LLM News and Articles
Wednesday, 2024-12-25 | ||||
17:37 | Papers Explained 1: Mistral 7B https://ai.plainenglish.io/papers-explained-1-mistral-7b-42810879ad45 | |||
17:12 | RAG: The AI That Fact-Checks Before It Speaks https://medium.com/@heshangoonawardena/rag-the-ai-that-fact-checks-before-it-speaks-d3f15e21c9fb | |||
16:43 | Real-Time Text and Voice-Based Retrieval Augmented Generation Pipeline with Gemini 2.0 https://itnext.io/real-time-text-and-voice-based-retrieval-augmented-generation-pipeline-with-gemini-2-0-707fadf73027 | |||
16:33 | Pydantic AI: AI Agent Library https://medium.com/@naresh.kancharla/pydantic-ai-ai-agent-library-021e7983d4c8 | |||
16:18 | Development of Robust AI agents https://fahadthedatascientist.medium.com/development-of-robust-ai-agents-dc331544e150 | |||
16:01 | QVQ-72B: The Ultimate Visual Reasoning AI You Can Run Locally https://pub.towardsai.net/qvq-72b-the-ultimate-visual-reasoning-ai-you-can-run-locally-0496f6747e65 | |||
15:39 | Building आकार AI: Transforming Enterprise Report Generation with LlamaIndex https://medium.com/@dwivedimav/building-%E0%A4%86%E0%A4%95%E0%A4%BE%E0%A4%B0-ai-transforming-enterprise-report-generation-with-llamaindex-9c2a66524fa8 | |||
15:11 | Building a Multi-agent Internet Research Assistant https://mlubbad.medium.com/building-a-multi-agent-internet-research-assistant-ebd9c5afad04 | |||
14:58 | Qwen2.5: Redefining Efficiency in Large Language Models https://ai.gopubby.com/qwen2-5-redefining-efficiency-in-large-language-models-c12f107f20ff | |||
14:41 | Defeating AI: A Detailed Security Testing Adventure with Gandalf AI https://medium.com/@a.k.yuksel/defeating-ai-a-detailed-security-testing-adventure-with-gandalf-ai-579ff22abdc7 | |||
14:26 | The Open-Source LLM Revolution: Gemma, Llama 2, and Mistral 7B https://medium.com/@frankmorales_91352/the-open-source-llm-revolution-gemma-llama-2-and-mistral-7b-ccf33208883f | |||
13:54 | From juicer to C3PO. A simple explanation of where artificial intelligence begins. https://medium.com/@marcin.maculewicz/from-juicer-to-c3po-a-simple-explanation-of-where-artificial-intelligence-begins-2caad75c9ec0 | |||
13:48 | Step for model development and deployment https://medium.com/@sajidaziz/step-for-model-development-and-deployment-843001e62d3b | |||
13:48 | How to find Tuned a model https://medium.com/@sajidaziz/how-to-find-tuned-a-model-7a8819a5cca6 | |||
13:48 | Refer below link for details https://medium.com/@sajidaziz/refer-below-link-for-details-107e6807050b | |||
12:47 | Open Source in the Age of AI: A Guide for Executives to 2025 https://medium.com/@edulabs/open-source-in-the-age-of-ai-a-guide-for-executives-to-2025-8caf580eb68e | |||
11:30 | The Data Advantage: Why Every Software Engineer Needs Analytics Know-How https://pedrovallese.medium.com/the-data-advantage-why-every-software-engineer-needs-analytics-know-how-3e08172530fe | |||
11:17 | Top 5 OpenAI o1 and o3 Alternatives — Cheaper and Faster! https://medium.com/@probirds.ni/top-5-openai-o1-and-o3-alternatives-cheaper-d976b80167c1 | |||
10:54 | From Prompt-Tuned LLMs to Agentic AI: A Deep Dive into the Evolution of Intelligent Systems https://medium.com/@utkarshpatidar170/from-prompt-tuned-llms-to-agentic-ai-a-deep-dive-into-the-evolution-of-intelligent-systems-8ac9b2925b22 | |||
10:34 | Pdf Parsing Techniques https://medium.com/@sudarshan-koirala/pdf-parsing-techniques-682d7750420f | |||
10:25 | Training & Fine-Tuning Your LLMs https://jananithinks.medium.com/training-fine-tuning-your-llms-4db4118bbc21 | |||
