Best of LLMDecember 2023

  1. 1
    Article
    Avatar of communityCommunity Picks·2y

    Ollama

    Get up and running with Llama, a large language model, locally. Run Llama on macOS and Linux, with Windows support coming soon.

  2. 2
    Article
    Avatar of phProduct Hunt·2y

    GPT Router - Avoid OpenAI Downtimes: One API for 30+ LLMs

    GPTRouter is an open source LLM API Gateway that offers a universal API for 30+ LLMs, vision, and image models, with smart fallbacks based on uptime and latency, automatic retries, and streaming. Stay operational even when OpenAI is down.

  3. 3
    Article
    Avatar of earthlyEarthly·2y

    The Future is Rusty

    The article discusses the challenges of learning complex programming languages like Rust and how LLMs (Large Language Models) can help with the intermediate material problem. By providing instant feedback and assistance, LLMs can bridge the gap in knowledge and enhance the learning process in programming. The article encourages readers to tackle challenging projects with the support of LLMs and emphasizes that learning curves are now less steep.

  4. 4
    Article
    Avatar of freecodecampfreeCodeCamp·2y

    Vector Search and RAG Tutorial – Using LLMs with Your Data

    Learn how to implement Vector Search and the RAG architecture in your applications using Atlas Vector Search. Vector embeddings can be used to organize data and perform semantic similarity searches. RAG improves response generation by utilizing relevant retrieved documents.

  5. 5
    Article
    Avatar of medium_jsMedium·2y

    A Comprehensive Survey of Large Language Models (LLMs)

    The article discusses the growth of large language models (LLMs), the key practices related to LLMs, the three emergent abilities of LLMs (In-Context Learning, Instruction Following, and Step-by-Step Reasoning), the development of the LLM landscape, training data sources for LLMs, and the continuous refinement and integration of LLMs into existing technological landscapes.

  6. 6
    Article
    Avatar of stackovStack Overflow Blog·2y

    The hardest part of building software is not coding, it's requirements

    The hardest part of building software is not coding, it's creating clear and precise requirements. AI has excelled in chess due to its finite parameters, but struggles with self-driving cars due to the infinite variables involved. While AI may be able to rewrite existing software faster, it cannot replace the need for human judgment and clear specifications.

  7. 7
    Article
    Avatar of arstechnicaArs Technica·2y

    Google’s best Gemini AI demo video was fabricated

    Google's Gemini AI demo video has caused controversy among AI experts for misrepresenting the model's capabilities.

  8. 8
    Article
    Avatar of medium_jsMedium·2y

    Semantic Search with MongoDB and FastAPI: Comprehensive Guide

    This comprehensive guide demonstrates how to elevate your application’s standard CRUD operations with Semantic Search functionality, leveraging new Vector Search feature of the MongoDB Atlas.