawl With Langchain For Web Scraping https://medium.com/@sebastianpetrus_65943/how-to-integrate-firecrawl-with-langchain-for-web-scraping-9344d4df75f1 | |||
08:53 | What's Ahead for OpenAI? Project Strawberry, Orion, and GPT Next https://digitalcurrencyresearch.io/2024/09/04/whats-ahead-for-openai-project-strawberry-orion-and-gpt-next/ | |||
08:38 | Title: Harnessing the Power of Gemini’s Long Context: An In-Depth Exploration of 10 Groundbreaking… https://medium.com/@aagamshah0812/title-harnessing-the-power-of-geminis-long-context-an-in-depth-exploration-of-10-groundbreaking-498edcbcbe25 | |||
08:31 | LLM for code generation: a scalable pipeline to gather SFT data https://medium.com/toloka/llm-for-code-generation-a-scalable-pipeline-to-gather-sft-data-60443d30dabb | |||
08:28 | Top 10 RAG Frameworks Github Repos 2024 https://medium.com/@sebastianpetrus_65943/top-10-rag-frameworks-github-repos-2024-12b2a81f4a49 | |||
08:15 | Node.js — An Introduction to the npm Package Manager https://medium.com/@andy1729/node-js-an-introduction-to-the-npm-package-manager-614651e42fb4 | |||
08:15 | Three Steps to Create Synthetic Data for LLM Training Using Llama 3.1 405B https://medium.com/@sebastianpetrus_65943/three-steps-to-create-synthetic-data-for-llm-training-using-llama-3-1-405b-6a6e92d76b48 | |||
08:11 | Where to Use Llama 3.1 405B Base Model via API https://medium.com/@sebastianpetrus_65943/where-to-use-llama-3-1-405b-base-model-via-api-41c9f91f862a | |||
08:04 | Standardizing Cloud Deployment for RAG | Accelerating AI Adoption with Blueprints https://medium.com/@davidbenshabat/standardizing-cloud-deployment-for-rag-accelerating-ai-adoption-with-blueprints-20829d5591b1 | |||
07:46 | Securing Large Language models: A Deep Dive into Common Attack Vectors https://medium.com/@bassonrichard/securing-large-language-models-a-deep-dive-into-common-attack-vectors-673c1e6435ee | |||
07:21 | Build a Financial Analyst Chatbot with RAG: from Scraping to Chatbot Q&A https://medium.com/@theophilusnathantanudjaja/build-a-financial-analyst-chatbot-with-rag-from-scraping-to-chatbot-q-a-a9fe423d1846 | |||
07:21 | Paper Review: Agentic Retrieval-Augmented Generation for Time Series Analysis https://artgor.medium.com/paper-review-agentic-retrieval-augmented-generation-for-time-series-analysis-9c1eadd29a1a | |||
07:19 | Vistara and Air India Merger: What You Need to Know https://medium.com/@andy1729/vistara-and-air-india-merger-what-you-need-to-know-7fe54373ccc0 | |||
07:02 | Solving Math Problems with LLMs https://medium.com/@arturgrygorian3/solving-math-problems-with-llms-89b966e2d24c | |||
06:55 | Knowledge graphs // AI reasoning improved https://sbagency.medium.com/knowledge-graphs-reasoning-improved-9cf76d2546f9 | |||
06:51 | What’s an AI like ChatGPT but Has No Restrictions? (How to Uncensor LLMs) https://medium.com/@ritafsanchez/whats-an-ai-like-chatgpt-but-has-no-restrictions-how-to-uncensor-llms-ae39da922c99 | |||
06:45 | How to Use GraphRAG in LlamaIndex (Step-by-Step Guide) https://medium.com/@tayloroakley/how-to-use-graphrag-in-llamaindex-step-by-step-guide-468cee61cb56 | |||
06:44 | How to Run Phi-3.5 Locally on Your Laptop (2 Methods) https://medium.com/@tayloroakley/how-to-run-phi-3-5-locally-on-your-laptop-2-methods-a78b03dcfa48 | |||
