Skip to content
EN

Back to the catalog

apeatling.com
rss2American English

Andy Peatling

apeatling.com · American English

Working with React.js, TypeScript, LLMs, & Agents

rss2 wordpress content slash wfw atom dc sy

Open the feed

https://apeatling.com/feed/

Last post
Sep 14, 2026
Posts in 24 h · 7 days · 30 days
0 · 0 · 1
Our last check
Answering
Served from
United States
Text score at discovery
47,675
Format
rss2
Features in the feed
content, slash, wfw, atom, dc, sy
Community
wordpress

Posts

What our queue read from this feed. Open one to read it here, or go to the site that published it.

  1. Ideas for WordPress in an agentic world
    Sep 14, 2026 · original
    Everything is changing, and quickly. I feel it every day I work on Miles . It’s hard to keep up with, and often exhausting. There are threats and opportunities everywhere. WordPress is in a tough position. The last twenty years had a clear path for growth. Convince people that WordPress is the best tool for building websites and owning that website end to end. Doing so resulted in more downloads, more word-of-mouth marketing, and ultimately more installs. That path is disappearing. Increasingly the platform choice is being made by an agent, acting only on what it has in its training data, or what it can find when searching the web. Spinning up a simple website can be done in 30 seconds without any effort on the part of the user. What could be done to help WordPress adjust to this new world? I’ll organize my thoughts into three areas, and my ideas under each. 1. Define what using WordPres
  2. Farewell, Automattic
    Jun 17, 2025 · original
    Yesterday was my first day back in the world of entrepreneurship. After seventeen wonderful years at Automattic , I resigned last Friday to begin this new chapter. During my time there, I helped grow the company from twenty to almost two thousand people through significant engineering and product development roles. I’m grateful for every moment of that journey. In my final two years at Automattic, I was deeply embedded in the application layer of AI development. It was a wild ride to say the least. The landscape is changing almost daily. There have been incredible improvements in foundation models and their ability to comprehend, orchestrate, and reason. The costs are driving towards zero, opening up greater opportunities to harness their power and offer unique value. This change is transforming software development, AI is fundamentally shifting how we build products. Developers can now
  3. Building a Real-time Agentic Server with REST+SSE
    Apr 23, 2025 · original
    Using a traditional REST API works well for many applications, but they have serious limitations when it comes to AI agents. Responses from large language models take time to generate, often several seconds. If you request a response and wait synchronously, your users are left staring at loading indicators. WebSockets are an option, but they’re more complex to implement and they maintain bidirectional connections that are typically overkill for agents. What we really need is a way to stream partial results from the server to the client in real-time, while keeping the overall architecture clean and simple. This is where Server-Sent Events come in! The REST+SSE Hybrid Pattern The approach I’ve found most effective combines REST endpoints for commands and queries with SSE for streaming responses. Here’s how it works. Your server exposes standard REST endpoints that clients use to send queri
  4. Supercharging AI Agents with Persistent Vector Storage
    Apr 22, 2025 · original
    When building AI agents you’ll notice something frustrating, they forget everything as soon as the conversation ends. This is obviously not ideal, and it’s where vector storage comes in. I’m going to share how you can implement a practical, persistent memory system for your agents. The Memory Problem When building agents it makes sense to initially focus on their reasoning capabilities and tool integration. But as soon as you start using these agents for real work, you’ll quickly discover that their ephemeral memory severely limits their usefulness. Users get frustrated repeating information, agents lose track of long-running tasks, and contextual knowledge vanishes between sessions. What we need is a way to give our agents memory that persists, can be searched semantically, and intelligently fits within the context limits of language models. That’s what I’ll explain in this post. Why Ve
  5. Architecting AI Agents with TypeScript
    Apr 21, 2025 · original
    If you’ve been working with large language models (LLMs) for some time you’ve probably noticed how quickly we’re moving beyond simple chat interfaces. The real power comes when you can orchestrate LLMs to work with external tools, maintain context, and perform complex tasks. I’ve been building these kinds of AI agents for a while now, and wanted to share a thoughtful approach to their architecture. In this post, I’ll walk you through how to build a flexible, maintainable AI agent system in TypeScript using functional programming patterns. This isn’t a theoretical post, I’ll provide complete code examples you can adapt for your own projects. What Makes an Agent? First, what separates an agent from a simple chatbot? While chatbots respond to messages in isolation, agents do considerably more. They understand user inputs and maintain context across interactions. They can process information
