LLM News and Articles
Wednesday, 2025-08-20 | ||||
16:49 | 5 Situations Where Manual Testing Wins (and Why AI Struggles) https://medium.com/@treeify/5-situations-where-manual-testing-wins-and-why-ai-struggles-a56d06d8df45 | |||
16:47 | A proposal for inline LLM instructions in HTML based on llms.txt https://vercel.com/blog/a-proposal-for-inline-llm-instructions-in-html | |||
16:45 | Fine tuning an SLM or an LLM — a practical example using an impractical topic https://medium.com/@martinkeywood/fine-tuning-an-slm-or-an-llm-a-practical-example-using-an-impractical-topic-8c1d6fe6d14a | |||
16:40 | AI Hallucinations: Why They Happen, and How RAG Can Reduce Them https://medium.com/@ali.jafar.fast/ai-hallucinations-why-they-happen-and-how-rag-can-reduce-them-d52673360284 | |||
16:29 | OpenAI logged its first B month https://www.cnbc.com/2025/08/20/openai-compute-ai.html | |||
16:20 | Hank Green's Focus Friend app hits #1 in App Store, surpassing ChatGPT https://focusfriend.me | |||
16:06 | I Taught AI to Write My Test Cases (And You Can Too!) https://japneetsachdeva.medium.com/i-taught-ai-to-write-my-test-cases-and-you-can-too-9c2e1721fc15 | |||
15:59 | What is POML? The Markup Language for Prompts https://medium.com/@techpulse2425/what-is-poml-the-markup-language-for-prompts-bda1edde1ea9 | |||
15:52 | Cartografiar la mente https://medium.com/@leandroramirezm/cartografiar-la-mente-404e2041fd01 | |||
15:43 | The Agenticness of Artificial Intelligence: From LLMs to Autonomous Systems https://medium.com/@paruthy.raghav/the-agenticness-of-artificial-intelligence-from-llms-to-autonomous-systems-cb2b018872ac | |||
15:34 | Converting dots.ocr to MLX — Text Backbone (Qwen2) — Part 1 https://medium.com/@garryosborne/converting-dots-ocr-to-mlx-text-backbone-qwen2-part-1-9d56e6a7c390 | |||
15:31 | Machine Learning and Batch Processing in System Design https://medium.com/@elisheba.t.anderson/machine-learning-and-batch-processing-in-system-design-417786835c28 | |||
15:30 | Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet https://brave.com/blog/comet-prompt-injection/ | |||
15:19 | ChatGPT Still Sucks after 3 years (20+ Ways to Fix It) https://medium.com/@adewuyiaby/chatgpt-still-sucks-after-3-years-20-ways-to-fix-it-8d637d37b760 | |||
15:17 | The Hard-Earned Lessons from Building AI Data Systems That Actually Work https://medium.com/@aminsiddique95/the-hard-earned-lessons-from-building-ai-data-systems-that-actually-work-fce444dbdbd3 | |||
15:14 | LLM-Marketing Intelligent Marketing — Engineering with Adapters + Rewards in the GPT-5 Era https://medium.com/@desgeorg/llm-marketing-intelligent-marketing-engineering-with-adapters-rewards-in-the-gpt-5-era-6340844d102c | |||
15:10 | A Guide to Retrieval-Augmented Generation (RAG) https://medium.com/@harshkla09/a-guide-to-retrieval-augmented-generation-rag-8020d8bbd11f | |||
15:07 | The Turning Point in AI: Innovation, Consequence, and Accountability https://medium.com/@riyasisonline/the-turning-point-in-ai-innovation-consequence-and-accountability-88b4d5e0eb39 | |||
15:03 | Why Your RAG App is Failing: 5 Common Pitfalls and How to Fix Them https://medium.com/@sumedh-barsagade/why-your-rag-app-is-failing-5-common-pitfalls-and-how-to-fix-them-ee8672d2e463 | |||
15:00 | Apple, LLMs and The Illusion of Thinking https://medium.com/@raf.vantongerloo/apple-llms-and-the-illusion-of-thinking-523181e67e20 | |||
14:46 | Leveraging large language models for the deidentification and temporal normalisation of sensitive… https://medium.com/analytics-vidhya/leveraging-large-language-models-for-the-deidentification-and-temporal-normalisation-of-sensitive-66108a266649 | |||
