LLM News and Articles
| Thursday, 2025-11-13 | ||||
| 10:38 | Mastering Post-Training Techniques for LLMs in 2025: Elevating Models from Generalists to… https://medium.com/@spanob562/mastering-post-training-techniques-for-llms-in-2025-elevating-models-from-generalists-to-7a5ae94c7dcd | |||
| 10:37 | Waarom AI de perfecte feedback-coach is (maar een waardeloze ghostwriter) https://medium.com/viascripta-nederlands/waarom-ai-de-perfecte-feedback-coach-is-maar-een-waardeloze-ghostwriter-9d1d012bb2f3 | |||
| 10:35 | How we stopped blocking PHP workers: A RoadRunner plugin story https://butschster.medium.com/how-we-stopped-blocking-php-workers-a-roadrunner-plugin-story-30766ce24b62 | |||
| 10:12 | I Gave a Financial AI Agent a 90% Token Diet — And It Got Smarter https://medium.com/@rodion.lim/i-gave-a-financial-ai-agent-a-90-token-diet-and-it-got-smarter-d44b65097fb2 | |||
| 10:08 | Hello GPT-5.1 — When an AI Upgrade Becomes a Field Shift https://medium.com/@peeranat.earth/hello-gpt-5-1-when-an-ai-upgrade-becomes-a-field-shift-3d4869682d5d | |||
| 09:51 | TOON (Token-Oriented Object Notation): The Smarter JSON for the LLM Era — With a Complete GenAI… https://blog.stackademic.com/toon-token-oriented-object-notation-the-smarter-json-for-the-llm-era-with-a-complete-genai-bbf19e2ef0b4 | |||
| 08:44 | Generation Control: Mastering AI Output for Better Results https://medium.com/coinmonks/generation-control-mastering-ai-output-for-better-results-6cdfc594d65c | |||
| 08:30 | When Artificial Intelligence Learns to Say “I Don’t Know (Yet)” https://medium.com/@ballurgi.rohit/when-artificial-intelligence-learns-to-say-i-dont-know-yet-8b9843ddee0d | |||
| 08:25 | How to Ship a Real AI Product Solo (and Not Go Broke) https://klaothongchan.medium.com/how-to-ship-a-real-ai-product-solo-and-not-go-broke-f529ac43c872 | |||
| 08:18 | “Grok on The Grill”, Part III-2 (*E) https://medium.com/@marc.chicha_82934/grok-on-the-grill-part-iii-2-e-b49eca6272fd | |||
| 08:11 | How I Cut My LLM Token Costs by 80% with One Line of Code https://lifeindraft.medium.com/how-i-cut-my-llm-token-costs-by-80-with-one-line-of-code-9329c0619178 | |||
| 08:07 | JSON vs TOON: How Token-Oriented Object Notation Can Slash Your LLM Costs (and Why It Matters) https://medium.com/@manishmahinia/json-vs-toon-how-token-oriented-object-notation-can-slash-your-llm-costs-and-why-it-matters-1619e2d2fda6 | |||
| 08:05 | How AI is Affecting How We Learn https://medium.com/@Alex_on_Tech/how-ai-is-affecting-how-we-learn-30521cb410c0 | |||
| 08:02 | How I Approach Any Generative AI Project Step by Step https://medium.com/@nithya-thimmaraju/how-i-approach-any-generative-ai-project-step-by-step-ed47e1a74178 | |||
| 07:48 | Why 90% of RAG Demos Never Make It to Production https://medium.com/@mannsaradva50/why-90-of-rag-demos-never-make-it-to-production-3406ff426176 | |||
| 07:16 | How to Reduce Prompt Tokens Using TOON: A Small Guide to Smarter LLM Spending https://madusanka.medium.com/how-to-reduce-prompt-tokens-using-toon-a-small-guide-to-smarter-llm-spending-2d7bfc4d1d45 | |||
| 07:10 | How Can Vanie LLM Convert Conversational Data into Actionable Insights for Fintech Growth… https://medium.com/@max.s_33396/how-can-vanie-llm-convert-conversational-data-into-actionable-insights-for-fintech-growth-1700243d3cb4 | |||
| 06:41 | Tetrix vs ChatGPT vs Claude — Who Really Understands Your System https://medium.com/deskree-ai/tetrix-vs-chatgpt-vs-claude-who-really-understands-your-system-a4da337ecc40 | |||
