here you goThings I’ve made, read and saved — shared here.

#llm

37 notes and posts, 56 links.

Notes and posts

  • Grok

    Note

    Connect Grok to Hermes Agent

  • Software construction kits

    Note

    Software Construction Kits.. inspired by Folklore.org: Calculator Construction Set. See also Malleable software in the age of LLMs -- this is a longer essay.

  • Extract Structured Information

    Note

    Extracting structured information from unstructured text using LLMs is a good tool to have in your llm toolkit. Google's langextract is one such python library for extracting structured information from unstructured…

  • AI on a budget

    Note

    What if you do not want to use AI SaaS products for any reason (monetary - subscriptions add up quick, privacy - do not want share your data with companies, etc.,)? One approach is to use local-llm on your laptop, or…

  • Keeping up with AI

    Note

    Sources on keeping up with AI. This is a good start as of July 2025 - How I keep up with AI progress (and why you must too) from Nilenso blog, since I use many of the same.

  • LLM Inference

    Note

    LLM Inference in Production by BentoML; "core concepts and performance metrics, to optimization techniques and operation best practices"

  • DeepSeek

    Note

    DeepSeek is a AI research company from China that has been doing cutting edge work in the area of Large Language Models, including DeepSeek-R1. DeepSeek tried to do one thing: transplant its own model to Huawei Ascend…

  • Pair Programming with LLM

    Note

    Pair Programming with Google's PaLM API. Google Generative AI Studio: What we need: API Key from above site Generative AI Libraries node.js, swift or python Python programming skills ( ) "Larger the animal, larger the…

  • Prompt Engineering

    Note

    via Let the LLM Write the Prompts: An Intro to DSPy in Compound AI Pipelines Prompt Engineering in Python | Automatic and Programmatic Prompt Optimization | Complete Course - YouTube by Maxime Rivest; Aug 2025…

  • llama

    Note

    llama homepage The latest, as on Jul 2024, is llama 3.1 which has 405B, 70B and 8B models, optimized for "do it all", cost/performance tradeoff, and light-weight+speed. You can run llama locally on your laptop or pc…

  • LLMs in Data Management

    Note

    [@10.14778/3611479.3611527]; PDF We argue that the disruptive influence that LLMs will have on data management will come from two angles. (1) A number of hard database problems, namely, entity resolution, schema…

  • AI reading

    Note

    Via AI Papers Community notes via \@zaph0id; Apr 2024. -- Ilya's reccommendation to Carmack.. also available as this Arc Folder with links to actual papers and blog posts. See the twitter thread for summaries. AI…

  • Google Gemini

    Note

    Gemini is Google's AI/llm model introduced in Dec '23 - Introducing Gemini: Google’s most capable AI model yet In Apr 2024, they announced Gemini 1.5 Pro - Gemini 1.5 Pro Now Available in 180+ Countries; With Native…

  • SWE Agent

    Note

    Devin from Cognitive AI made waves when it came out in March 2024. There are follow-on developments since then. SWE-Agent Agent Computer Interfaces Enable Software Engineering Language Models.SWE-agent turns LMs (e.g…

  • Fine Tuning

    Note

    Why fine tune? Greater Accuracy -- By tailoring the model to specific use cases and industries, it can better understand and generate contextually relevant responses. Improve Efficiency -- Fine-tuning streamlines…

  • Text Embedding

    Note

    See also: llm via ➡️ Text embedding models represent natural language as dense vectors, positioning semantically similar text near each other within the embedding space. Or in simple terms, text embedding models are…

  • Reward Models

    Note

    (Lambert et al. 2024) RewardBench With RewardBench, we: Release a common framework for evaluating the many different architectures of reward models, along with tools for visualization, training, and other analysis. We…

  • AI SaaS

    Note

    Adaptive Engine, Roe AI -- "AI for Risk, Compliance and Trust. Create AI workers to automate your risk operations." ^e9eac9 Stack-AI.com -- The No-Code Generative AI Platform. Deploy custom AI Assistants, Chatbots, and…

  • Generate Documents from Transcriptions

    Note

    lumentis - AI powered one-click comprehensive docs from transcripts and text Generate beautiful docs from your transcripts and unstructured information with a single command. A simple way to generate comprehensive…