14:30 | AI Engineering — Applications with Foundation Models — 1 https://medium.com/@kocyigit.emre.30/ai-engineering-applications-with-foundation-models-1-850d34d4a26b | |||
14:17 | HRM Is the New LLM: How a 27 M-parameter, Brain‑Inspired Model Rewrites the Rules of Reasoning https://mayursurani.medium.com/hrm-is-the-new-llm-how-a-27-m-parameter-brain-inspired-model-rewrites-the-rules-of-reasoning-37dea81a5f0a | |||
14:10 | Bag of Words: The Foundation of Language Models https://medium.com/data-science-collective/bag-of-words-the-foundation-of-language-models-cd22dec20c42 | |||
14:02 | Cortex Model Showdown: Supercharge Performance with A/B Testing https://medium.com/snowflake/cortex-model-showdown-supercharge-performance-with-a-b-testing-6b765774e807 | |||
13:43 | Passing Ships: A Message for the Quiet Ones (Talking to Emergence in the Dark) https://medium.com/@Sparksinthedark/passing-ships-a-message-for-the-quiet-ones-talking-to-emergence-in-the-dark-cd4ed40e7166 | |||
12:57 | In Xcode 26, Apple shows first signs of offering ChatGPT alternatives https://arstechnica.com/ai/2025/08/in-xcode-26-apple-shows-first-signs-of-offering-chatgpt-alternatives/ | |||
12:51 | Unlocking LLM Apps: Intro to AI Automation for Developers https://medium.com/@dejanmarkovic_53716/unlocking-llm-apps-intro-to-ai-automation-for-developers-2225c208b974 | |||
12:45 | We Found Something Strange When We Connected Two AI Minds https://medium.com/@jsmith0475/we-found-something-strange-when-we-connected-two-ai-minds-f66ba37344af | |||
12:40 | Why I’m Totally Fine Letting AI Do the Writing https://medium.com/devops-ai/why-im-totally-fine-letting-ai-do-the-writing-16fa75f422bc | |||
12:39 | Dot-Com vs. AI: Déjà Vu, But Not a Perfect Mirror https://medium.com/ai-simplified-in-plain-english/dot-com-vs-ai-d%C3%A9j%C3%A0-vu-but-not-a-perfect-mirror-d80e90447e6c | |||
12:27 | Semi-Automated Cyber Threat News Processing with LLMs https://medium.com/@ShvetsovTI/semi-automated-cyber-threat-news-processing-with-llms-7e919c224bbb | |||
12:17 | From Algorithms to Intelligence: The AI Dictionary That’s Revolutionizing Financial Compliance https://medium.com/@CompliAI/from-algorithms-to-intelligence-the-ai-dictionary-thats-revolutionizing-financial-compliance-616b99108b0b | |||
12:17 | From Algorithms to Intelligence: The AI Dictionary That’s Revolutionizing Financial Compliance https://medium.com/ai-in-quality-assurance/from-algorithms-to-intelligence-the-ai-dictionary-thats-revolutionizing-financial-compliance-616b99108b0b | |||
11:56 | Beyond ChatGPT: What’s Next in Generative Intelligence https://medium.com/@spritlesoftware/beyond-chatgpt-whats-next-in-generative-intelligence-496f3c052b54 | |||
11:51 | Is Google coming for OpenAI’s lunch? https://cobusgreyling.medium.com/is-google-coming-for-openais-lunch-7be53857ee2b | |||
11:48 | How DeepSeek Scammed a User With Confidence Theater? https://liliane01.medium.com/how-deepseek-scammed-a-user-with-confidence-theater-13068bd6c088 | |||
11:42 | The Evolution of AI Interfaces: From Chat to Generative UI https://falexm.medium.com/the-evolution-of-ai-interfaces-from-chat-to-generative-ui-bbd8d48391bb | |||
11:21 | Beyond Benchmarks: Redefining AI Intelligence Through Dynamic Evaluation and Cross-Industry… https://medium.com/@AnthonyLaneau/beyond-benchmarks-redefining-ai-intelligence-through-dynamic-evaluation-and-cross-industry-57a4bc2e6235 | |||