| 06:26 | Understanding AI Agents: Compilers of Human Intent https://levelup.gitconnected.com/understanding-ai-agents-compilers-of-human-intent-190a6de7c7ae | |||
| 06:22 | What Is the TOON Format? Discover Data Efficiency with ToonifyIt https://medium.com/@toonifyit.now/what-is-the-toon-format-discover-data-efficiency-with-toonifyit-ff768f177ea3 | |||
| 06:20 | Shrink Your LLM Bills: A Developer’s Guide to the TOON Data Format https://medium.com/@therahulpahuja/shrink-your-llm-bills-a-developers-guide-to-the-toon-data-format-75e7c13dad9e | |||
| 05:46 | The Pocket-Sized On-Device Game Changer https://medium.com/coding-nexus/the-pocket-sized-on-device-game-changer-c0be444d8b82 | |||
| 05:42 | 8 Types of LLMs You’ll See Inside AI Agents (and when to use each) https://medium.com/@mieitza/8-types-of-llms-youll-see-inside-ai-agents-and-when-to-use-each-0485f0af29c8 | |||
| 05:38 | What is the typical mistake when using AI for semantics? https://medium.com/analysts-corner/what-is-the-typical-mistake-when-using-ai-for-semantics-624ba108c589 | |||
| 05:37 | Gradient Flows and Compute–Performance Trade-offs in Intelligent Systems https://medium.com/@omanyuk/gradient-flows-and-compute-performance-trade-offs-in-intelligent-systems-4f4f6bbc963f | |||
| 05:06 | Kimi K2 Thinking https://medium.com/@tthomas1000/kimi-k2-thinking-974fc02e5a02 | |||
| 04:57 | Understanding LLM Inference https://ai.gopubby.com/understanding-llm-inference-91e6a990bc1c | |||
| 04:57 | Understanding LLM Inference https://medium.com/@harsha90145/understanding-llm-inference-91e6a990bc1c | |||
| 04:31 | The New Brutality of OpenAI https://www.theatlantic.com/technology/2025/11/openai-lawsuit-subpoenas/684861/ | |||
| 04:28 | Como os LLM’s aprenderam a te responder https://medium.com/@artur.matos_9925/como-os-modelos-de-linguagem-aprenderam-a-te-responder-ea8ee04ed808 | |||
| 04:16 | How I predicted that Google would unrank AI images https://medium.com/@corbbin/how-i-predicted-that-google-would-unrank-ai-images-6ff90ff79a9e | |||
| 03:35 | 7 Graph RAG Patterns That Transform Generic AI Answers Into Precise, Auditable Intelligence https://medium.com/@monsuralirana/7-graph-rag-patterns-that-transform-generic-ai-answers-into-precise-auditable-intelligence-792348cfd530 | |||
| 03:33 | Top LLM Papers of the Week (November Week 2, 2025) https://medium.com/@kalyanks/top-llm-papers-of-the-week-november-week-2-2025-6b768939ccc4 | |||
| 03:33 | GPT-5.1: The Next Big Leap in AI (And What It Means for You) https://ai.plainenglish.io/gpt-5-1-the-next-big-leap-in-ai-and-what-it-means-for-you-e55b448af748 | |||
| 03:14 | When Claude Told Me NO https://medium.com/@Jamie-Collins/when-claude-told-me-no-2f57d5d35e43 | |||
| 03:08 | Beyond Self-Correction: How MARA’s AI ‘Dream Team’ is Fixing Chatbot Failure https://towardsdev.com/beyond-self-correction-how-maras-ai-dream-team-is-fixing-chatbot-failure-116b1c02899f | |||
| 02:53 | LMCache v0.3.6 https://medium.com/@strong_grey_eagle_939/lmcache-v0-3-6-dca3646b8086 | |||
| 02:50 | Trusting Your AI: A Guide for Non-Technical Decision Makers https://guyernest.medium.com/trusting-your-ai-a-guide-for-non-technical-decision-makers-eb9ff11f0769 | |||
| 02:48 | How I Cut My LLM Token Costs by 80% with One Line of Code https://medium.com/coding-nexus/how-i-cut-my-llm-token-costs-by-80-with-one-line-of-code-0ac0b09461ff | |||
| 02:45 | Stop Calling LLMs as AI https://medium.com/@greekofai/stop-calling-llms-as-ai-193f85cef73d | |||
