LLM News and Articles
Tuesday, 2024-09-17 | ||||
13:01 | Show HN: Opik, an open source LLM evaluation framework https://github.com/comet-ml/opik | |||
12:46 | Llama 3.1 70B compressed by 6.4x using AQLM-PV, now released https://huggingface.co/ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16/tree/main | |||
12:45 | Eski Google CEO’su Yapay Zeka Hakkında Ne Saklıyor? https://haldun-bozkurt.medium.com/eski-google-ceosu-yapay-zeka-hakk%C4%B1nda-ne-sakl%C4%B1yor-3eaf1de88754 | |||
12:41 | Converting Pandas Rows to Text for a Large Language Model (LLM) https://chrisyandata.medium.com/converting-pandas-rows-to-text-for-a-large-language-model-llm-5099f0cd2fdc | |||
12:25 | How to Use the Langchain Logo in Your Projects Effectively https://medium.com/@garysvenson09/how-to-use-the-langchain-logo-in-your-projects-effectively-41fae6fe18d6 | |||
12:24 | Sam Altman departs OpenAI's safety committee https://techcrunch.com/2024/09/16/sam-altman-departs-openais-safety-committee/ | |||
12:05 | Evaluating domain-specific LLMs https://medium.com/sage-ai/evaluating-domain-specific-llms-650bf61d6b9f | |||
11:46 | Does AI-assisted Writing reduce Diversity? https://code.likeagirl.io/does-ai-assisted-writing-reduce-diversity-38dbc3fceb4c | |||
11:39 | Getting Started with LLMOps: Efficiently Deploying and Managing Large Language Models in Production https://medium.com/@mexasol/getting-started-with-llmops-efficiently-deploying-and-managing-large-language-models-in-production-5570282f9082 | |||
11:34 | How to Integrate Intel RealSense Camera D400 series with NVIDIA Jetson for Real-Time AI… https://medium.com/@mexasol/how-to-integrate-intel-realsense-camera-d400-series-with-nvidia-jetson-for-real-time-ai-667767fa996a | |||
11:27 | ZML - High performance AI inference stack https://github.com/zml/zml | |||
11:18 | How to Understand Large Language Models as Foundation Models https://medium.com/@asakisakamoto02/how-to-understand-large-language-models-as-foundation-models-7a861b6bd89f | |||
11:15 | Elevating Productivity and Creativity with Microsoft CoPilot for Developers https://blog.devgenius.io/elevating-productivity-and-creativity-with-microsoft-copilot-for-developers-57fd00b1d68f | |||
11:14 | [PM review #1] - Making OpenAI’s GPT Store a friendlier place https://medium.com/@lancelot.salavert/pm-review-1-making-openais-gpt-store-a-friendlier-place-c819f7a9e602 | |||
11:10 | Elon Musk, Sam Altman, and the Silicon Valley Elite Manipulate the Public https://fortune.com/2024/09/17/elon-musk-sam-altman-silicon-valley-elite-manipulate-public/ | |||
10:49 | Automating ERP Material Bookings with AI: Speeding Up Inventory Management https://medium.com/@extraktai/automating-erp-material-bookings-with-ai-speeding-up-inventory-management-29c14426ae8b | |||
10:43 | AI’nt That Easy #16: Optimizing Enterprise Gen AI: Advanced Caching Strategies for RAG on PDFs https://aakriti-aggarwal.medium.com/aint-that-easy-16-optimizing-enterprise-gen-ai-advanced-caching-strategies-for-rag-on-pdfs-4874694a8da7 | |||
10:01 | Large Language Models in Finance: A Deep Dive https://medium.com/@anandvlinkedin/large-language-models-in-finance-a-deep-dive-9f8454f498f6 | |||
09:45 | Large Language Models Review: Pricing, Benchmarks, Use Cases https://medium.com/@getanakin/large-language-models-review-pricing-benchmarks-use-cases-78a555546dd3 | |||
09:40 | Mastering Mistral: A Step-by-Step Guide to Fine-Tuning with QLoRA https://medium.com/ai-enthusiast/mastering-mistral-a-step-by-step-guide-to-fine-tuning-with-qlora-39ee83ffa690 | |||