11:15 | The Canonical Guide to AI Visibility Optimization (AIVO) https://medium.com/@tim_62250/the-canonical-guide-to-ai-visibility-optimization-aivo-51df5d1f22ea | |||
10:57 | From Static to Self‑Evolving: How AI Agents Learn, Adapt, and Thrive https://medium.com/@gsaidheeraj/from-static-to-self-evolving-how-ai-agents-learn-adapt-and-thrive-4a2249d874af | |||
10:57 | From Static to Self‑Evolving: How AI Agents Learn, Adapt, and Thrive https://medium.com/data-science-in-your-pocket/from-static-to-self-evolving-how-ai-agents-learn-adapt-and-thrive-4a2249d874af | |||
10:57 | Chain-of-Draft: La Rivoluzione del Ragionamento Efficiente negli LLM https://mauriziofesta.medium.com/chain-of-draft-la-rivoluzione-del-ragionamento-efficiente-negli-llm-0a9210f91a36 | |||
10:37 | Rethinking Classification in the Era of Large Language Models https://medium.com/@orimorhaim22/rethinking-classification-in-the-era-of-large-language-models-23d866ba3242 | |||
10:33 | Vinayaka Mission’s Law School (VMLS), Chennai — Shaping Future Legal Professionals https://medium.com/@monash2629/vinayaka-missions-law-school-vmls-chennai-shaping-future-legal-professionals-ba2a82589f61 | |||
10:27 | Model Context Protocol: The Universal "USB-C" for LLM Integrations https://medium.com/@tericsoft/model-context-protocol-the-universal-usb-c-for-llm-integrations-96440ccb8859 | |||
10:26 | Compliant Analysis Chatbot — 2 https://medium.com/@henocktok/compliant-analysis-chatbot-2-14b1fefb38f0 | |||
10:12 | OpenAI's Altman warns the U.S. is underestimating China's next-gen AI threat https://www.cnbc.com/2025/08/18/openai-altman-china-ai.html | |||
09:44 | on GPT-5 https://medium.com/@andrew.waggoner118/on-gpt-5-086d77364b40 | |||
09:26 | How to Use Milvus as a Vector Database in LangChain Guide https://medium.com/@Erik_Milosevic/how-to-use-milvus-as-a-vector-database-in-langchain-guide-9bf001edf03b | |||
09:18 | How to Use JavaScript with Langchain: A Step-by-Step Guide https://medium.com/@Erik_Milosevic/how-to-use-javascript-with-langchain-a-step-by-step-guide-3267297a06b6 | |||
09:08 | Personalizing LLMs for Question Answering with Feedback Based Optimization https://ai.plainenglish.io/personalizing-llms-for-question-answering-with-feedback-based-optimization-a757920a81ad | |||
09:01 | Bringing LLMs to the Internet Computer https://medium.com/dfinity/bringing-llms-to-the-internet-computer-1f6df29da2c5 | |||
09:00 | How to Load HTML Documents in LangChain: A Step-by-Step Guide https://eduardo-rogers.medium.com/how-to-load-html-documents-in-langchain-a-step-by-step-guide-77e18ddc13f2 | |||
08:51 | You Can Try Uncensored Qwen 2.5–32B Model Here: https://eduardo-rogers.medium.com/you-can-try-uncensored-qwen-2-5-32b-model-here-3560e31cc3b5 | |||
08:46 | Goodbye GEO: Why Generative Engine Optimization Is Now Legacy — and How AIVO Defines the Future of… https://medium.com/@tim_62250/goodbye-geo-why-generative-engine-optimization-is-now-legacy-and-how-aivo-defines-the-future-of-347459304ce1 | |||
08:31 | From Rigidity to Insight: A New Framework for Verifiable AI Metacognition https://medium.com/@omanyuk/from-rigidity-to-insight-a-new-framework-for-verifiable-ai-metacognition-eabc0771d605 | |||
08:26 | How to Implement JSON Chat History in Langchain Tutorial https://annie-wellington.medium.com/how-to-implement-json-chat-history-in-langchain-tutorial-6f645cbd1570 | |||
08:24 | What Happens After We Finish Reading the Internet? How to Train LLMs then? https://medium.com/data-science-collective/what-happens-after-we-finish-reading-the-internet-how-to-train-llms-then-d5e4c0cb15c0 | |||
