LLM News and Articles
| Friday, 2024-08-02 | ||||
| 07:56 | How LLaMA-Adapter Beats LoRA https://medium.com/@edmond.po/how-llama-adapter-beats-lora-deep-fusion-in-record-time-86bcecbab08f | |||
| 07:52 | Zuckerberg says Meta will need 10x more computing power to train Llama 4 than Llama 3 https://medium.com/augmented-startups/zuckerberg-says-meta-will-need-10x-more-computing-power-to-train-llama-4-than-llama-3-5a57a2a5486a | |||
| 07:48 | Using Snowflake for AI completion in Manychat https://medium.com/manychat-engineering/using-snowflake-for-ai-completion-in-manychat-10fe3a152c47 | |||
| 07:41 | LLMOps- A guide towards from becoming Zero to Hero https://medium.com/@manoranjan.rajguru/llmops-a-guide-towards-from-becoming-zero-to-hero-99457b60fa19 | |||
| 07:34 | Twilio Is Looking For Startups Before September 29th https://blog.gopenai.com/twilio-is-looking-for-startups-before-september-29th-0f721d460b37 | |||
| 07:34 | Top 6 Chatbot Apps for Android in 2024 https://medium.com/@devashish_m/top-6-chatbot-apps-for-android-in-2024-0c6914c65a58 | |||
| 07:20 | Model Collapse in AI https://medium.com/thedeephub/model-collapse-in-ai-813418fd8516 | |||
| 07:17 | Feedback Loops in Generative AI: How AI May Shoot Itself in the Foot https://medium.com/@anthony.demeusy/feedback-loops-in-generative-ai-how-ai-may-shoot-itself-in-the-foot-3c16b16fc1d7 | |||
| 07:16 | Adv. LLM Integration: Enhancing Agricultural Machinery https://medium.com/@ramakrushnamohapatra/adv-llm-integration-enhancing-agricultural-machinery-ab05ad668a93 | |||
| 07:13 | CodeMapper: Your AI’s Guide to Understanding Code https://medium.com/@mbonsign/codemapper-your-ais-guide-to-understanding-code-ef2bda7f333e | |||
| 07:05 | ChatGPT Citing Plagiarized Versions of NYT Articles on an Armenian Content Mill https://futurism.com/chatgpt-plagiarized-nyt-articles | |||
| 06:59 | Segment Anything Model 2 (SAM 2) + GPT-4o — Cascading Foundation Models via Visual Prompting —… https://medium.com/@tenyks_blogger/segment-anything-model-2-sam-2-gpt-4o-cascading-foundation-models-via-visual-prompting-76158ff0b9f4 | |||
| 06:58 | Running Mistral Models with Hugging Face or Ollama https://medium.com/@researchgraph/running-mistral-models-with-hugging-face-or-ollama-5bb63770d985 | |||
| 05:52 | Show HN: I built Choosy Chat to get the best answer between GPT, Claude, Gemini https://www.choosy.chat/ | |||
| 05:50 | Salesforce AI Introduces ‘ThinK’: A New AI Method that Exploits Substantial Redundancy Across the Channel Dimension of the KV Cache https://www.marktechpost.com/2024/08/01/salesforce-ai-introduces-think-a-new-ai-method-that-exploits-substantial-redundancy-across-the-channel-dimension-of-the-kv-cache/ | |||
| 05:42 | LLM Chains using SequentialChain, RouterChain https://bobrupakroy.medium.com/llm-chains-using-sequentialchain-routerchain-964c9aa14f8b | |||
| 05:29 | The Revolution of Large Language Models: From ChatGPT-3 to Llama3.1 https://medium.com/@zuhayr.codes/the-revolution-of-large-language-models-from-chatgpt-3-to-llama3-1-3ad8c400c9b6 | |||
| 04:37 | Building AI-Powered Web Applications In 20 Minutes with FriendliAI, Vercel AI SDK, and Next.js https://medium.com/@friendli.ai/building-ai-powered-web-applications-in-20-minutes-with-friendliai-vercel-ai-sdk-and-next-js-c2f03c7fbaf9 | |||
| 04:19 | Level Up Your Client-Side Interactions with Friendli’s gRPC Support https://medium.com/@friendli.ai/level-up-your-client-side-interactions-with-friendlis-grpc-support-9864f44d79a0 | |||