| 02:33 | 5 Surprising Truths About MCP, The AI Protocol Uniting Google and OpenAI https://medium.com/@muhammad.awais.professional/5-surprising-truths-about-mcp-the-ai-protocol-uniting-google-and-openai-37e87cf4b9e1 | |||
| 02:24 | LLMs vs RAG vs Agents in Simple Terms https://medium.com/@kalyanks/llms-vs-rag-vs-agents-in-simple-terms-4f6d94a0e1de | |||
| 02:23 | LLMs: Basics to Fine Tuning https://medium.com/emergent-intelligence/llms-basics-to-fine-tuning-3312928c128d | |||
| 01:56 | Microsoft Agent Framework https://billtcheng2013.medium.com/microsoft-agent-framework-8a36dbc4119c | |||
| 00:55 | FairEval: A Human-Aligned Evaluation Framework for Generative Models https://medium.com/@kriti0608/faireval-a-human-aligned-evaluation-framework-for-generative-models-d822bfd5c99d | |||
| 00:34 | Designing Self-Improving Autonomous AI: Persistence-First, No-Meta Governance, and Geometric… https://medium.com/@omanyuk/designing-self-improving-autonomous-ai-persistence-first-no-meta-governance-and-geometric-923164eaf1c6 | |||
| 00:32 | ZeroGPU on Hugging Face: Run Open Models for (Almost) Free https://thamizhelango.medium.com/zerogpu-on-hugging-face-run-open-models-for-almost-free-2a3c9d87fcdf | |||
| 00:05 | JustRL: When Simple Reinforcement Learning Beats Complex Training Schemes https://ai-engineering-trend.medium.com/justrl-when-simple-reinforcement-learning-beats-complex-training-schemes-a3cd29a03f98 | |||
| 00:00 | Building for an Open Future - our new partnership with Google Cloud https://huggingface.co/blog/google-cloud | |||
| Wednesday, 2025-11-12 | ||||
| 23:40 | ArXiv Labs is pausing new proposals https://blog.arxiv.org/2025/11/12/attention-arxiv-users-arxiv-labs-is-pausing-new-proposals/ | |||
| 23:16 | Salesforce May Have Just Bought the Future of Enterprise Decision-Making (And Almost Nobody… https://digitizingpolaris.com/salesforce-may-have-just-bought-the-future-of-enterprise-decision-making-and-almost-nobody-6cff14546b4d | |||
| 23:05 | Altman and Masa Back a 27-Year-Old's Plan to Build a New Bell Labs Ultra https://www.corememory.com/p/exclusive-altman-and-masa-back-episteme-louis-andre | |||
| 22:57 | Building an AI-Powered Semantic Memory System with Graph Databases and Vector Embeddings https://nikhil-datasolutions.medium.com/building-an-ai-powered-semantic-memory-system-with-graph-databases-and-vector-embeddings-adba193f916d | |||
| 22:57 | OpenAI releases GPT-5.1 alongside eight new ChatGPT personality styles https://arstechnica.com/ai/2025/11/openai-walks-a-tricky-tightrope-with-gpt-5-1s-eight-new-personalities/ | |||
| 22:32 | Meet Anannas: The Secret Weapon That Simplifies AI Model Chaos https://dibishks.medium.com/meet-anannas-the-secret-weapon-that-simplifies-ai-model-chaos-345113dc4bae | |||
| 22:21 | GPT-5.1 Instant and GPT-5.1 Thinking System Card Addendum [pdf] https://cdn.openai.com/pdf/4173ec8d-1229-47db-96de-06d87147e07e/5_1_system_card.pdf | |||
| 22:12 | If You Don’t Master AI Agents This Year, You’ll Be Playing Catch-Up Forever https://medium.com/@somo19833/if-you-dont-master-ai-agents-this-year-you-ll-be-playing-catch-up-forever-c8512226c445 | |||
| 22:06 | Andrej Karpathy reviews latest wide-release Tesla FSD version https://twitter.com/karpathy/status/1988705360723763242 | |||
| 22:04 | ⚡ Tackling the GPU Cost Crisis in AI Inference https://medium.com/@tensormesh/tackling-the-gpu-cost-crisis-in-ai-inference-1a8dce3f57ab | |||