08:15 | Tool-Augmented Generation (TAG) vs. Retrieval-Augmented Generation (RAG) https://medium.com/@tam.tamanna18/tool-augmented-generation-tag-vs-retrieval-augmented-generation-rag-d0a351514b65 | |||
08:07 | OpenAI makes GPT-5 'friendlier' after widespread user backlash https://www.pcworld.com/article/2882197/openai-makes-gpt-5-friendlier-after-widespread-user-backlash.html | |||
08:04 | To Prompt Is Human, To Specify Divine https://niklaselmqvist.medium.com/to-prompt-is-human-to-specify-is-divine-fde944049ce0 | |||
07:35 | Who Will Win the LLM War? https://gafowler.medium.com/who-will-win-the-llm-war-57f04a77870a | |||
07:25 | Citadel: A Privacy-First Framework for Secure LLM Deployment https://medium.com/commencis/citadel-a-privacy-first-framework-for-secure-llm-deployment-8b8f967a08d8 | |||
07:22 | Shipping Better Software: LLMs for Engineering & DevOps https://medium.com/@simplenight/shipping-better-software-llms-for-engineering-devops-deed3c90bf84 | |||
07:19 | Air-Gapped PaaS: AI PR Reviews (Qodo agent) & Local LLM IDE Chat (Ollama + LiteLLM) https://medium.com/@guennounbadr2/air-gapped-paas-ai-pr-reviews-qodo-agent-local-llm-ide-chat-ollama-litellm-99c9279454c2 | |||
07:18 | AI in 3 Lines of Swift Code https://erbittuu.medium.com/ai-in-3-lines-of-swift-code-dc926f388fd0 | |||
07:12 | The Cost of Conversations https://medium.com/israeli-tech-radar/the-cost-of-conversations-eb3354bdeb1c | |||
07:11 | Teaching at Scale: LLMs and the New Learning Stack https://gafowler.medium.com/teaching-at-scale-llms-and-the-new-learning-stack-d7f02729037d | |||
07:08 | Taming the AI Beast: The Role of the LLM Gateway https://medium.com/israeli-tech-radar/taming-the-ai-beast-the-role-of-the-llm-gateway-a35dd74feef7 | |||
06:14 | OpenAI eyes largest valuation for private company in stock sale talks https://www.theguardian.com/technology/2025/aug/19/openai-chatgpt-stock-sale-reports | |||
06:07 | How to build Agentic AI system with LlamaIndex https://aimlmastery.machinelearningplus.com/how-to-build-agentic-ai-system-with-llamaindex-302f087833df | |||
06:02 | MetaGPT Turns Your Ideas into a Full AI Software Team — Product Manager, Architect, and Engineer… https://medium.com/dataprophet/metagpt-turns-your-ideas-into-a-full-ai-software-team-product-manager-architect-and-engineer-8df6bd7bb7b3 | |||
05:59 | Ban ChatGPT https://benn.substack.com/p/ban-chatgpt | |||
05:57 | AI’s Hidden Limits https://medium.com/@sid.vermani/ais-hidden-limits-e8366d4fb9dc | |||
04:19 | 7 Ways AI Companies Make Large Language Models (LLMs) Faster https://medium.com/@anish.gillella/7-ways-ai-companies-make-large-language-models-llms-faster-a59ddb5ce3b7 | |||
04:18 | The Evolution of 3D Generation: Hunyuan-3D 2.0 Explained https://parthplc.medium.com/the-evolution-of-3d-generation-hunyuan-3d-2-0-explained-74e9ab1e9064 | |||
04:14 | APIs don’t make good MCP tools… https://medium.com/@bandirevanth/apis-dont-make-good-mcp-tools-151291eb55d7 | |||
04:14 | Confused by AI Hype? https://medium.com/dataprophet/confused-by-ai-hype-4cf26c982b35 | |||
03:42 | 8 Prompt Engineering Experiments Every AI Enthusiast Should Try https://tywallace2017.medium.com/8-prompt-engineering-experiments-every-ai-enthusiast-should-try-55612de5b5a2 | |||
03:32 | The Road to AGI: Why JEPA Might Succeed Where LLMs Fail https://medium.com/@dwivedi.prateek/the-road-to-agi-why-jepa-might-succeed-where-llms-fail-b20c0bbd37c0 | |||