| 04:07 | AI at Your Fingertips, Anytime, Anywhere. https://acubeddu87.medium.com/ai-at-your-fingertips-anytime-anywhere-3c722d8879f4 | |||
| 03:48 | Inside Apple’s AI: Understanding the Architecture and Innovations of AFM Models https://medium.com/@vantuandang1990/inside-apples-ai-understanding-the-architecture-and-innovations-of-afm-models-e6638988e257 | |||
| 03:39 | OpenAI rolls out voice mode after delaying it for safety reasons https://www.washingtonpost.com/technology/2024/07/30/openai-voice-mode-launch-sky-scarlett-johansson/ | |||
| 03:32 | Understanding Penetration Testing with LLMs https://blog.gopenai.com/understanding-penetration-testing-with-llms-2b0ec6add14a | |||
| 03:26 | RAG on CSV data with Knowledge Graph- Using RDFLib, RDFLib-Neo4j, and Langchain https://medium.com/@fatimaparada.taboada/rag-on-csv-data-with-knowledge-graph-using-rdflib-rdflib-neo4j-and-langchain-4b12a114a20e | |||
| 03:17 | AGENTGEN framework : enhancing LLM based Agents planning abilities via Environment and Task… https://medium.com/@techsachin/agentgen-framework-enhancing-llm-based-agents-planning-abilities-via-environment-and-task-dc5b67c49896 | |||
| 03:13 | Robotic Grasping with Visual-Linguistic Framework https://medium.com/@faiz.neet/robotic-grasping-with-visual-linguistic-framework-863f73697ec6 | |||
| 03:02 | Top 3 Generative AI Courses 2024 https://augmentedstartups.medium.com/top-3-generative-ai-courses-2024-f9cc4ddd372a | |||
| 02:59 | The Rise of the LLM OS: From AIOS to MemGPT and Beyond https://medium.com/@messouaboya17/the-rise-of-the-llm-os-from-aios-to-memgpt-and-beyond-513177680359 | |||
| 02:52 | “Moore’s Law” for AI? https://medium.com/mirabolic/moores-law-for-ai-88e93e9ef41a | |||
| 02:24 | Understanding Quantization in Large Language Models (LLMs) https://medium.com/@messouaboya17/understanding-quantization-in-large-language-models-llms-1d1ccedb8acb | |||
| 02:17 | The AI Reliability Challenge: Fine-Tuning, Prompting, or RAG — Who Takes the Crown? https://generativeai.pub/the-ai-reliability-challenge-fine-tuning-prompting-or-rag-who-takes-the-crown-bb7d33b9e34e | |||
| 02:05 | How to Fine-Tune Llama 3.1 (8B Instruct) https://medium.com/@rschaeffer23/how-to-fine-tune-llama-3-1-8b-instruct-bf0a84af7795 | |||
| 01:16 | Use GPT-4o-mini free of charge in JavaScript/TypeScript https://github.com/mumu-lhl/duckduckgo-ai-chat | |||
| 01:16 | Building a Legal LLM RAG System using NZ Court Judgements https://medium.com/@ningchen914/building-a-legal-llm-rag-system-a-step-by-step-tutorial-using-nz-court-judgements-671fe7baba4a | |||
| 00:38 | Using generative AI in a rule-based decision https://medium.com/@pberlandier/using-generative-ai-in-a-rule-based-decision-32b67bb91403 | |||
| 00:38 | Using generative AI in a rule-based decision https://medium.com/ibm-cloud-pak-for-automation/using-generative-ai-in-a-rule-based-decision-32b67bb91403 | |||
| 00:14 | Intelligent Automation Framework (IAF) https://systemdesigner.medium.com/intelligent-automation-framework-iaf-6d5bc759f61f | |||
| Thursday, 2024-08-01 | ||||
| 23:42 | How to run a LLM locally with a ChatGPT like interface https://medium.com/@devhanif/how-to-run-a-llm-locally-with-a-chatgpt-like-interface-9e5ec8092cc3 | |||
| 23:36 | Crazy Challenge: Run Llama 405B on a 8GB VRAM GPU https://ai.gopubby.com/crazy-challenge-run-llama-405b-on-a-8gb-vram-gpu-ab5a280a3889 | |||