09:39 | AI Wrapped 2024: A Year of Transformation and Innovation https://medium.com/@tarifabeach/ai-wrapped-2024-a-year-of-transformation-and-innovation-bdc430b49c52 | |||
09:31 | Thoughts on Practical Business Applications of Agent Systems Based on Large Language Models https://medium.com/@denisromanovsky/thoughts-on-practical-business-applications-of-agent-systems-based-on-large-language-models-7b30ee40e9be | |||
09:20 | Setup 100% Free and Local Production Grade LLM Observability in 10 minutes using Langfuse https://medium.com/@vanshkharidia7/setup-100-free-and-local-production-grade-llm-observability-in-10-minutes-using-langfuse-031877effc07 | |||
09:14 | The AI Powered Digital Swiss Army Knife https://shilpasrikarra.medium.com/the-ai-powered-digital-swiss-army-knife-c2c8a5c0c601 | |||
09:14 | Palantir and Anduril Form Tech Consortium to Bid on U.S. Defense Contracts https://medium.com/@datacake.ai/palantir-and-anduril-form-tech-consortium-to-bid-on-u-s-defense-contracts-6321de60be7e | |||
08:41 | Forwarding Streaming Response in Real-Time https://medium.com/@kirtan141100/forwarding-streaming-response-in-real-time-7beda49eeb19 | |||
08:17 | LangChain: Automating Large Language Model (LLM) Evaluation https://medium.com/@sarayavalasaravikiran/langchain-automating-large-language-model-llm-evaluation-411c3ec37a0b | |||
08:13 | Dear colleagues and students working on large language models (LLMs) and programming languages, https://medium.com/@saciptoker.misc/dear-colleagues-and-students-working-on-large-language-models-llms-and-programming-languages-3b5feef52ec2 | |||
08:01 | Qwen QVQ-72B: Best open-sourced Image Reasoning LLM https://medium.com/data-science-in-your-pocket/qwen-qvq-72b-best-open-sourced-image-reasoning-llm-95b474d3b9a0 | |||
07:50 | Benchmarking Large Language Models: A Comprehensive Overview https://medium.com/@frankmorales_91352/benchmarking-large-language-models-a-comprehensive-overview-e54621d00d4b | |||
07:50 | Benchmarking Large Language Models: A Comprehensive Overview https://medium.com/thedeephub/benchmarking-large-language-models-a-comprehensive-overview-e54621d00d4b | |||
07:37 | Preventing Model Swapping In Ollama — A Guide To Persistent Loading https://medium.com/@noel.B/preventing-model-swapping-in-ollama-a-guide-to-persistent-loading-f81f1dfb858d | |||
07:12 | Mastering the Art of Training One Large Language Model to Precisely Mimic the Another LLM: A Deep… https://medium.com/@rakesh.sheshadri44/mastering-the-art-of-training-one-large-language-model-to-precisely-mimic-the-another-llm-a-deep-4808ba7a1079 | |||
07:05 | The Gen AI Breakthrough: What It Can Do, What It Can’t, and What Lies Ahead https://medium.com/@manishb2km/the-gen-ai-breakthrough-what-it-can-do-what-it-cant-and-what-lies-ahead-9229be1e00a7 | |||
06:56 | HuggingChat is the One LLM App You Shouldn’t Overlook https://ai.plainenglish.io/huggingchat-is-the-one-llm-app-you-shouldnt-overlook-2f391ddd6e7f | |||
06:48 | “I’m Not a Math Pro or Ph.D. Holder, but I Cracked Machine Learning with This Simple Approach” https://medium.com/@verma75preetam/im-not-a-math-pro-or-ph-d-holder-but-i-cracked-machine-learning-with-this-simple-approach-58a9966606e5 | |||
06:12 | Conversational Prompt Engineering: Simplify Prompt Design and Unlock Better LLM Outputs https://medium.com/@himanshu_72022/conversational-prompt-engineering-simplify-prompt-design-and-unlock-better-llm-outputs-7238e52798a3 | |||
05:44 | Show HN: I made a website to semantically search ArXiv papers https://papermatch.mitanshu.tech/ | |||