| 21:53 | LLM Management, Explained: What, Why, When, and How (with PromptLayer, Helicone, TruLens & more) https://jewelhuq.medium.com/llm-management-explained-what-why-when-and-how-with-promptlayer-helicone-trulens-more-1ca5ccc5e25e | |||
| 21:46 | Fast, Cheap, Dangerous? Securing Code-First Agent Architectures https://idanhabler.medium.com/fast-cheap-dangerous-securing-code-first-agent-architectures-9066c1085f1c | |||
| 21:23 | OpenAI's viability called into question by reported spending with Microsoft https://www.theregister.com/2025/11/12/openai_spending_report/ | |||
| 20:59 | Show HN: ChatExport Structurer – parse ChatGPT/Claude exports into queryable SQL https://github.com/1ch1n/chat-export-structurer | |||
| 20:41 | The Ultimate Pair Programmer — Why AI Coding Needs Human Experience https://medium.com/@Jaraxal/the-ultimate-pair-programmer-why-ai-coding-needs-human-experience-6ece78e7f8ec | |||
| 20:24 | I Fought the Prompt, and I (Mostly) Won https://medium.com/womenintechnology/i-fought-the-prompt-and-i-mostly-won-1c58c30e594e | |||
| 20:22 | Retrieval-Augmented Generation (RAG): A Technical Primer for the Modern AI Stack https://medium.com/@jiyang.kang/retrieval-augmented-generation-rag-a-technical-primer-for-the-modern-ai-stack-ab0dfeec2c94 | |||
| 19:53 | LLM Output Drift in Financial Workflows: Validation and Mitigation (arXiv) https://arxiv.org/abs/2511.07585 | |||
| 19:51 | TOON Format: The Next Big Thing in Token Efficiency for LLMs https://medium.com/@amrit.01sinha/toon-format-the-next-big-thing-in-token-efficiency-for-llms-de1bf983478e | |||
| 19:41 | How high are OpenAI's compute costs? Possibly a lot higher than we thought https://www.ft.com/content/fce77ba4-6231-4920-9e99-693a6c38e7d5 | |||
| 19:37 | Agentic Workflows https://cobusgreyling.medium.com/agentic-workflows-6d2f5340c1b5 | |||
| 19:31 | From Basic RAG to Advanced Retrieval: A Practical Roadmap Using the Modern RAG Stack https://medium.com/data-science-collective/from-basic-rag-to-advanced-retrieval-a-practical-roadmap-using-the-modern-rag-stack-1185eebeed60 | |||
| 19:23 | MCP and A2A in AI Agent Protocols — Security considerations (IV) — Artificial Intelligence Risk… https://socfortress.medium.com/mcp-and-a2a-in-ai-agent-protocols-security-considerations-iv-artificial-intelligence-risk-ca6cfb23ed35 | |||
| 19:20 | General Questions Related to GPT (LLM) https://medium.com/@imsatvindersinghmavi/general-questions-related-to-gpt-llm-1f7593d436e6 | |||
| 19:10 | Your Journey From LLMs to Agents https://medium.com/@khannap2001/your-journey-from-llms-to-agents-6e9d143d2b73 | |||
| 19:05 | GPT-5.1: A smarter, more conversational ChatGPT https://openai.com/index/gpt-5-1/ | |||
| 19:02 | Perfis de inferência com Amazon Bedrock https://medium.com/senior/perfis-de-infer%C3%AAncia-com-amazon-bedrock-08bd0ac2e3a6 | |||
| 18:56 | Applications and Stages Of Large Language Models (LLMs) https://medium.com/@imsatvindersinghmavi/applications-and-stages-of-large-language-models-llms-419137355acb | |||
| 18:33 | Anthropic invests B in American AI infrastructure https://www.diffusemind.com/group/8a325136-480b-4e75-a40c-a5d254051109/index.html | |||
| 18:30 | I'm taking a three-week LLM fast https://cekrem.github.io/posts/im-taking-a-three-week-llm-fast/ | |||
| 18:17 | OpenAI fights order to turn over millions of ChatGPT conversations https://www.reuters.com/business/media-telecom/openai-fights-order-turn-over-millions-chatgpt-conversations-2025-11-12/ | |||