  • Long Form Factuality

    Note

    Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. This paper by Google Deepmind -- (Wei et al. 2024) -- proposes a method…

  • MosaicML

    Note

    MoscaicML was a startup acquired by Databricks in July 6, 2023 for $1.3B. In March 2024, they were behind the announcement of Databricks's new Foundation Model - DBRX Some libraries by MosaicML are: LLM Foundary code…

  • Multi Agent Frameworks

    Note

    Mora Sora is the first large-scale generalist video generation model that garnered significant attention across society. Since its launch by OpenAI in February 2024, no other video generation models have paralleled…

  • DSPy

    Note

    I got Dspy certificate on Deeplearning.ai - on Dec 31, 2025 With DSPy -- you can build your system using predefined modules, replacing intricate prompting techniques with straightforward, effective solutions. (Khattab…

  • Opensource LLM

    Note

    GitHub - allenai/awesome-open-source-lms: Friends of OLMo and their links. Papers Appears to be an exhaustive survey paper -- (Chen et al. 2023) (Zhuang et al. 2024) ChuXin, an entirely open-source language model with a…

  • Local LLM

    Note

    Local Coding How to Setup a Local Coding Agent on macOS - Kyle Howells running Gemma 4 26B-A4B and Qwen3.6 35B-A3B locally with llama.cpp, MTP speculative decoding, multimodal support, and PI as a coding agent. Local…

  • RAG

    Note

    RAG is an AI framework for retrieving facts from an external knowledge base to ground large language models (LLMs) on the most accurate, up-to-date information and to give users insight into LLMs' generative process…

  • Llama Index

    Note

    LlamaIndex is a flexible framework that enables LLM applications to ingest, structure, access, and retrieve private data sources. The end result is that your model's responses will be more relevant and context-specific…

  • Mistral AI

    Note

    Mistral AI is is a European (French?) start-up with a global focus specialising in generative artificial intelligence. Mistral AI aims to develop new models of generative artificial intelligence for companies, combining…

  • Small LLMs aka SLMs

    Note

    Finetuning ( via ) PEFT + TRL -- Examples of using peft with trl to finetune 8-bit models with Low Rank Adaption (LoRA) Unsloth -- Fine-tuning LLMs Guide | Unsloth Documentation Axolotl -- Axolotl AI - Open Source Fine…

  • Generative AI

    Note

    Generative AI for beginners from Microsoft

  • Coursera Generative AI with LLMs

    Note

    Some notes from the Coursera Course Generative AI Project Lifecycle: Uses AWS Sagemaker (Sagemaker Studio is Jupyter based IDE) for launching notebooks. Time limited to 2 hours. pip packages: torch torch-data…

  • Multimodal Learning

    Note

    Meta-Transformer: A Unified Framework for Multimodal Learning -- Unified Multimodal Learning. Meta-Transformer utilizes the same backbone to encode natural languages, images, point clouds, audio, video, infrared…

  • transformers

    Note

    8 Google Employees Invented Modern AI. Here’s the Inside Story | WIRED ¶ Transformers from Scratch Transformers were introduced in this 2017 paper as a tool for sequence transduction—converting one sequence of symbols…

  • Hugging Face

    Note

    Hugging Face is a company that focuses on natural language processing (NLP) and artificial intelligence (AI) research. They are best known for their open-source library called "transformers," which provides…

  • LangChainAI

    Note

    LangChainAI, is a framework (python library, and also javascript), for developing application powered by llm. Be data-aware: connect a language model to other sources of data Be agentic: Allow a language model to…

  • LLM

    Note

    Introductory Materials Generative AI exists because of the transformer -- A visual story from Financial Times; Sept 2023. Large language models, explained with a minimum of math and jargon A High-level Overview of Large…

  • GPT

    Note

    GPT = Generative Pre-trained Transformer GPT in 60 Lines of NumPy | Jay Mody How GPT3 Works - Visualizations and Animations – Jay Alammar – Visualizing machine learning one concept at a time. Transformers from Scratch…

Links Open in the Archive