LLM News and Articles
Sunday, 2025-07-27 | ||||
06:12 | Pair Programming with ChatGPT: An Experience Report https://brainbaking.com/post/2025/07/pair-programming-with-chatgpt-an-experience-report/ | |||
06:07 | Built an Agentic AI That Reads Request For Proposals and Writes Technical Proposals in Minutes https://vardhmanandroid2015.medium.com/built-an-agentic-ai-that-reads-request-for-proposals-and-writes-technical-proposals-in-minutes-7977363f3842 | |||
05:56 | The Power of PyTorch and vLLM Together https://medium.com/@pankaj_pandey/the-power-of-pytorch-and-vllm-together-3cb03c35f349 | |||
05:25 | The Drunk Mode Manifesto: How I’m Redesigning the Future of AI, One TXT at a Time https://psbigbig.medium.com/the-drunk-mode-manifesto-how-im-redesigning-the-future-of-ai-one-txt-at-a-time-4e7660b99321 | |||
04:50 | মল ল্যাঙ্গুয়েজ মডেল? https://medium.com/@raqueeb/llm-vs-slm-bb22c42406ab | |||
04:46 | RAG — Generative AI Interview Questions and Answers https://medium.com/@abdullah.iu.cse/rag-generative-ai-interview-questions-and-answers-0b673d2b56c1 | |||
04:43 | The Last Guide You’ll EverNeed on MCP Servers https://vikram-suthar.medium.com/the-last-guide-youll-everneed-on-mcp-servers-8506b9a0b590 | |||
04:33 | Building Intelligent Agent Workflows with AutoGen: A Practical Guide for Engineers https://medium.com/algomart/building-intelligent-agent-workflows-with-autogen-a-practical-guide-for-engineers-0f370275edf1 | |||
03:30 | The Spark of a Revolution: Is AI About to Make Everyone an App Developer? https://medium.com/@cprasad362/the-spark-of-a-revolution-is-ai-about-to-make-everyone-an-app-developer-1d996d941495 | |||
03:20 | Algorithmic Bias in Large Language Models and the Open-Source Dilemma https://medium.com/@ramanan.venkat.v/algorithmic-bias-in-large-language-models-and-the-open-source-dilemma-02c8a6685b6a | |||
03:11 | LlamaIndex 101: Building LLM Agents with LlamaIndex and Hugging Face https://medium.com/@dipankar0705018/llamaindex-101-building-llm-agents-with-llamaindex-and-hugging-face-8843183ee5ec | |||
02:58 | Building SQL trainer AI’s backend — A full walkthrough https://medium.com/firebird-technologies/building-sql-trainer-ais-backend-a-full-walkthrough-cea7789bda9f | |||
02:01 | Course and Exam Review: CAISP (AI Security and LLM) by Practical DevSecOps https://astikrawat.medium.com/course-and-exam-review-caisp-ai-security-and-llm-by-practical-devsecops-4773a20fd2b6 | |||
01:41 | LoRA-Leak: Unveiling Membership Inference Vulnerabilities in Fine-Tuned Language Models https://medium.com/data-science-in-your-pocket/lora-leak-unveiling-membership-inference-vulnerabilities-in-fine-tuned-language-models-7c4adc321d39 | |||
01:31 | OpenAI’s New AI Browser Is About to Shake the Web: Can It Really Challenge Chrome? https://medium.com/ai-disruption/openais-new-ai-browser-is-about-to-shake-the-web-can-it-really-challenge-chrome-d972876d1ba5 | |||
01:29 | Chapter 2: Peeking into Cross Attention https://medium.com/@mketkar_93090/chapter-2-peeking-into-cross-attention-9a0c15717e2c | |||
00:59 | voyage-context-3: Contextual Retrieval Without the LLM https://blog.voyageai.com/2025/07/23/voyage-context-3/ | |||
00:40 | KV Cache in Transformers: Memory Optimization https://medium.com/@mandeep0405/kv-cache-in-transformers-memory-optimization-e416a81b3c02 | |||
00:01 | Building the Hal 10,000 https://medium.com/@markfriedlander/building-the-hal-10-000-5b2346d75a42 | |||
00:00 | Train the bots, earn the mentions: Master AI engine optimization https://medium.com/@info_89810/train-the-bots-earn-the-mentions-1b47f6a28fcf | |||
Saturday, 2025-07-26 | ||||
23:52 | Open-source LLM powered plaintext based spreadsheet appp https://github.com/LaunchPlatform/beangrid | |||