| 18:12 | Predatory Opt-Outs: The Speculators Come for the Anthropic Copyright Settlement https://writerbeware.blog/2025/11/07/predatory-opt-outs-the-speculators-come-for-the-anthropic-copyright-settlement/ | |||
| 18:10 | Is Your Content an Asset? How to Write for a World of AI Agents https://ai.gopubby.com/is-your-content-an-asset-how-to-write-for-a-world-of-ai-agents-097b827e57b7 | |||
| 18:06 | Detroit: Become Human is a Closer Reality Than You Think https://medium.com/@aarden.muller/detroit-become-human-is-a-closer-reality-than-you-think-b3ed40d75968 | |||
| 18:06 | Control LLM Spend and Access with any-LLM-gateway https://blog.mozilla.ai/control-llm-spend-and-access-with-any-llm-gateway/ | |||
| 18:00 | Whisper Leak side-channel attack bad actors access sensitive LLM conversations https://www.scworld.com/news/whisper-leak-side-channel-attack-lets-bad-actors-access-sensitive-llm-conversations | |||
| 17:57 | I deleted ChatGPT (and most of my other apps) https://www.dtlarson.com/feed-the-beast | |||
| 17:56 | Prompt Engineering 101: How to Talk to AI So It Understands You https://medium.com/@dharamai2024/prompt-engineering-101-how-to-talk-to-ai-so-it-understands-you-d9e924e36bb8 | |||
| 17:55 | Why We Should Use Caching in LLM and RAG-Based Applications https://medium.com/@dharamai2024/why-we-should-use-caching-in-llm-and-rag-based-applications-54daadd02e6f | |||
| 17:15 | We analyzed 47,000 ChatGPT conversations. Here's what people use it for https://www.washingtonpost.com/technology/2025/11/12/how-people-use-chatgpt-data | |||
| 16:54 | AI/ LLM Hacking — Part 7 — System Prompt Leakage | Vector & Embedding Weakness https://medium.com/@darshannnaik1234/ai-llm-hacking-part-7-system-prompt-leakage-vector-embedding-weakness-68bca76d9dd4 | |||
| 16:41 | Structuring LLM Outputs with Pydantic for Reliable AI Workflows https://pvsravanth.medium.com/structuring-llm-outputs-with-pydantic-for-reliable-ai-workflows-8ada56bf3b47 | |||
| 16:38 | How Much OpenAI Spends on Inference and Its Revenue Share with Microsoft https://www.wheresyoured.at/oai_docs/ | |||
| 16:35 | 10 Modelos de IA Líderes em Benchmark de Tarefas Jurídicas https://medium.com/@phalaportugues/10-modelos-de-ia-l%C3%ADderes-em-benchmark-de-tarefas-jur%C3%ADdicas-cb9fdf3a79d6 | |||
| 16:30 | LLM hype on Social Media vs in professional life https://medium.com/ai-analytics-diaries/llm-hype-on-social-media-vs-in-professional-life-78fff2738339 | |||
| 16:23 | Grok vs ChatGPT: 2025 LLM Battle — Features, APIs & Benchmarks https://medium.com/@gjak675/grok-vs-chatgpt-2025-llm-battle-features-apis-benchmarks-37518a16f305 | |||
| 16:21 | Baidu releases open-source multimodal AI that it claims beats GPT-5 and Gemini https://venturebeat.com/ai/baidu-just-dropped-an-open-source-multimodal-ai-that-it-claims-beats-gpt-5 | |||
| 16:17 | The PowerPC Has Still Got It (Llama on G4 Laptop) https://www.hackster.io/news/the-powerpc-has-still-got-it-c4348bd7a88c | |||
| 16:11 | Building an Intelligent Hashing Cache System for AI Reports https://medium.com/@95jaymishra/building-an-intelligent-hashing-cache-system-for-ai-reports-42b1ed26367a | |||
| 16:06 | Breaking the Web Scraping Barrier: Building an Autonomous Web Crawler with AI https://medium.com/@aswin.rs/breaking-the-web-scraping-barrier-building-an-autonomous-web-crawler-with-ai-2f0144f76c30 | |||
| 16:05 | China’s AI Amid Chip Shortages: A Silent Battle for Resources https://ai-engineering-trend.medium.com/chinas-ai-amid-chip-shortages-a-silent-battle-for-resources-5a155716eaab | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124