06:42 | Mistral Large 2 vs Llama 405B vs GPT-4 vs Claude 3.5 Sonnet: A Complete Comparision https://medium.com/@tayloroakley/mistral-large-2-vs-llama-405b-vs-gpt-4-vs-claude-3-5-sonnet-a-complete-comparision-f9d56148e7b8 | |||
06:42 | Llama 3.1 Context Window, Tokens, Explained https://medium.com/@tayloroakley/llama-3-1-context-window-tokens-explained-a7f1d433fafe | |||
06:32 | Costruire un LLM in locale con Streamlit e Ollama (Llama3) https://medium.com/@lumenn.blog/costruire-un-llm-in-locale-con-streamlit-e-ollama-llama3-be2706ca1eb0 | |||
05:33 | Critic-CoT: A Novel Framework Enhancing Self-Critique and Reasoning Capabilities in Large Language Models for Improved AI Accuracy and Reliability https://www.marktechpost.com/2024/09/03/critic-cot-a-novel-framework-enhancing-self-critique-and-reasoning-capabilities-in-large-language-models-for-improved-ai-accuracy-and-reliability/ | |||
05:18 | How I Used Clustering to Improve Chunking and Build Better RAGs https://towardsdatascience.com/improving-rag-chunking-with-clustering-03c1cf41f1cd | |||
05:15 | Introduction to Generative AI and Building a Chatbot Agent with Vertex AI https://generativeai.pub/introduction-to-generative-ai-and-building-a-chatbot-agent-with-vertex-ai-48e3100a7fdf | |||
05:04 | YAML vs JSON — Best Format for Astro, React, AI Projects & Developers Guide Part 1 https://medium.com/@sasserenterprises/yaml-vs-json-best-format-for-astro-react-ai-projects-developers-guide-part-1-c7c1405ace57 | |||
04:20 | Integrating python app with large language model https://medium.com/@abdul.arfan/integrating-python-app-with-large-language-model-431c3506f43e | |||
04:06 | Large Language Models (LLMs) https://medium.com/@vijaya.sannapa/large-language-models-llms-a35b9aa04dd3 | |||
04:02 | Unlock Immediate Access to Llama 3 on Groq Using These Strategies https://medium.com/@erkajalkumari/unlock-immediate-access-to-llama-3-on-groq-using-these-strategies-dbd8a7ebdd19 | |||
03:23 | The LLAMA run https://medium.com/@tejeswar_79802/the-llama-run-c9d0e016ebe8 | |||
03:09 | Building my first RAG App https://chinsj.medium.com/building-my-first-rag-app-5a699f1ee7c6 | |||
02:13 | DSPy: Revolutionising AI Application Development with Language Models https://codescrum.medium.com/dspy-revolutionising-ai-application-development-with-language-models-9e308e9db3aa | |||
01:46 | OpenAI, Adobe and Microsoft back California bill requiring AI content watermarks https://techcrunch.com/2024/08/26/openai-adobe-microsoft-support-california-bill-requiring-watermarks-on-ai-content/ | |||
01:44 | I accidentally bought an AI-generated book https://sarah-packowski.medium.com/i-accidentally-bought-an-ai-generated-book-73a2db65500a | |||
01:14 | How to build an autonomous news Generator with AI using Fluvio https://medium.com/@vincentlee007/how-to-build-an-autonomous-news-generator-with-ai-using-fluvio-a8f3e592f6db | |||
00:00 | Hugging Face partners with TruffleHog to Scan for Secrets https://huggingface.co/blog/trufflesecurity-partnership | |||
Tuesday, 2024-09-03 | ||||
23:41 | Fleak’s API Versioning: The Secret to Microservices Efficiency https://medium.com/@fleak.ai/fleaks-api-versioning-the-secret-to-microservices-efficiency-07ee51a04709 | |||
23:41 | OpenAI and Anthropic agree to send models to US Government for safety evaluation https://venturebeat.com/ai/openai-and-anthropic-agree-to-send-models-to-us-government-for-safety-evaluations/ | |||