05:38 | Are LLMs Killing Creativity? My Brain Feels Like Oatmeal, and I Blame the Robots! https://sheriffjbabu.medium.com/are-llms-killing-creativity-my-brain-feels-like-oatmeal-and-i-blame-the-robots-6587088f00df | |||
05:13 | Can we have custom knowledge base with Gemini apis ? https://medium.com/@urwithdhanu/can-we-have-custom-knowledge-base-with-gemini-apis-0ecdab5654c2 | |||
05:11 | Qwen Team Releases QvQ: An Open-Weight Model for Multimodal Reasoning https://www.marktechpost.com/2024/12/24/qwen-team-releases-qvq-an-open-weight-model-for-multimodal-reasoning/ | |||
05:07 | A Comprehensive Overview and Study Guide for Amazon Q Business https://medium.com/@rafa.xu.au/a-comprehensive-overview-and-study-guide-for-amazon-q-business-533a171380cd | |||
04:42 | Scaling Smarter: An Overview of Large Language Models (LLMs) and Their Compression Techniques Part… https://medium.com/@deniz.kenan.kilic/scaling-smarter-an-overview-of-large-language-models-llms-and-their-compression-techniques-part-4e6bc846c215 | |||
04:41 | Scaling Smarter: An Overview of Large Language Models (LLMs) and Their Compression Techniques Part… https://medium.com/@deniz.kenan.kilic/scaling-smarter-an-overview-of-large-language-models-llms-and-their-compression-techniques-part-c983fc674c96 | |||
04:31 | KAG (Knowledge Augmented Generation): A Step Beyond RAG https://umeey.medium.com/kag-knowledge-augmented-generation-a-step-beyond-rag-a86925694a01 | |||
03:53 | The Rise and Evolution of RAG in 2024: A Year in Review https://medium.com/@infiniflowai/the-rise-and-evolution-of-rag-in-2024-a-year-in-review-9a0dbc9ea5c9 | |||
03:41 | Breaking Barriers on 2025: Google DeepMind’s Game-Changing AI Innovations https://medium.com/@rameshkannanyt0078/breaking-barriers-on-2025-google-deepminds-game-changing-ai-innovations-65383a9e5690 | |||
02:33 | Sinusoidal Embeddings: How Transformers Interpret Tokens Positions https://medium.com/@giovanitavares/sinusoidal-embeddings-how-transformers-interpret-tokens-positions-bd701babb508 | |||
01:38 | OpenAI’s o3 Model: Scaling AI Capabilities at a Higher Cost https://medium.com/@datacake.ai/openais-o3-model-scaling-ai-capabilities-at-a-higher-cost-57f281abc022 | |||
Tuesday, 2024-12-24 | ||||
22:14 | From Blank Canvas to Finished Product: How LLMs Transform Software Development — and the Golden… https://medium.com/@mboiman/from-blank-canvas-to-finished-product-how-llms-transform-software-development-and-the-golden-db26d6abce88 | |||
21:11 | Building a GUI for Image Background Removal with wxPython and RemBG https://blog.gopenai.com/building-a-gui-for-image-background-removal-with-wxpython-and-rembg-63a10867be12 | |||
21:04 | THE FULL LLMs DICTIONARY https://medium.com/@origoldbsc/the-full-llms-dictionary-28cf6fac636b | |||
21:04 | RobustFT: framework for Robust Supervised Fine-tuning of LLMs under noisy response https://medium.com/@techsachin/robustft-framework-for-robust-supervised-fine-tuning-of-llms-under-noisy-response-f54ea2800057 | |||
20:31 | 2025 Enterprise Data & AI Trends: Agents, Platforms, and Moonshots https://sanjmo.medium.com/2025-enterprise-data-ai-trends-agents-platforms-and-moonshots-0010c8b4d1f3 | |||
19:57 | OWASP Principles for Securing Large Language Models https://medium.com/@zbabar/owasp-principles-for-securing-large-language-models-2fcfed187c83 | |||
19:34 | Fine-Tuning Gemma2 Models for Tamil News Translation with HuggingFace BnB, Uploading Model Weights… https://abishpius.medium.com/fine-tuning-gemma2-models-for-tamil-news-translation-with-huggingface-bnb-uploading-model-weights-7cfd1281e2ad | |||