| 23:22 | Prompt “Engineering” for Engineers https://medium.com/@navdeepsharma/prompt-engineering-for-engineers-b75833a9c4af | |||
| 22:44 | Re: The End of Software https://medium.com/@impure/re-the-end-of-software-d04dad5d1022 | |||
| 22:33 | Using Google Colab to run LLM Models https://medium.com/@researchgraph/using-google-colab-to-run-llm-models-8c308cac6efa | |||
| 22:06 | The Evolution and Impact of Large Language Models https://medium.com/@maheshpshankar/the-evolution-and-impact-of-large-language-models-ab4ce44adefb | |||
| 22:02 | Build Product Knowledge Graph using LLM https://pub.towardsai.net/build-product-knowledge-graph-using-llm-a0d0354156ac | |||
| 21:11 | Your AI is Only as Smart as Your Data: The Key to Unlocking LLM and RAG Potential https://maddyarvapally.medium.com/your-ai-is-only-as-smart-as-your-data-the-key-to-unlocking-llm-and-rag-potential-7ca8e1e7fc5c | |||
| 20:56 | Q & A ChatBot — A Generative AI Application Using Large Language Models https://medium.com/@pankaja.ambalgi/q-a-chatbot-a-generative-ai-application-using-large-language-models-ce4119f70c2f | |||
| 20:41 | LLMs (Büyük Dil Modelleri) https://medium.com/@umutsahinn1/llms-b%C3%BCy%C3%BCk-dil-modelleri-aeca2bc820b7 | |||
| 20:02 | Sam Altman-Backed Rain AI Hires Apple Chip Vet to Lead Hardware https://www.bloomberg.com/news/articles/2024-06-28/sam-altman-backed-rain-ai-hires-apple-chip-vet-to-lead-hardware | |||
| 20:01 | Using Snowflake for AI completion in Manychat https://medium.com/snowflake/using-snowflake-for-ai-completion-in-manychat-37bfaa914f8c | |||
| 19:32 | Smaller Yet Superior: Why Chinchilla’s Approach to Training Data Is a Game-Changer https://pub.aimind.so/smaller-yet-superior-why-chinchillas-approach-to-training-data-is-a-game-changer-68e8bfa1e56c | |||
| 19:28 | Harnessing OpenDevin: A Versatile Platform for AI-Driven Software Development and Multi-Agent… https://readquick.medium.com/harnessing-opendevin-a-versatile-platform-for-ai-driven-software-development-and-multi-agent-1a0d83184e5c | |||
| 19:13 | Show HN: Code to run Gemma2-2B on a Mac – a powerful model with GPT 3.5 perf https://github.com/notnotrishi/mlxcli | |||
| 19:11 | The Fundamental Importance of MMR in Social Media Algorithms https://medium.com/@mario.pba/the-fundamental-importance-of-mmr-in-social-media-algorithms-31335c51b2cb | |||
| 18:57 | RAG vs. Long-Context LLMs: A Comprehensive Study with a Cost-Effective Hybrid Approach https://blog.gopenai.com/rag-vs-long-context-llms-a-comprehensive-study-with-a-cost-effective-hybrid-approach-3e8df1e7ad33 | |||
| 18:25 | Paper Review: Generative Agents: Interactive Simulacra of Human Behaviour https://medium.com/@dataism/paper-review-generative-agents-interactive-simulacra-of-human-behaviour-a16ae12b103e | |||
| 18:11 | Part B of The Pictures That Bots Made: Visions of 2224 and Sir Bot Bot https://medium.com/@aleksmilanov/part-b-of-the-pictures-that-bots-made-visions-of-2224-and-sir-bot-bot-35c1d526094e | |||
| 18:02 | A Deep Dive Into Model Quantization https://pub.towardsai.net/a-deep-dive-into-model-quantization-529c489f72b8 | |||
| 17:56 | Llama 3.1: The AI Powerhouse That’s Got Me Hooked https://medium.com/@saisupriya.varu/llama-3-1-the-ai-powerhouse-thats-got-me-hooked-8bd7eb582a35 | |||
| 17:53 | Creating and Deploying an LLM Application Using AWS Bedrock, AWS Lambda, and AWS API Gateway https://kshitijkutumbe.medium.com/creating-and-deploying-an-llm-application-using-aws-bedrock-aws-lambda-and-aws-api-gateway-557d6de140e8 | |||