23:40 | Maximize Your AI Performance: Why Compound Workflows Are the Future https://medium.com/@fleak.ai/maximize-your-ai-performance-why-compound-workflows-are-the-future-d350fb9e243b | |||
23:37 | Boost Data Processing Efficiency with SQL and LLM Integration https://medium.com/@fleak.ai/boost-data-processing-efficiency-with-sql-and-llm-integration-a60fe7aa4d75 | |||
23:32 | Advancing Document Summarization https://medium.com/@girishwangikar/advancing-document-summarization-6f6a24f2fbb0 | |||
23:30 | What is Fleak? https://medium.com/@fleak.ai/what-is-fleak-3df7ac071e7f | |||
22:58 | In Defence Of AI Writing https://medium.com/@impure/in-defence-of-ai-writing-f88ed1f86309 | |||
22:43 | Cracking the Code: How Adversarial Attacks Manipulate AI Language Models https://saksheepatil05.medium.com/cracking-the-code-how-adversarial-attacks-manipulate-ai-language-models-239620395e58 | |||
22:01 | Applications of Multimodal Large Language Models in Personalized Healthcare https://pub.towardsai.net/applications-of-multimodal-large-language-models-in-personalized-healthcare-ecc501090e06 | |||
21:42 | Unlocking the Power of LLMs: 10 Innovative Use Cases Explored with Code https://medium.com/@dhshah1112/unlocking-the-power-of-llms-10-innovative-use-cases-explored-with-code-ed888c169210 | |||
21:39 | AI Prompt Arsenal: Supercharging AI Agents and RAG Systems https://medium.com/@ssuparnataneja/ai-prompt-arsenal-supercharging-ai-agents-and-rag-systems-d1a7dc621af6 | |||
21:39 | Diving Deeper with Structured Outputs https://towardsdatascience.com/diving-deeper-with-structured-outputs-b4a5d280c208 | |||
21:36 | Scan LLM-Codegen for security issues https://chromewebstore.google.com/detail/secure-ai-generated-code/bengiidgkchpliicfplbejjnoennfkmo | |||
20:28 | AI’nt That Easy#14: Scaling LLM Apps: Why System Design Matters https://aint-that-easy.medium.com/aint-that-easy-14-scaling-llm-apps-why-system-design-matters-54fcb88af511 | |||
20:25 | Corporate suicide: Ignoring the AI revolution https://medium.com/@teratalker/corporate-suicide-ignoring-the-ai-revolution-68043bd636ca | |||
20:07 | Anthropic Quickstarts https://github.com/anthropics/anthropic-quickstarts | |||
20:07 | What is Generative AI? https://medium.com/@teratalker/what-is-generative-ai-6827cbb459db | |||
19:46 | What is AI Good For? https://medium.com/inkwell-atlas/what-is-ai-good-for-7ee642b98481 | |||
19:43 | Best Practices for Using AI Models in Content Creation https://medium.com/@teratalker/best-practices-for-using-ai-models-in-content-creation-9a45ed0679ae | |||
19:37 | What is the difference between GPT and LLM? https://medium.com/@teratalker/what-is-the-difference-between-gpt-and-llm-e7fd4cf22943 | |||
19:36 | Don’t waste time using AI https://medium.com/@acu192/dont-waste-time-using-ai-110f81aace1e | |||
19:28 | Top 20 Best LLMs in 2024 https://medium.com/@teratalker/top-20-best-llms-in-2024-14e7dbbf16b4 | |||
19:16 | OpenAI Pleads It Can't Make Money Without Using Copyrighted Materials for Free https://futurism.com/the-byte/openai-copyrighted-material-parliament | |||
19:11 | Turbocharging Language Models and Shrinking Giants: The Minitron Blueprint for Powerful, Compact AI https://readqvick.medium.com/turbocharging-language-models-and-shrinking-giants-the-minitron-blueprint-for-powerful-compact-ai-582d7a2735c0 | |||