18:48 | LLM-friendly Knowledge Representation for Augmented Generation and Reasoning https://sbagency.medium.com/llm-friendly-knowledge-representation-for-augmented-generation-and-reasoning-8602a4ebec63 | |||
18:35 | What is LLM? https://medium.com/@vigneshn/what-is-llm-8b711a20927a | |||
18:07 | Building a Knowledge Stack: My Journey as a Computer Programmer (Scientist) https://medium.com/@aadharshideal/building-a-knowledge-stack-my-journey-as-a-computer-programmer-scientist-005a2010c5f8 | |||
17:58 | Building an Enterprise Chatbot with LangChain https://medium.com/@karolbhandari666/building-an-enterprise-chatbot-with-langchain-08442aa7e767 | |||
17:27 | Language Embedding: A Geographical Map Analogy https://medium.com/@ste.rota/language-embedding-a-geographical-map-analogy-aa39d594b13a | |||
17:01 | A Framework for Enhanced Agentic AI: Smarter, Safer, and Scalable Systems https://dr-arsanjani.medium.com/a-framework-for-enhanced-agentic-ai-smarter-safer-and-scalable-systems-d14f8b15c77e | |||
16:58 | Frameworks of LLMs — Langchain and Llama Index https://praveenkrishna.medium.com/frameworks-of-llms-langchain-and-llama-index-000fb4cfbe7e | |||
16:39 | Google is using Anthropic's Claude to improve Gemini https://techcrunch.com/2024/12/24/google-is-using-anthropics-claude-to-improve-its-gemini-ai/ | |||
16:23 | Building a Multi Agent based — “Auto Recursive” — Plan , Execute, Re-Plan Process https://medium.com/@nayan.j.paul/building-a-multi-agent-based-auto-recursive-plan-execute-re-plan-process-4f17a270078c | |||
15:52 | AI-ce breakers: AI-powered question generator https://medium.com/@isa.dario.isa/ai-ce-breakers-ai-powered-question-generator-8c0900b99ac6 | |||
15:36 | Top 5 OpenAI o1 and o3 Alternatives — Best Reasoning Models https://medium.com/@probirds.ni/openai-o1-and-o3-alternatives-577b7ad3ead3 | |||
15:07 | Prompts: Communication with LLMs https://praveenkrishna.medium.com/prompts-communication-with-llms-af3298bd4773 | |||
15:01 | Exploring “Langfuse” — An open-source LLM Engineering Platform https://ajay-arunachalam08.medium.com/exploring-langfuse-an-open-source-llm-engineering-platform-38cf5fe746e6 | |||
14:38 | Building Effective AI Agents for Beginners https://medium.com/@alexglushenkov/building-effective-ai-agents-for-beginners-4276d179e514 | |||
14:31 | TAI 131: OpenAI’s o3 Passes Human Experts; LLMs Accelerating With Inference Compute Scaling https://pub.towardsai.net/tai-131-openais-o3-passes-human-experts-llms-accelerating-with-inference-compute-scaling-2e819e93d457 | |||
13:56 | 5 WAYS TO RUN LLMS LOCALLY WITHOUT INTERNET https://mlubbad.medium.com/5-ways-to-run-llms-locally-without-internet-fa27ceb5d043 | |||
13:37 | O que é um LLM? Entenda de Forma Simples! https://epma.medium.com/o-que-%C3%A9-um-llm-entenda-de-forma-simples-3d0deb27e340 | |||
13:21 | LangChain Series — 2 — Automating Insights with Python and AI: A Simple Movie Query Example https://neuralnotes.medium.com/langchain-series-2-automating-insights-with-python-and-ai-a-simple-movie-query-example-9ce2e12c914b | |||
12:32 | From Words to Concepts: Ushering in the Next Era of AI with LCM https://medium.com/@alexglushenkov/from-words-to-concepts-ushering-in-the-next-era-of-ai-with-lcm-ac70e6233d9c | |||
12:01 | Llm Fine Tuning Guide: Do You Need It and How to Do It https://pub.towardsai.net/llm-fine-tuning-guide-do-you-need-it-and-how-to-do-it-d9bf7ce164c6 | |||
11:37 | Bitnet : Enerji Probleminin Yeni Umudu https://medium.com/@cenghanbayram35/bitnet-enerji-probleminin-yeni-umudu-bb64d1941d41 | |||