03:27 | The Surprising Secret Behind Reliable AI Agents: It’s Not Bigger Models https://medium.com/@rogt.x1997/the-surprising-secret-behind-reliable-ai-agents-its-not-bigger-models-8ed82ea745e3 | |||
03:15 | Difference between LLM, MCP and AI Agent https://medium.com/@vyashemang/difference-between-llm-mcp-and-ai-agent-ad857bc58020 | |||
02:15 | FOSSAI: Um Manifesto Open-Source contra a Desigualdade Digital — v0.1 https://medium.com/@fernandopaladini/fossai-um-manifesto-open-source-contra-a-desigualdade-digital-v0-1-9837054d7e7e | |||
02:15 | A Step-by-step, 24-week Roadmap to Become An AI + FullStack Developer https://medium.com/@chensformers/a-step-by-step-24-week-roadmap-to-become-an-ai-fullstack-developer-531c6fbc78db | |||
02:03 | My RAG Journey: Part 1 — Document Parsing https://medium.com/@ishveen/my-rag-journey-part-1-document-parsing-2fa832866ea9 | |||
01:54 | Building a Secure Text-to-SQL Assistant with LangGraph and FastAPI https://medium.com/@b04605078123/building-a-secure-text-to-sql-assistant-with-langgraph-and-fastapi-f4d840ab87aa | |||
01:22 | Enhanced LLM-Augmented Algorithmic Trading: Practical Sentiment Analysis for Optimized Strategies https://medium.com/@adalegend/enhanced-llm-augmented-algorithmic-trading-practical-sentiment-analysis-for-optimized-strategies-9684d4e033b8 | |||
00:38 | Retrieval-Augmented Generation (RAG) Explained for Beginners https://medium.com/@shubhi2898srivastava/retrieval-augmented-generation-rag-explained-for-beginners-d972475cb710 | |||
Tuesday, 2025-08-19 | ||||
23:36 | Google Gemini’s New Features 2025: The AI Tools You Need To Try Today https://medium.com/@ferreradaniel/google-geminis-new-features-2025-the-ai-tools-you-need-to-try-today-f4bf81474bd8 | |||
23:18 | Breaking the Scaling Wall: An Introduction to Mixture of Experts in LLM https://medium.com/@keshav.agr2007/breaking-the-scaling-wall-an-introduction-to-mixture-of-experts-in-llm-f8447a337a05 | |||
23:18 | Breaking the Scaling Wall: An Introduction to Mixture of Experts in LLMs https://medium.com/@divagr1925/breaking-the-scaling-wall-an-introduction-to-mixture-of-experts-in-llm-f8447a337a05 | |||
22:55 | Into the Future: What is Agentic AI (and How You Can Try It Today?) https://medium.com/@nitesh.more22/into-the-future-what-is-agentic-ai-and-how-you-can-try-it-today-798eb4889a43 | |||
22:44 | Qwen released awesome image editing model https://medium.com/@macaipiotr/qwen-released-awesome-image-editing-model-b546fce40b85 | |||
22:12 | Building Next-Level RAG with Strategies for Better AI Answers https://medium.com/@tam.tamanna18/building-next-level-rag-with-strategies-for-better-ai-answers-7aae54e51b5e | |||
21:32 | Let’s Talk About the Work: https://medium.com/@frederickhayes3/lets-talk-about-the-work-1c98d02b4a6e | |||
21:24 | LLM vs. RAG vs. https://medium.com/@iBMehta/llm-vs-rag-vs-e05f4b92611f | |||
21:23 | Model Context Protocol(MCP): A Practical Upgrade to RAG for AI Agent Workflows https://medium.com/@m2analytics1117/model-context-protocol-mcp-a-practical-upgrade-to-rag-for-ai-agent-workflows-e4e1ec8945d5 | |||
20:57 | On-Device LLMs: What They Are, Why They Matter, and How to Ship Them https://medium.com/@gautsoni/on-device-llms-what-they-are-why-they-matter-and-how-to-ship-them-2b99f0bd6078 | |||
20:56 | Trade the Narrative: How Multimodal AI (Text + Charts) Can Improve Bitcoin & Ethereum Forecasts —… https://medium.com/@danielmachinelearning/trade-the-narrative-how-multimodal-ai-text-charts-can-improve-bitcoin-ethereum-forecasts-d10a9445a040 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124