09:36 | The AI Acceleration Showdown: vLLM vs. TGI in the Race for Efficient LLM Deployment https://runaker.medium.com/the-ai-acceleration-showdown-vllm-vs-tgi-in-the-race-for-efficient-llm-deployment-13fe90c635be | |||
09:13 | What are AI Agents? https://mirkan.medium.com/what-are-ai-agents-3fc158fb5b05 | |||
08:41 | ️ Why Your RAG System Is Failing — and How to Fix It https://blog.curiosity.ai/%EF%B8%8F-why-your-rag-system-is-failing-and-how-to-fix-it-7fe66780a335 | |||
08:33 | Gemini Overview https://medium.com/@ali.atguedda/gemini-overview-54c34ee9f8d5 | |||
08:08 | ChatGPT O1 Preview Review https://medium.com/@shenx3/chatgpt-o1-preview-review-a767a2885752 | |||
07:54 | Unlocking the Power of AI Agents: When LLMs Can Do More Than Just Talk https://blog.ml6.eu/unlocking-the-power-of-ai-agents-when-llms-can-do-more-than-just-talk-59d60c0d424a | |||
07:30 | Automatically process all backorders from email to excel on SharePoint using Power Automate https://medium.com/@extraktai/automatically-process-all-backorders-from-email-to-excel-on-sharepoint-using-power-automate-54a8101cf0c0 | |||
07:25 | Large Language Model https://datavrpscience.medium.com/large-language-model-f46a8b61209b | |||
07:18 | How to Use Hugging Face Pipeline in LangChain Community https://medium.com/@asakisakamoto02/how-to-use-hugging-face-pipeline-in-langchain-community-e8c96c99b380 | |||
07:08 | Planning in Natural Language Improves LLM Search for Code Generation https://arxiv.org/abs/2409.03733 | |||
06:23 | We're approaching LLM prompt evaluation at QA.tech https://qa.tech/blog/how-were-approaching-llm-prompt-evaluation-at-qa-tech/ | |||
06:16 | How to Leverage API Integration Benefits for Your Business https://medium.com/@tayloroakley/how-to-leverage-api-integration-benefits-for-your-business-2a10238762c7 | |||
06:04 | Optimizing LLM Training https://medium.com/@gautamgoswami/optimizing-llm-training-6336b7be4b17 | |||
05:58 | What’s Stopping You from Building Your Own AI App? Start Now with AWS SageMaker! https://medium.com/@abhijeetas8660211/whats-stopping-you-from-building-your-own-ai-app-start-now-with-aws-sagemaker-44db9ca9a707 | |||
05:57 | How Cache Helps in Generative AI Response and Cost Optimization https://medium.com/@punya8147_26846/how-cache-helps-in-generative-ai-response-and-cost-optimization-9a6c9be058bb | |||
05:52 | “Not Diamond” AI: New Free LLM Beats ChatGPT, Claude, Llama and Gemini by Including them All https://medium.com/@alexanderpani1/not-diamond-ai-new-free-llm-beats-chatgpt-claude-llama-and-gemini-by-including-them-all-2e430ec4192b | |||
05:45 | Whisper vs Deepgram vs Google Speech-to-Text: A Comprehensive Review https://medium.com/@getanakin/whisper-vs-deepgram-vs-google-speech-to-text-a-comprehensive-review-797046958da3 | |||
05:36 | Build a Conversational Storytelling Bot in 20 Minutes with AWS Bedrock https://medium.com/@DataTechBridge/build-a-conversational-storytelling-bot-in-20-minutes-with-aws-bedrock-03bebe2d2f1a | |||
05:31 | Is Prompt Engineering the Job of Future? https://medium.com/mynextdeveloper/is-prompt-engineering-the-job-of-future-b3e0637fc670 | |||
05:03 | Spotlight on 6Eskai at Meta’s WhatsApp Business Summit https://stories.riafy.me/spotlight-on-6eskai-at-metas-whatsapp-business-summit-679b68700e2b | |||
04:25 | How to Load Local Models in Langchain for Your Projects https://medium.com/@garysvenson09/how-to-load-local-models-in-langchain-for-your-projects-596e3dff32be | |||