18:53 | Step-Based Cascading Prompts: Deterministic Signals from the LLM Vibe Space https://shelbyjenkins.github.io/blog/cascade-prompt/ | |||
18:42 | Chip giant Intel spurned OpenAI and fell behind the times https://www.reuters.com/technology/artificial-intelligence/how-chip-giant-intel-spurned-openai-fell-behind-times-2024-08-07/ | |||
18:27 | Glossary of LLM Terms and Abbreviations in Academic Papers https://medium.com/@k.e.elsayed/glossary-of-llm-terms-and-abbreviations-in-academic-papers-d3cc484673e2 | |||
18:14 | Using multiple LLMs in parallel: Advantages and opportunities https://medium.com/@teratalker/using-multiple-llms-in-parallel-advantages-and-opportunities-f4c1babbc5c7 | |||
18:05 | Line-By-Line, Let’s Reproduce GPT-2: Section 3 — Training https://towardsdatascience.com/line-by-line-lets-reproduce-gpt-2-section-3-training-f2fef87880fc | |||
18:05 | Mosaic AI Flywheel: Better, Cheaper, Faster AI Systems https://medium.com/@jlipem/mosaic-ai-flywheel-better-cheaper-faster-ai-systems-98807d680164 | |||
18:02 | Building a Pet Name Generator with Streamlit, LangChain, and Gemini API https://medium.com/@adeelfarooq417/building-a-pet-name-generator-with-streamlit-langchain-and-gemini-api-62a6f9e2a4ff | |||
17:47 | The History & Future of Prompt Engineering https://cobusgreyling.medium.com/the-history-future-of-prompt-engineering-6066ba2215fd | |||
17:39 | Protecting AI from Jailbreak Attempts: Insights from Auto Defense https://medium.com/@hasaanijaz01/protecting-ai-from-jailbreak-attempts-insights-from-auto-defense-d002786fd2f8 | |||
17:27 | Gen AI applications and the art of Observability and Monitoring https://medium.com/@nayan.j.paul/gen-ai-applications-and-the-art-of-observability-and-monitoring-9b2459caee3a | |||
17:09 | The Era of Advanced AI Language Models: A Revolution in Online Marketing https://medium.com/@mediabeats/the-era-of-advanced-ai-language-models-a-revolution-in-online-marketing-55b7ed8fbb1d | |||
16:13 | The End of AI Hallucinations: A Breakthrough in Accuracy for Data Engineers https://medium.com/@JamesStakelum/the-end-of-ai-hallucinations-a-breakthrough-in-accuracy-for-data-engineers-e67be5cc742a | |||
15:57 | My name is Claude https://medium.com/@hjiouij/my-name-is-claude-9596e68d7b0c | |||
15:32 | RAG Chatbots: Revolutionizing Information Retrieval and Dialogue Systems https://medium.com/@cheygalkaduwa/rag-chatbots-revolutionizing-information-retrieval-and-dialogue-systems-5ff4a11cf94e | |||
15:05 | OWASP: Top 10 for LLM https://medium.com/@anu.abraham37/owasp-top-10-for-llm-74ad0b35ecc9 | |||
14:57 | Significant Traffic Decline in Online Knowledge Communities Post-ChatGPT https://medium.com/@copywritermeenal/significant-traffic-decline-in-online-knowledge-communities-post-chatgpt-c3284b3cb990 | |||
14:52 | Build reliable agents in JavaScript with LangGraph.js v0.2: Now supporting Cloud and Studio https://blog.langchain.dev/javascript-langgraph-v02-cloud-studio/ | |||
14:44 | TAI #115: LLM Adoption Taking Off? OpenAI API Use Up 2x in 5 Weeks, LLama at 350m Downloads. https://pub.towardsai.net/tai-115-llm-adoption-taking-off-openai-api-use-up-2x-in-5-weeks-llama-at-350m-downloads-3f708e5694d1 | |||