11:19 | BitNet su CPU: i miei appunti su installazione e vantaggi LLM 1.58 Bits https://andreabelvedere.medium.com/bitnet-su-cpu-i-miei-appunti-su-installazione-e-vantaggi-llm-1-58-bits-4a553c8f2af9 | |||
10:52 | Digital Immortality are just LLM’s trained on yourself https://medium.com/@angel__/digital-immortality-are-just-llms-trained-on-yourself-ffb77b2855aa | |||
10:12 | Building a Web-Enhanced Self-Reflecting Agent with Haystack Llama 3.2 and Ollama in Google colab https://medium.com/@sahin.samia/building-a-web-enhanced-self-reflecting-agent-with-haystack-llama-3-2-and-ollama-in-google-colab-2bf6a864fd7e | |||
10:02 | Turning LLMs Into AI Agents https://ai.gopubby.com/turning-llms-into-ai-agents-b51bb1d5d569 | |||
10:02 | Turning LLMs Into AI Agents https://iamshobhitagarwal.medium.com/turning-llms-into-ai-agents-b51bb1d5d569 | |||
10:02 | Turning LLMs Into AI Agents https://generativeai.pub/turning-llms-into-ai-agents-b51bb1d5d569 | |||
09:38 | Fine tuning method for Large Language Models (LLMs) https://medium.com/@arpitpadwekar/fine-tuning-method-for-large-language-models-llms-5e136ddc696c | |||
09:32 | batch.md https://medium.com/@codewithdark/batch-md-69183112f567 | |||
09:22 | Augmenting a Large Language Model with Retrieval-Augmented Generation and Fine-tuning https://medium.com/@ashishsingh.chunar2017/augmenting-a-large-language-model-with-retrieval-augmented-generation-and-fine-tuning-38e6a9267114 | |||
09:21 | Ollama x Open-WebUI: ChatGPT Lokal Gratis Tanpa Batas! https://medium.com/@rizal_hilman/ollama-x-open-webui-chatgpt-lokal-gratis-tanpa-batas-aa771df35611 | |||
09:07 | ChatGPT search tool vulnerable to manipulation and deception, tests show https://www.theguardian.com/technology/2024/dec/24/chatgpt-search-tool-vulnerable-to-manipulation-and-deception-tests-show | |||
08:21 | Roadmap to Becoming an NLP and LLM Expert https://shangaganjot.medium.com/roadmap-to-becoming-an-nlp-and-llm-expert-84755746dc67 | |||
08:01 | Programming AI: The Role of Code in Advancing LLMs https://tekinmuhammed.medium.com/programming-ai-the-role-of-code-in-advancing-llms-c1dfb6c1a036 | |||
07:01 | Could AI be the Copilot you always wanted for stock-market research?Let’s Find Out https://medium.datadriveninvestor.com/could-ai-be-the-copilot-you-always-wanted-for-stock-market-research-lets-find-out-cb0f9e25691c | |||
06:57 | Web Scraping with LLMs-ChatGroq https://ai.plainenglish.io/web-scraping-with-llms-chatgroq-8054f198729f | |||
06:54 | Fine-Tuning Embeddings for RAG Applications https://medium.com/@ailabs/fine-tuning-embeddings-for-rag-applications-272165a31b4a | |||
06:20 | What is the Web LLM Attack? https://medium.com/@info_79425/what-is-the-web-llm-attack-578f0dff39fa | |||
05:38 | Docling: Your Linguistic Detective for Document Analysis https://medium.com/@jshaik2452/docling-your-linguistic-detective-for-document-analysis-77b7ff2b33c8 | |||
04:52 | LangChain Series -1 — Unlocking the Power of LangChain: A Beginner’s Introduction https://neuralnotes.medium.com/langchain-series-1-unlocking-the-power-of-langchain-a-beginners-introduction-5fce56892971 | |||
03:37 | Force LLM to Answer “Yes” or “No” https://medium.com/@tomo_38285/intro-09d52269a79d | |||
02:44 | Mathematics, Coding, Neural Networks, and the Future of Computation https://medium.com/@nmirbakhsh/mathematics-coding-neural-networks-and-the-future-of-computation-9c58285109e3 | |||
02:32 | Apple’s AI Gambit: A New Era of Innovation and Competition https://medium.com/thedeephub/apples-ai-gambit-a-new-era-of-innovation-and-competition-8320189078ba |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227