03:51 | LLM Architectures Explained: Encoder-Decoder Architecture (Part 4) https://medium.com/@vipra_singh/llm-architectures-explained-encoder-decoder-architecture-part-4-b96ace71394c | |||
03:50 | Large Language Model (LLM) Interview Questions https://skphd.medium.com/large-language-model-llm-interview-questions-ded6264547f1 | |||
03:37 | Exploring Retrieval-Augmented Generation (RAG) Through Real-Life Applications https://medium.com/@samanvitha.sateesha/exploring-retrieval-augmented-generation-rag-through-real-life-applications-12de19a53c40 | |||
03:18 | How to Install Langchain Community from PyPI Effectively https://medium.com/@asakisakamoto02/how-to-install-langchain-community-from-pypi-effectively-5c00570965e4 | |||
02:49 | AI’nt That Easy#15: Prompt Caching: Boosting LLM Efficiency and Speed https://aakriti-aggarwal.medium.com/aint-that-easy-15-prompt-caching-boosting-llm-efficiency-and-speed-03d567403255 | |||
02:21 | Search, Retrieval and Augmentation https://productcoalition.com/search-retrieval-and-augmentation-2e5f1b0185b0 | |||
02:18 | vLLM: A Deep Dive into Efficient LLM Inference and Serving https://medium.com/@asimsultan2/vllm-a-deep-dive-into-efficient-llm-inference-and-serving-17804bf047df | |||
02:16 | Hidden Chain-of-Thought decoding: faster and efficient CoT decoding to improve reasoning of LLMs https://medium.com/@techsachin/hidden-chain-of-thought-decoding-faster-and-efficient-cot-decoding-to-improve-reasoning-of-llms-d95584bc9346 | |||
02:16 | How to Get Repositories from GitHub Easily and Quickly https://medium.com/@tayloroakley/how-to-get-repositories-from-github-easily-and-quickly-869293f0404f | |||
01:57 | Day 16: Red Teaming and Testing LLM Robustness https://blog.gopenai.com/day-16-red-teaming-and-testing-llm-robustness-5f575d903eb9 | |||
01:45 | Stable Diffusion XL vs 2.1: Features, Pricing, and Use Cases https://medium.com/@getanakin/stable-diffusion-xl-vs-2-1-features-pricing-and-use-cases-2ba9c8547511 | |||
01:30 | Day 15: Function Calling and Data Extraction with LLMs https://blog.gopenai.com/day-15-function-calling-and-data-extraction-with-llms-20f70570c44c | |||
01:17 | The Grimoire of Prompt Engineering https://medium.com/@timdiscovers/the-grimoire-of-prompt-engineering-8c448e9ba794 | |||
00:51 | Raycast with Fabric https://medium.com/@wilder.labs/raycast-with-fabric-5308b52ca3c4 | |||
00:27 | Large Language Models Explained: How AI is Transforming Language Processing And Yandex at the… https://samuelokediji.medium.com/large-language-models-explained-how-ai-is-transforming-language-processing-and-yandex-at-the-59e1a1f3e615 | |||
00:25 | How to Load Different File Types in Langchain Tutorial https://medium.com/@garysvenson09/how-to-load-different-file-types-in-langchain-tutorial-f9444ca37d2f | |||
00:00 | Introducing the SQL Console on Datasets https://huggingface.co/blog/sql-console | |||
Monday, 2024-09-16 | ||||
23:44 | How to Train and Deploy Your Own LLM Locally: A Comprehensive Guide For UI Code Generation https://nzouat.medium.com/how-to-train-and-deploy-your-own-llm-locally-a-comprehensive-guide-for-ui-code-generation-8f60aa8b9176 | |||
23:40 | Building AI Clinic Agent with Toolhouse AI and OpenAI https://medium.com/@ShawnBasquiat/building-ai-clinic-agent-with-toolhouse-ai-and-openai-31eb46faa005 | |||
23:18 | How to Load TXT Files with LangChain UnstructuredFileLoader https://medium.com/@asakisakamoto02/how-to-load-txt-files-with-langchain-unstructuredfileloader-e01373acd05a | |||