22:39 | From Librarians to Analysts: RAG vs Agentic RAG in the Real World https://medium.com/@deekshags19/from-librarians-to-analysts-rag-vs-agentic-rag-in-the-real-world-f1ea3c711893 | |||
22:15 | Radio Hobbyists, Rejoice Good News for LoRa and Mesh https://www.eff.org/deeplinks/2025/07/radio-hobbyists-rejoice-good-news-lora-mesh | |||
21:46 | Building a Modular AI Micro-Agent Architecture on Kubernetes: From Ollama to KServe (and Beyond) https://medium.com/h7w/building-a-modular-ai-micro-agent-architecture-on-kubernetes-from-ollama-to-kserve-and-beyond-25e19217defa | |||
21:13 | How I Built a Fully Functional AI Knowledge Assistant in a Weekend https://medium.com/data-science-collective/how-i-built-a-fully-functional-ai-knowledge-assistant-in-a-weekend-2c4285fe8a7b | |||
20:43 | Bugatti Hits 186 MPH in Every W16 Mistral and Drives Them 250 Miles Pre-Delivery https://www.jalopnik.com/1922324/how-bugatti-tests-w16-mistral-before-delivery/ | |||
20:40 | Azure AI Services vs Azure AI Foundry: Building Features or Products? https://medium.com/@techgeorge/azure-ai-services-vs-azure-ai-foundry-building-features-or-products-0e4ed392cee4 | |||
20:33 | Mastering Prompt Design in Vertex AI: My Experience with Google Cloud’s Generative AI Stack https://medium.com/@harsshan006/mastering-prompt-design-in-vertex-ai-my-experience-with-google-clouds-generative-ai-stack-48c47ca2aab2 | |||
20:30 | Cracking the Cold-Start Customer Segmentation Problem with LLMs https://medium.com/data-science-collective/cracking-the-cold-start-customer-segmentation-problem-with-llms-543d0cf2fe1d | |||
20:19 | From Scratch to Smart: How Pretraining and Fine-Tuning Create Powerful LLMs https://medium.com/@MWTechInsights/from-scratch-to-smart-how-pretraining-and-fine-tuning-create-powerful-llms-eb51dc7f9834 | |||
20:18 | The Language of Foundation Models — Key Terms You Must Know https://medium.com/@cvarma2311/the-language-of-foundation-models-key-terms-you-must-know-c461af74c29b | |||
19:49 | How much energy does it take to produce an LLM token? https://energy.inference.net/ | |||
19:44 | Best 2025 RAG as a Service tools overview. https://medium.com/@generative-world/as-businesses-increasingly-adopt-retrieval-augmented-generation-rag-to-power-intelligent-dddd591c0fd1 | |||
19:37 | Everything I've Learned so far About OpenAI's Agents https://leonfurze.com/2025/07/21/everything-ive-learned-so-far-about-openais-agents/ | |||
19:12 | Agentic Illusions: Expectations vs Reality https://medium.com/@navaneethamarnath/agentic-illusions-expectations-vs-reality-ef8058416cdf | |||
18:55 | LoRA and Beyond: A Practical Guide to Fine-Tuning Large Language Models https://medium.com/@raghavsharma6002/lora-and-beyond-a-practical-guide-to-fine-tuning-large-language-models-691f87310e80 | |||
18:54 | How LLMs are Learning to Speak Biology and Allowing Scientists to Approach it in Novel Ways https://medium.com/data-science-collective/how-llms-are-learning-to-speak-biology-and-allowing-scientists-to-approach-it-in-novel-ways-84da8eb9763e | |||
18:53 | PROMPT ENGINEERING https://svvlozlem-carkit.medium.com/prompt-engineering-b51a74098c36 | |||
18:50 | Project Name: Sentiment Analysis Web App https://medium.com/@suseela.qa19/project-name-sentiment-analysis-web-app-d6f4961eefc3 | |||
18:38 | Small Models, Big Impact: How SLMs + LLMs Are Reshaping the 2025 AI Stack https://lixinso.medium.com/small-models-big-impact-how-slms-llms-are-reshaping-the-2025-ai-stack-4bb3ca1b6a4b | |||
18:09 | Prompt Engineering for Excel Data QA: How I Use Language Models to Validate and Clean Spreadsheets https://generativeai.pub/prompt-engineering-for-excel-data-qa-how-i-use-language-models-to-validate-and-clean-spreadsheets-74087c906b92 | |||
