XIO

xWire

Posts from every feed QUEST has found across the web — blogs, news, podcasts, channels and more.

XDA - AI tools

The world’s best source for computing news, reviews, editorials guides, and more.

I wrote my own Claude Code mod to show my usage window, and I stopped getting cut off mid-task

Claude Code is great, but you know what's not? The usage restrictions. There have been times when I've been working on a new feature, only to exhaust my allowance before I could finish. Claude Code does have a built-in /usage command that shows how much of your allowance you've consumed, but I wanted something that would keep track of it continuously and, more importantly, tell me how much longer I could keep working at my current pace. So I built a small tool that sits alongside Claude Code,…

I let Claude Code clean out my Downloads folder every Friday, and it's the most useful thing I've automated

My vision board for the last few years has consistently had one goal that I've not quite been able to tick off: become a more organized person. I've tried just about everything to make it happen, from downloading countless productivity apps to creating elaborate systems that I inevitably abandon a few days later. Yet, somehow, I always find myself right back where I started.

These small local models keep saving my 8GB GPU from an upgrade

Every few weeks a new open-weight model drops, and the version that all the reviews are about isn't usually one I can run on 8GB. The comments under those releases barely change either; someone always says to save up for a 16GB or 24GB card. But honestly, I'd rather invest that in something like a tablet because the rest of what I do on my PC truly doesn't need more than 8GB, at least not right now.

I run a 2B vision model on my phone and stopped sending my screenshots to ChatGPT and Claude

Screenshots have become one of the main ways people use AI. Ever since the big players, Gemini in particular, introduced the ability to upload images and analyze them, it's become a staple in the workflow. I know it is for me, at least. There's nothing more convenient than snapping something and just showing it to an AI, as opposed to taking notes and describing what you saw to your chatbot. And that extends to mobile.

I found a free Claude Code and Codex alternative that does almost everything I need for my work

There is no shortage of AI coding tools out there. I have experimented with everything from Claude Code and Codex to Google Antigravity, and while each has its strengths, there is one thing they have in common: getting the most out of them can become expensive. I was considering adding yet another AI coding subscription to my monthly expenses when I came across OpenCode.

Claude has a drift problem, and the fix wasn't better prompting

Anyone who's used Claude has probably encountered its drift problem from time to time. You set a rule in the first message, even something simple like how a reply should be formatted, it holds up for about a dozen turns then starts slipping. Further in, Claude seems to start answering a different question than the one you asked, or suddenly agrees with something it pushed back on earlier.

Claude Code isn't just for building apps anymore, and I'm using it to bring back what I miss

If nothing else kills me, nostalgia will. That's a saying I've always, always resonated with. I'm the kind of person who holds on to handwritten notes and letters people give me, keeps random little things purely because they remind me of a particular moment, and gets extremely sentimental over things most people wouldn't think twice about.

I made Gemini 4 Argon, Fable 5.1, and GPT-6 Astra build the same audio tool, and the best-looking one wasn't the best-sounding one

Every new flagship model launches with a chart full of coding benchmarks, and most of them test things like fixing bugs in existing code or working through tasks in a terminal. But those numbers aren't always relevant because many people use these models for something else entirely, like getting a project started from a prompt instead of giving it a whole codebase. I fall into the latter category and like to build little utilities that I've always wanted to see come to life, and finally can…

I let Claude redesign my Home Assistant dashboard, and it did in minutes what I'd put off for months

My Home Assistant setup powers my entire home, and it has grown considerably over the years. I've got literal dozens of lights, sensors, media players, and automations spread across my home. Unfortunately, my dashboard experiments haven't quite kept up. It looks fine, but there are plenty of imperfections. Between misaligned heights and a lack of specific controls, I just haven't had the time or the will to dive into the YAML to fix these.

My 8GB laptop now runs an AI that can see and talk, and it never goes online

My M2 MacBook Air has 8GB of system memory, which is something that usually disqualifies it from running any particularly exciting local large language models. A local model that can see an image usually responds through text alone, and giving it the ability to hear, and a voice, usually means running separate models for each capability. Stacking three or four of them on an 8GB system is, understandably, a non-starter.