23:10 | Language Model Aware Speech Tokenization (LAST): A Unique AI Method that Integrates a Pre-Trained Text Language Model into the Speech Tokenization Process https://www.marktechpost.com/2024/09/16/language-model-aware-speech-tokenization-last-a-unique-ai-method-that-integrates-a-pre-trained-text-language-model-into-the-speech-tokenization-process/ | |||
23:09 | Beyond the Surface: Challenges in Evaluating Model-Generated Responses with Perfect Retrieval and… https://medium.com/@pradeepdas/beyond-the-surface-challenges-in-evaluating-model-generated-responses-with-perfect-retrieval-and-cf23417718b5 | |||
23:04 | OpenAI's O1 for Legal Work https://www.spellbook.legal/blog/openai-o1-for-law-legal-spellbook | |||
22:57 | We fine-tuned an LLM to triage and fix insecure code https://corgea.com/blog/fine-tuning-for-precision-and-privacy-how-corgea-s-llm-enhances-enterprise-application-security | |||
22:51 | How to Fine Tune Flux.1 Model with Your Own Photos? https://medium.com/@01coder/how-to-fine-tune-flux-1-model-with-your-own-photos-c957533ba6df | |||
22:30 | AI Projects Are Like Baking Bread https://medium.com/@semtioc/ai-projects-are-like-baking-bread-1fb899589e2a | |||
22:17 | How to Prepare for Rest API Interview Questions Effectively https://medium.com/@tayloroakley/how-to-prepare-for-rest-api-interview-questions-effectively-21dad4c3f365 | |||
22:16 | Reflection AI: Exploring the Reflection 70B LLM Powered by Llama 3.1 and Advanced Self-Correction https://medium.com/@monsuralirana/reflection-ai-exploring-the-reflection-70b-llm-powered-by-llama-3-1-and-advanced-self-correction-d2ee4980f346 | |||
22:01 | How to Create a Medical Agent / RAG System. https://pub.towardsai.net/how-to-create-a-medical-agent-rag-system-effd0aaacc91 | |||
21:46 | DCGANs: Deep Convolutional Generative Adversarial Network https://medium.com/@halfdeb/dcgans-deep-convolutional-generative-adversarial-network-69bb63601fc8 | |||
21:45 | Stable Diffusion XL vs 1.5: A Comprehensive Model Review https://medium.com/@getanakin/stable-diffusion-xl-vs-1-5-a-comprehensive-model-review-77dcd82268a2 | |||
20:44 | Comparing Logic and Math Capabilities of LLMs (Part 1) https://medium.com/@dimkarata/comparing-logic-and-math-capabilities-of-llms-part-1-77c30d72dff0 | |||
20:34 | Pentesting AI Applications-OWASP Top 10 for LLMs https://medium.com/@shi.vani/pentesting-ai-applications-owasp-top-10-for-llms-cab1f12d3215 | |||
20:25 | How to Troubleshoot Empty Results from Langchain LLMs https://medium.com/@garysvenson09/how-to-troubleshoot-empty-results-from-langchain-llms-674b709e26db | |||
19:56 | The RoPE Effect: Untangling Positional Encoding in AI Language Models https://medium.com/@himankvjain/the-rope-effect-untangling-positional-encoding-in-ai-language-models-1bf0ab46776b | |||
19:44 | LLMs & the Strawberry Riddle: Technical Background https://medium.com/@davehk/llms-the-strawberry-riddle-technical-background-65bed7444ede | |||
19:31 | The Working of Knowledge Graphs, How Nodes & Edges Weave the Web of Data! https://hammad-munir.medium.com/the-working-of-knowledge-graphs-how-nodes-edges-weave-the-web-of-data-917396e6f333 | |||
19:23 | LLMInspect: Observability in Large Language Models in Enterprises (LLM) using OpenTelemetry https://medium.com/@sabrina_khan/llminspect-observability-in-large-language-models-in-enterprises-llm-using-opentelemetry-4bb52db4c956 | |||
19:18 | How to Find Langchain Logo PNG Transparent for Your Projects https://medium.com/@asakisakamoto02/how-to-find-langchain-logo-png-transparent-for-your-projects-9780dae2e808 | |||