| 17:49 | Beating GPT-4o and Claude 3.5 on SWE-bench Lite through repeated sampling https://arxiv.org/abs/2407.21787 | |||
| 17:44 | O'Reilly Answers: A case study of poorly designed LLM powered RAG system https://shekhargulati.com/2024/08/01/oreilly-answers-a-case-study-of-poorly-designed-llm-powered-rag-system/ | |||
| 17:42 | Building a RAG Pipeline with MongoDB: Vector Search for Personalized Movie Picks https://medium.com/@pablomerchanrivera/building-a-rag-pipeline-with-mongodb-vector-search-for-personalized-movie-picks-46a58a2aaac9 | |||
| 17:42 | Text-to-SQL Excellence: An Evaluation of Sonnet 3.5 and GPT-4o https://medium.com/querymind/text-to-sql-excellence-an-evaluation-of-sonnet-3-5-and-gpt-4o-c52af5206ffc | |||
| 16:46 | Google Unveils New AI Models https://medium.com/@victor_gevers/google-unveils-new-ai-models-a2ec6ebe90f1 | |||
| 16:39 | Large Language Monkeys: Scaling Inference Compute with Repeated Sampling https://scalyresearch.stanford.edu//pubs/large_language_monkeys/ | |||
| 16:39 | Exploring GraphRAG with Implementation https://medium.com/@thisisrishi/exploring-graphrag-with-implementation-fce5a634f18b | |||
| 16:38 | LangGraph Studio: The first agent IDE https://blog.langchain.dev/langgraph-studio-the-first-agent-ide/ | |||
| 16:26 | Transforming University Admissions with AI: Automating FAQ Generation https://medium.com/@rohit.veeradhi/transforming-university-admissions-with-ai-automating-faq-generation-c382ed81ff2b | |||
| 16:01 | The Rise of Small Language Models https://odsc.medium.com/the-rise-of-small-language-models-960eb2266cc4 | |||
| 15:58 | Show HN: Engine Core – open-source LLM chat management and tool call framework https://github.com/Engine-Labs/engine-core | |||
| 15:54 | Llama 405B vs. GPT 4O – Prompt by prompt comparison https://blog.monsterapi.ai/blogs/llama-3-1-405b-vs-gpt4o-head-to-head-comparison/ | |||
| 15:43 | How to get llama2 running on your Raspberry Pi https://medium.com/@wilsosomdb/how-to-get-llama2-running-on-your-raspberry-pi-from-8c551115323d | |||
| 15:42 | RetiDirect vs. Augmented: When to Use LLMs and When to Opt for RAG for Optimal Results https://medium.com/@prompas/retidirect-vs-augmented-when-to-use-llms-and-when-to-opt-for-rag-for-optimal-results-457ecb814ee0 | |||
| 15:41 | #34 Deep Learning Essentials: Multi-task Learning & Activation Functions in NNs https://pub.towardsai.net/34-deep-learning-essentials-multi-task-learning-activation-functions-in-nns-bf809053f0b5 | |||
| 15:33 | Understanding the Parameters of Large Language Models https://medium.com/@n3d/understanding-the-parameters-of-large-language-models-2c61fd7f2958 | |||
| 15:24 | Accessing HuggingFace Models in LangChain https://medium.com/@prajwal_/accessing-huggingface-models-in-langchain-2cb362d1247c | |||
| 15:22 | Local LLM Fine-Tuning on Mac (M1 16GB) https://towardsdatascience.com/local-llm-fine-tuning-on-mac-m1-16gb-f59f4f598be7 | |||
| 15:15 | Conversational Agents vs. Normal Agents https://medium.com/@kaviyadharishini21/conversational-agents-vs-normal-agents-f4f330706aaa | |||
| 15:07 | ChatGPT vs. Spreadsheet powered AI https://medium.grid.is/chatgpt-vs-spreadsheet-powered-ai-f2f90848ee41 | |||
| 14:56 | How to Implement a GenAI Agent using Autogen or LangGraph https://towardsdatascience.com/how-to-implement-a-genai-agent-using-autogen-or-langgraph-929135afd34d | |||