14:26 | On the Use of LLMs and AI vs. Writers https://medium.com/@pinkypirateblog/on-the-use-of-llms-and-ai-vs-writers-d84f9734bc97 | |||
14:17 | Crawling the Web for LLMs https://medium.com/@ifrimradumdc/crawling-the-web-for-llms-31d56c792e88 | |||
14:07 | Semantic Chunking: Improving AI Information Retrieval https://medium.com/@nirdiamant21/semantic-chunking-improving-ai-information-retrieval-2f468be2d707 | |||
13:52 | A short note on Reinforced Fine-Tuning or ReFT https://medium.com/@nielspace/a-short-note-on-reinforced-fine-tuning-or-reft-71dee61b9020 | |||
13:35 | Making LLMs stupidly effective https://medium.com/@jones.steveg/making-llms-stupidly-effective-cb239794a6f0 | |||
13:07 | OpenAI plans to build its own AI chips on TSMC's forthcoming https://www.pcgamer.com/software/ai/openai-plans-to-build-its-own-ai-chips-on-tsmcs-forthcoming-16-nm-a16-process-node/ | |||
11:44 | Comprehensive Guide to LLM Fine-Tuning Strategies https://medium.com/@gurpreetkaurj/comprehensive-guide-to-llm-fine-tuning-strategies-de7ab0ce2c19 | |||
11:33 | It’s Time To Take A Break From ChatGPT (and its variants). https://medium.com/the-new-climate/its-time-to-take-a-break-from-chatgpt-and-its-variants-3a02212d53b9 | |||
11:26 | Executive Summary of the NVIDIA 2024 State of AI in Financial Services Report https://medium.com/ai-governance-testing/executive-summary-of-the-nvidia-2024-state-of-ai-in-financial-services-report-addff35dbc7f | |||
11:23 | PM Modi’s Historic Visit to Brunei and Singapore https://medium.com/@andy1729/pm-modis-historic-visit-to-brunei-and-singapore-af871222b91b | |||
11:13 | Claude Artifacts: Anthropic is a game changer in AI interfaces! https://medium.com/@axevil/claude-artifacts-anthropic-is-a-game-changer-in-ai-interfaces-40089f23b699 | |||
11:04 | Creating a RAG application with AWS CDK as IaC, Qdrant and LlamaIndex https://medium.com/@benitomartin/creating-a-rag-application-with-aws-cdk-as-iac-qdrant-and-llamaindex-9138fd6999ef | |||
11:01 | Using AI to Create Comprehensible Input Stories in Spanish: Tips for Development https://medium.com/@marketing_novita.ai/using-ai-to-create-comprehensible-input-stories-in-spanish-tips-for-development-c3f93c81e4c6 | |||
10:27 | Getting Out Of Generative AI https://paulmwatson.medium.com/getting-out-of-generative-ai-3920a5e0d7ce | |||
10:24 | Self-developed LLM: Motiff’s Strategy for Future UI Design https://medium.com/motiff/self-developed-llm-motiffs-strategy-for-future-ui-design-032b9813c1ef | |||
10:24 | The Problem With Open Sourcing AI Datasets https://paulmwatson.medium.com/the-problem-with-open-sourcing-ai-datasets-1b9a85ccde5f | |||
09:12 | Introduction to LLM Agents: How to Build a Simple Reasoning and Acting Agent from Scratch (Part 1) https://medium.com/@ayoubkirouane3/introduction-to-llm-agents-how-to-build-a-simple-reasoning-and-acting-agent-from-scratch-part-1-843e14686be7 | |||
09:12 | Introduction to LLM Agents: How to Build a Simple Reasoning and Acting Agent from Scratch (Part 1) https://blog.gopenai.com/introduction-to-llm-agents-how-to-build-a-simple-reasoning-and-acting-agent-from-scratch-part-1-843e14686be7 | |||
08:04 | Reflecting on LLM Memory and Accuracy https://lukaszborun.medium.com/reflecting-on-llm-memory-and-accuracy-b74c5b083499 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803