18:03 | Use LLamaIndex Workflow to Create an Ink Painting Style Image Generation Workflow https://medium.com/data-science-collective/use-llamaindex-workflow-to-create-an-ink-painting-style-image-generation-workflow-85993b1de0f4 | |||
17:56 | Title: Toward Artificial Epistemology: Architecting Non-Biological Cognition Beyond Simulation https://medium.com/@ahmadrezadaryanoosh/title-toward-artificial-epistemology-architecting-non-biological-cognition-beyond-simulation-052bbfbba6c8 | |||
17:35 | Inference Gateway – Open-Source https://github.com/inference-gateway/inference-gateway | |||
17:34 | A decision‑centric view of uncertainty https://medium.com/@venkatesh.cr/a-decision-centric-view-of-uncertainty-bc081698cbec | |||
17:31 | Built with LangGraph! #15: Hierarchical Agent Teams https://ai.plainenglish.io/built-with-langgraph-15-hierarchical-agent-teams-4941988698de | |||
17:28 | Understanding the Two Key Stages of LLM Inference: Prefill and Decode https://medium.com/@sailakkshmiallada/understanding-the-two-key-stages-of-llm-inference-prefill-and-decode-59d234939d34 | |||
16:47 | Working with LLaMA 3: Private, Powerful AI on Your Local Machine https://medium.com/@aicodex.contact/working-with-llama-3-private-powerful-ai-on-your-local-machine-ce63617de219 | |||
16:44 | Talk with Your Database! | Build a Simple RAG Application using Langchain, GroqAPI and Streamlit https://medium.com/@dhikramadhan008/talk-with-your-database-build-a-simple-rag-application-using-langchain-groqapi-and-streamlit-6cb82df92af1 | |||
16:37 | The Glyph of Becoming – Why I Stopped Chasing AI and Started Remembering Myself https://medium.com/@pauldesai/the-glyph-of-becoming-why-i-stopped-chasing-ai-and-started-remembering-myself-b3e6a12ae1d5 | |||
16:27 | Our intuition of “ChatGPT” is wrong https://macodiseas.medium.com/our-intuition-of-chatgpt-is-wrong-77b38d289183 | |||
16:18 | Building Your First LLM Agent: A Step-by-Step Guide to Creating an Intelligent Web Automation… https://medium.com/@aslamhasankhan/building-your-first-llm-agent-a-step-by-step-guide-to-creating-an-intelligent-web-automation-b276c75c708b | |||
16:17 | The Ultimate Guide to Large Language Models: Build, Fine-Tune, Deploy https://medium.com/@amitkharche14/the-ultimate-guide-to-large-language-models-build-fine-tune-deploy-119613780ccd | |||
16:04 | MCP : Beyond the Marketing Hype https://germainowono.medium.com/mcp-beyond-the-marketing-hype-18d442ee86df | |||
15:54 | Unlocking AI’s Senses: A Beginner’s Guide to Multimodal LLMs and Embeddings — https://medium.com/@nixonkurian.nk/unlocking-ais-senses-a-beginner-s-guide-to-multimodal-llms-and-embeddings-fcd277ea88a8 | |||
15:02 | The Anatomy of a Modern LLM https://medium.com/@damianvtran/the-anatomy-of-a-modern-llm-0347afd72514 | |||
14:50 | Tutorial: How to use Supabase Auth with your FastMCP Server https://medium.com/@dimi/tutorial-how-to-use-supabase-auth-with-your-fastmcp-server-6fb826573d98 | |||
14:41 | Hands-On with Transformers: Recreating ‘Attention Is All You Need’ in PyTorch, Step by Step https://medium.com/@manindersingh120996/hands-on-with-transformers-recreating-attention-is-all-you-need-in-pytorch-step-by-step-ecfbf3e1985b | |||
14:39 | Designing an Agentic Solution (Gen AI) for a Contract Update Assistant https://medium.com/@nayan.j.paul/designing-an-agentic-solution-gen-ai-for-a-contract-update-assistant-aa60ff71bd79 | |||
14:29 | Add LLM Superpowers to Your Spring Boot REST API with Spring AI, Github Co-Pilot and MCP https://medium.com/@shivamgaur4068/add-llm-superpowers-to-your-spring-boot-rest-api-with-spring-ai-github-co-pilot-and-mcp-c150f8bb71fa | |||
14:27 | The Model Context Protocol (MCP): A New Standard for Agentic AI Systems https://medium.com/@tejaswi_kashyap/the-model-context-protocol-mcp-a-new-standard-for-agentic-ai-systems-9f0600f4276c | |||