| 14:28 | How Not to Be Stupid When Building GenAI Apps https://shekhargulati.medium.com/how-not-to-be-stupid-when-building-genai-apps-9c0edb39ac64 | |||
| 14:09 | Adam-mini: A More Efficient Deep Learning Optimizer with Half the Memory Usage https://medium.com/@zergtant/adam-mini-a-more-efficient-deep-learning-optimizer-with-half-the-memory-usage-15e3ef99a0aa | |||
| 13:55 | Di intelligenze artificiali, atenei e servizi digitali https://medium.com/@gpirrotta/di-intelligenze-artificiali-atenei-e-servizi-digitali-0e9b679dc65a | |||
| 13:40 | Attention Mechanism and Positional Encoding in Neural Networks https://medium.com/@ilyurek/attention-mechanism-and-positional-encoding-in-neural-networks-c5d20f470622 | |||
| 13:32 | Imagining AI Benchmarking for Ukraine: Key Features of a Future Platform https://blog.gopenai.com/imagining-ai-benchmarking-for-ukraine-key-features-of-a-future-platform-c7fcb4dac557 | |||
| 13:15 | How to Train a Large Language Model https://medium.com/@analyticsinsight/how-to-train-a-large-language-model-3caf33f5d383 | |||
| 12:45 | Will Long-Context LLMs Cause the Extinction of RAG https://ai.gopubby.com/will-long-context-llms-cause-the-extinction-of-rag-de41ca5ddfc6 | |||
| 12:00 | MindSearch: A Multi-Agent AI Framework Processing 300+ Web Pages in Under 3 Minutes to Enhance Information Retrieval and Integration https://www.marktechpost.com/2024/08/01/mindsearch-a-multi-agent-ai-framework-processing-300-web-pages-in-under-3-minutes-to-enhance-information-retrieval-and-integration/ | |||
| 11:38 | Creating Synthetic Training Data https://cobusgreyling.medium.com/creating-synthetic-training-data-84a742889e14 | |||
| 11:21 | First Large-Language-Models(LLM) Beginners Guide https://bobrupakroy.medium.com/first-large-language-models-llm-beginners-guide-c74da7a2ba3d | |||
| 11:15 | ChatGPT Advanced Voice Mode counting as fast as it can to 10 https://twitter.com/CrisGiardina/status/1818627205217272098 | |||
| 11:04 | RouteLLM: The AI Traffic Cop That’s Saving Big Tech Bucks https://medium.com/@cognidownunder/routellm-the-ai-traffic-cop-thats-saving-big-tech-bucks-553cb0267e57 | |||
| 10:13 | Baidu’s Self-Reasoning Approach to Curbing AI Hallucinations https://teqnoverse.medium.com/baidus-self-reasoning-approach-to-curbing-ai-hallucinations-d8070982b926 | |||
| 09:32 | Decoding Mixtral of Experts: Complete Guide https://medium.com/@marketing_novita.ai/decoding-mixtral-of-experts-complete-guide-8ef126b8713e | |||
| 09:23 | ChatPDF and ChatCom with LangChain https://medium.com/@liuzikai0216/chatpdf-and-chatcom-with-langchain-f7fcb99c6a79 | |||
| 09:03 | From Voice to Text: OpenAI Whisper Model in Action https://blog.gopenai.com/from-voice-to-text-openai-whisper-model-in-action-273ee4f3b46e | |||
| 09:02 | SIGNLLM : AI Solutions for Hearing Impairment https://medium.com/@ssark/signllm-ai-solutions-for-hearing-impairment-993ece917e14 | |||
| 08:53 | MindSearch: LLM-Based Web Search Engine Similar to Perplexity.ai and SearchGPT https://github.com/InternLM/MindSearch | |||
| 07:44 | FAISS (Facebook AI Similarity Search) : A Deep Dive into Index Structures for Efficient Data… https://medium.com/@nisanth.m.s/faiss-facebook-ai-similarity-search-a-deep-dive-into-index-structures-for-efficient-data-7a4524037556 | |||
| 07:36 | Meta Segment Anything Model 2 (SAM 2) https://augmentedstartups.medium.com/meta-segment-anything-model-2-sam-2-f457e99d1c60 | |||
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803