I gave my local AI model access to my personal documents, and it finally became more useful than a chatbot

Ever since chatbots came onto the map, they've gotten really efficient at working with documents. This is great for heavy workloads, but not so much for the documents you'd rather keep private, because now they end up on Google, Anthropic, or OpenAI servers. A health insurance policy nobody can make sense of, or a few months of bank statements, is where an AI could save real time, but it's also something you want to keep local.

I ran Codex inside Home Assistant, and having it next to my smart home changed how I code

I've been using AI coding agents for quite some time now, and they've made it much easier to build and experiment with projects that I wouldn't have attempted otherwise. But Home Assistant has always been a little different. Working on automations often requires you to copy YAML files, explain how different devices and entities are connected, and go back and forth between the agent and Home Assistant to test changes.

Someone recreated Photoshop with Claude, so I built a version that only does what I need

Just a few weeks ago, a developer decided he'd had enough of Adobe's subscription practices and took matters into his own hands. He used his 15 years of software engineering experience and a Claude Code subscription to recreate seven of Adobe's most popular Creative Cloud applications, including Photoshop, Premiere Pro, and Lightroom. He made all of these apps completely free and open-source.

I stopped trying to make one local LLM do everything, and that's when it got useful

Anyone running local models on a regular gaming GPU ends up making the same trade-off. An 8GB card has room for one decent model at a time, so whichever one is loaded handles every request that comes in that day, whether it suits the job or not. Smaller models tend to work faster but they can really struggle with heavy workloads or multi-step tasks. The obvious fix is loading something a little bigger, but then every quick question gets slower as the session grows.

I gave my local LLM a system prompt modeled on how Claude talks, and it stopped feeling like a cheap substitute

Local LLMs have pretty much one selling point that's hard to argue with: you own the entire workflow pipeline and get to keep everything private. But often, using one can still feel like a knockoff, because they need to run on your own machine instead of a data center. And if you have a regular mid-tier computer like most people, then you will probably get frustrated with local AI more often than not.

4 jobs my local AI handles for free that I would never trust with a cloud model

Lately, I've found myself ruminating about the privacy concerns surrounding sharing every bit of data with cloud AI service providers. I've previously talked about how AI chatbots, due to the nature of their platform, have access to far more user data than search engines ever did, and that makes them uniquely vulnerable. Frontier models are multimodal and take in text, images, documents, and even video, while a search engine only kept track of what a user was looking for.

I gave Gemini 4 Argon in Antigravity and Claude Code the same messy side project, and only one of them left it better than it found it

My favorite smart home gadget is a 2015 Amazon Kindle Paperwhite that is more useful than when it was new, thanks to a jailbreak and a Home Assistant dashboard. Its code was written for someone else's house, which makes it a perfect test for an AI coding agent. Google launched Gemini 4 Argon in Antigravity last month, and we've already argued that Antigravity 2.0 beats Claude Code and Codex at their own game. So I gave Argon and Claude Code the same repo, the same one-line brief, and an hour…

I replaced Grammarly Pro with a local model on my GPU, and my drafts never leave my PC

Month after month, it feels like we're getting close to what I'd call a subscription pandemic. Every other service demands a premium for a "Pro" or a "Premium" tier that drags down your balance on the first of every month and tries to get you hooked on its ecosystem. Over time, you're made to believe that the service you're paying for is an essential expense, and it earns a rather stubborn spot on your bank statement.

My local LLM turns my voice notes into to-do items automatically, and nothing falls through the cracks

My PC is usually a mess of windows, apps, browser tabs, and half-finished things I'm supposed to remember. In fact, if I had a dollar for every time a thought appeared while I was working only to disappear the next minute, I could probably hire an assistant to stay on top of every task for me. I'll think of something I need to do, tell myself I’ll get to it in a minute, and then spend the next hour wondering what it was.

I tried OpenClaw and Perplexity Computer, but ChatGPT Dots finally feels like a personal assistant

We've reached a pretty dystopian point where people will casually say they asked "Chat" a question, and everyone around them knows exactly who they're talking about. Not a friend, not a colleague, but an AI chatbot. Somehow, we've gone from Googling everything to treating ChatGPT like that one friend who knows a little bit about everything.