19:10 | Building a Dynamic Podcast Generator Inspired by Google’s NotebookLM and Illuminate https://saschaheyer.medium.com/building-a-dynamic-podcast-generator-inspired-by-googles-notebooklm-and-illuminate-e585cfcd0af1 | |||
18:58 | Practical Guidance for Evaluating Large Language Model (LLM) Products https://medium.com/@piscaries/practical-guidance-for-evaluating-large-language-model-llm-products-391807796000 | |||
18:37 | MotleyCrew with Llama 3.1: fully open source multi-agent AI https://medium.com/motleycrew-ai/motleycrew-with-llama-3-1-fully-open-source-multi-agent-ai-5b10ec981523 | |||
18:26 | Boosting Retrieval in RAG Systems with Query Expansion https://angelina-yang.medium.com/boosting-retrieval-in-rag-systems-with-query-expansion-11b224ab7d67 | |||
18:17 | How to Use HCM Integration for Streamlined HR Processes https://medium.com/@tayloroakley/how-to-use-hcm-integration-for-streamlined-hr-processes-5daaab014121 | |||
18:12 | Generative AI 101: Leveraging Large Language Models to Transform Marketing Strategies https://palarkaprabha.medium.com/generative-ai-101-leveraging-large-language-models-to-transform-marketing-strategies-15182259501a | |||
18:12 | How I Built My Own AI Coding Assistant for VSCode in 15 Mins https://ai.gopubby.com/how-i-built-my-own-ai-coding-assistant-for-vscode-in-15-mins-e4f71ba5d406 | |||
18:09 | Reverse Engineering OpenAI's O1 https://www.interconnects.ai/p/reverse-engineering-openai-o1 | |||
18:00 | Por que LLMs alucinam? https://medium.com/@carlosguilherme.schneider/por-que-llms-alucinam-215190ee3f65 | |||
17:49 | Parameter-Efficient Fine-Tuning (PEFT) for Large Language Models: Making AI More Adaptable and… https://medium.com/@ysfckmk/parameter-efficient-fine-tuning-peft-for-large-language-models-making-ai-more-adaptable-and-52fb0395af2a | |||
17:45 | Stable Diffusion 1.5 vs 2.1: Review, Benchmark & Pricing Insights https://medium.com/@getanakin/stable-diffusion-1-5-vs-2-1-review-benchmark-pricing-insights-7715e11c87b8 | |||
17:33 | ChatGPT Is Getting Scary Better at Math https://win-vector.com/2024/09/16/chatgpt-is-getting-scary-better-at-math/ | |||
16:48 | Newton-Raphson Fractals with ChatGPT https://medium.com/@dacmorton/newton-raphson-fractals-with-chatgpt-007703c7c45b | |||
16:46 | Large Action Models (LAMs): A Comprehensive Guide https://prajnaaiwisdom.medium.com/large-action-models-lams-a-comprehensive-guide-f43f68704451 | |||
16:40 | Announcing LangChain v0.3 https://blog.langchain.dev/announcing-langchain-v0-3/ | |||
16:35 | Identifying Emerging Research Trends in Artificial Intelligence: A Topic Modeling Using NMF https://medium.com/thedeephub/identifying-emerging-research-trends-in-artificial-intelligence-a-topic-modeling-using-nmf-d6689dbd173c | |||
16:25 | How to Limit Output Tokens in LangChain Efficiently https://medium.com/@garysvenson09/how-to-limit-output-tokens-in-langchain-efficiently-c0df0bb8a85f | |||
16:21 | ASCVIT V1: Automatic Statistical Calculation, Visualization and Interpretation Tool https://towardsdatascience.com/ascvit-v1-automatic-statistical-calculation-visualization-and-interpretation-tool-aa910001a3a7 | |||
16:12 | Cutting LLM API Costs with Dynamic Model Selection https://medium.com/@sohumfuke/cutting-llm-api-costs-with-dynamic-model-selection-cabce7c26d41 | |||
16:08 | Building a Scalable Support Queue Assistant with RAG and LLMs https://medium.com/@ranga4all1_/building-a-scalable-support-queue-assistant-with-rag-and-llms-baaa01660cf8 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803