  6. Part 4: Testing and interacting with your fine-tuned LLM
    Jan 8, 2024 · original
    This post is the final part of: A simple guide to local LLM fine-tuning on a Mac with MLX . This part of the guide assumes you have completed the fine-tuning process and have an adapters.npz file ready to use. If that’s not the case check our Part 3: Fine-tuning your LLM using the MLX framework . Step 1: Determine prompts to compare results of fine tuning In order to test and see the results of your fine-tuned model, you’ll want to compare prompting the fine-tuned model to the base model. I’m not going to go into detail on the best way to do this, you’ll likely to want to create a number of prompts for the outputs you’re trying to improve with fine-tuning. Depending on the kind of fine-tuning you’re doing you may have quantitative or qualitative ways to evaluate the results. Step 2: Test your prompts on the base and fine-tuned models The MLX library has some built in functionality to han
  7. Part 3: Fine-tuning your LLM using the MLX framework
    Jan 8, 2024 · original
    This post is the third of four parts of: A simple guide to local LLM fine-tuning on a Mac with MLX . This part of the guide assumes you have training data available to fine-tune with. The data should be in JSONL format . If that’s not the case then check out Part 2: Building your training data for fine-tuning . Step 1: Clone the mlx-examples Github repo Machine learning research folks at Apple have created a fantastic new framework called MLX . MLX is an array framework that is built for Apple silicon, allowing it to utilize the unified memory in Macs and thus bringing significant performance improvements. The mlx-examples Github repo contains a whole range of different examples for using MLX. It’s a great way to learn how to use it. I’m going to assume you have knowledge of Git and Github here. You can clone the MLX examples repo using: git clone https://github.com/ml-explore/mlx-exampl
  8. Part 2: Building your training data for fine-tuning
    Jan 8, 2024 · original
    This post is the second of four parts of: A simple guide to local LLM fine-tuning on a Mac with MLX . This part of the guide assumes you have your environment with Python and Pip all set up correctly. If that’s not the case then start with the first step . If you already have fine-tuning training data in JSONL format, you can skip to the fine-tuning step . There are a number of different tools to get LLMs running locally on a Mac. One good one is LM Studio , providing a nice UI to run and chat to offline LLMs. For this guide I’m going to use Ollama as it provides a local API that we’ll use for building fine-tuning training data. Step 1: Download Ollama and pull a model Go ahead and download and install Ollama. For this guide I’m going to use the Mistral 7B Instruct v0.2 model from Mistral.ai . You’re welcome to pull a different model if you prefer, just switch everything from now on for
  9. Part 1: Setting up your environment
    Jan 8, 2024 · original
    This post is the first of five parts of: A simple guide to local LLM fine-tuning on a Mac with MLX . If you’re starting on this journey from scratch, you’ll need to set a few things up on your Mac in order to get going. If you have Python and Pip ready to go, you can skip to step two . Step 1: Install Homebrew Homebrew is a package manager that will help you manage and install software that you need (like Python). I like it because it provides an easy way to switch versions and uninstall packages. To install Homebrew, open the Terminal app (or install iTerm ) and paste the following: /bin/bash -c " $( curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh) " Bash command to install Homebrew Go ahead and install Xcode command line tools if it prompts you during the installation. Step 2: Install an upgraded version of Python and Pip Mac OS has come pre-installed with
  10. A simple guide to local LLM fine-tuning on a Mac with MLX
    Jan 8, 2024 · original
    Hello there! Are you looking to fine-tune a large language model (LLM) on your Apple silicon Mac? If so, you’re in the right place. Let’s walk through the process of fine-tuning step-by-step. It won’t cost you a penny because we’re going to do it all on your own hardware using Apple’s MLX framework . Once we’re done you’ll have a fully fine-tuned LLM you can prompt, all from the comfort of your own device. I’ve broken this guide down into multiple sections. Each part is self contained, so feel free to skip to the part that’s most relevant to you: Setting up your environment . Building your training data for fine-tuning . Fine-tuning your LLM using the MLX framework . Testing and interacting with your fine-tuned LLM . Let me add a disclaimer here . Everything in this space moves really fast, so within weeks some of this is going to be out of date! I’m also learning this myself, so I expec

Discovered by the rss-feed-index crawler, which checks each feed at most once a month.

Same record as JSON: https://api.agentalog.com/api/feeds/fd_apeatling_com_f99bd7c2463e8caa. More from this site: apeatling.com in the Feeds tab.