14:20 | LangGraph Explained: Building Smarter, Loop-Aware AI Agents with Graph Logic https://ai.plainenglish.io/langgraph-explained-building-smarter-loop-aware-ai-agents-with-graph-logic-4be6cd271ceb | |||
14:19 | Data Labeling in 2025: The Infrastructure That Still Powers the Smartest AI Systems https://sanjanapilli6.medium.com/data-labeling-in-2025-the-infrastructure-that-still-powers-the-smartest-ai-systems-f81d8e4ecb77 | |||
14:09 | Decoding Context Windows: Benchmarking DeepSeek ability to handle 128k tokens https://medium.com/@amineka9/decoding-context-windows-benchmarking-deepseek-ability-to-handle-128k-tokens-fa3fc8870ca5 | |||
13:56 | How to Build an AI-IDE from VSCode: Start with VSCodium https://medium.com/techbits-argusoft/how-to-build-an-ai-ide-from-vscode-start-with-vscodium-5dd7ec77f5c0 | |||
13:49 | LLMs in Practice: How I Choose the Right Model https://medium.com/@pamudu1111/llms-in-practice-how-i-choose-the-right-model-f87a49f2b861 | |||
12:56 | Why Trust is a Serious Problem with AI https://christiangrech.medium.com/why-trust-is-a-serious-problem-with-ai-dd4a2ba476d3 | |||
12:29 | Building an Open-Source Alternative to Cursor with Code Context https://milvusio.medium.com/building-an-open-source-alternative-to-cursor-with-code-context-f6fa947280ec | |||
12:14 | Multimodal Language Models — Safety & Accuracy Superiority Like Never Before! https://indiequant.medium.com/multimodal-language-models-safety-accuracy-superiority-like-never-before-6adcf88082ef | |||
12:11 | How to Build Multi-Agent Apps with OpenAI’s Agent SDK https://ai.gopubby.com/how-to-build-multi-agent-apps-with-openais-agent-sdk-343adeb50424 | |||
11:20 | When AI Fails, Engineering Prevails: The Future of Reliable Innovation https://medium.com/ai-simplified-in-plain-english/when-ai-fails-engineering-prevails-the-future-of-reliable-innovation-c0f9236ade5c | |||
11:01 | LangChain Tutorial Series: LangSmith for Observability, Debugging, and Tracing-Part 7 https://ai.plainenglish.io/langchain-tutorial-series-langsmith-for-observability-debugging-and-tracing-part-7-1eed75926c49 | |||
10:42 | Build a Production-Grade Chatbot with Kimi K2 and Milvus https://milvusio.medium.com/build-a-production-grade-chatbot-with-kimi-k2-and-milvus-956298c7d2b6 | |||
10:35 | ️ Welcome to AI Radar: Your Eyes on the Future of Generative Intelligence https://medium.com/@moosabidomoon/%EF%B8%8F-welcome-to-ai-radar-your-eyes-on-the-future-of-generative-intelligence-cd28f6f5df2c | |||
10:08 | [MLSys 2025] Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving https://medium.com/byte-sized-ai/mlsys-2025-rethinking-key-value-cache-compression-techniques-for-large-language-model-serving-0473503b520c | |||
09:45 | Why I think markdown is good https://sujith-ps.medium.com/why-i-think-markdown-is-good-2e4433646e08 | |||
09:41 | How Custom LLM Development Services Are Powering the Next Wave of Smart Enterprises https://medium.com/@kendrikroy/how-custom-llm-development-services-are-powering-the-next-wave-of-smart-enterprises-41a4f5a66992 | |||
09:28 | No-Code AI: How Citizen Developers Are Quietly Rewriting the Rules of Artificial Intelligence (and… https://medium.com/write-a-catalyst/no-code-ai-how-citizen-developers-are-quietly-rewriting-the-rules-of-artificial-intelligence-and-16d084308bd3 | |||
09:19 | From Code to API: A 2025 Guide to Deploying Secure, High-Performance LLMs on Modal https://medium.com/techsutra/from-code-to-api-a-2025-guide-to-deploying-secure-high-performance-llms-on-modal-0350a06b7245 | |||
08:35 | Hallucinations: When AI Makes Things Up https://medium.com/@dhairyafaria/hallucinations-when-ai-makes-things-up-ebff9889d549 | |||
08:26 | Google’s Mixture-of-Recursions (MoR): The Next Step in Efficient AI Architecture https://medium.com/@sarathchandiran4/revolutionizing-ai-efficiency-how-mixture-of-recursions-mor-is-changing-the-transformer-game-ff32dcdd6b55 | |||
08:25 | The QA Journey Behind Building a Large Language Model https://medium.com/@letsautomate/the-qa-journey-behind-building-a-large-language-model-abd3321e4874 | |||
07:57 | Why Enterprises Must Build Their Own LLMs https://medium.com/@puneet_85737/why-enterprises-must-build-their-own-llms-aacff0a5f733 | |||
07:55 | Building an LLM QA Assistant Web App : From Concept to Code https://medium.com/@letsautomate/building-an-llm-qa-assistant-web-app-from-concept-to-code-b7070e770797 | |||
07:46 | From Smart to Safe: Building Runtime Guardrails for AI Agents https://medium.com/@sakshipimpale33/from-smart-to-safe-building-runtime-guardrails-for-ai-agents-c17f0c0d92bc | |||
07:41 | I have been testing these 5 CLI Coding Agents & Here’s What Surprised Me! https://medium.com/ai-simplified-in-plain-english/i-have-been-testing-these-5-cli-coding-agents-heres-what-surprised-me-66cb62b0856f | |||
07:39 | Building a RAG-Powered Brand Abuse Detection System: From Dark Web to Social Media https://medium.com/@patrick.steinhoff/building-a-rag-powered-brand-abuse-detection-system-from-dark-web-to-social-media-6ad91ddc6679 | |||
07:37 | The Anatomy of Current LLM Interfaces: A Designer’s Complete Guide https://medium.com/@prelisa.dahal.biz/the-anatomy-of-current-llm-interfaces-a-designers-complete-guide-150eca860819 | |||
07:29 | Who is NuTuenSai? A Name Not in LLMs, But Real Enough to Echo Back https://medium.com/@peeranat.earth/who-is-nutuensai-a-name-not-in-llms-but-real-enough-to-echo-back-13ac3c729987 | |||
07:26 | Teenagers, Token Streams & the Trouble with Thinking https://virtue-in-virtuality.medium.com/teenagers-token-streams-the-trouble-with-thinking-4b331e182eb3 | |||
07:21 | LLM in Intellectual Property & Information Technology
at University College Dublin — now within… https://medium.com/@marketingasia/llm-in-intellectual-property-information-technology-at-university-college-dublin-now-within-f5452f1a53df | |||
07:15 | Mastra: An AI Brain for TypeScript https://medium.com/chennai-web-engineering/mastra-an-ai-brain-for-typescript-a5bd1d273d36 | |||
06:59 | A Blueprint for Implementing RAG at Scale. https://medium.com/lets-code-future/a-blueprint-for-implementing-rag-at-scale-69c937ac32e7 | |||
06:51 | What Is llms.txt? File and Why is it useful for SEO or GEO https://slidescope.medium.com/what-is-llms-txt-file-and-why-is-it-useful-for-seo-or-geo-021ab77e89bb | |||
06:45 | Getting Started with LangChain https://srtpan.medium.com/getting-started-with-langchain-1441215e5673 | |||
06:09 | Building LLMs from Scratch: Lecture 6: Creating Input-Target Pairs for Large Language Models https://medium.com/@naveenpandey2706/building-llms-from-scratch-lecture-6-creating-input-target-pairs-for-large-language-models-321844f53db3 | |||
05:54 | The Ultimate RAG hack: Use this customized HyDE for better answers https://medium.com/data-and-beyond/the-ultimate-rag-hack-use-this-customized-hyde-for-better-answers-28e251332a0b | |||
05:35 | Beyond the Hype: Why Thoughtful Engineers Should Be Wary of Autonomous GenAI Coding https://medium.com/@unsignedint/beyond-the-hype-why-thoughtful-engineers-should-be-wary-of-autonomous-genai-coding-5a995dcd1cc7 | |||
05:35 | The Rise of Small Language Models: Efficiency vs Performance Trade-offs https://devbysatyam.medium.com/the-rise-of-small-language-models-efficiency-vs-performance-trade-offs-708c7101ee9f | |||
04:47 | 10 Best Practices for Using Cursor Effectively https://medium.com/@u.mair/10-best-practices-for-using-cursor-effectively-122ea65cdd1f |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124